初始化项目，由ModelHub XC社区提供模型
Model: mesolitica/Malaysian-Llama-3.1-8B-Instruct Source: Original Platform
This commit is contained in:
ModelHub XC
65
.gitattributes
vendored
Normal file
65
.gitattributes
vendored
Normal file
@@ -0,0 +1,65 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
lora-embedding-128-llama3.1-8b-malaysian-8k/checkpoint-4800/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
lora-embedding-128-llama3.1-8b-malaysian-8k/checkpoint-1000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
lora-embedding-128-llama3.1-8b-malaysian-8k/checkpoint-2600/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
lora-embedding-128-llama3.1-8b-malaysian-8k/checkpoint-5200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
lora-embedding-128-llama3.1-8b-malaysian-8k/checkpoint-3600/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
lora-embedding-128-llama3.1-8b-malaysian-8k/checkpoint-2400/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
lora-embedding-128-llama3.1-8b-malaysian-8k/checkpoint-600/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
lora-embedding-128-llama3.1-8b-malaysian-8k/checkpoint-800/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
lora-embedding-128-llama3.1-8b-malaysian-8k/checkpoint-1400/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
lora-embedding-128-llama3.1-8b-malaysian-8k/checkpoint-2000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
lora-embedding-128-llama3.1-8b-malaysian-8k/checkpoint-1600/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
lora-embedding-128-llama3.1-8b-malaysian-8k/checkpoint-3400/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
lora-embedding-128-llama3.1-8b-malaysian-8k/checkpoint-5800/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
lora-embedding-128-llama3.1-8b-malaysian-8k/checkpoint-4400/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
lora-embedding-128-llama3.1-8b-malaysian-8k/checkpoint-4600/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
lora-embedding-128-llama3.1-8b-malaysian-8k/checkpoint-1800/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
lora-embedding-128-llama3.1-8b-malaysian-8k/checkpoint-200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
lora-embedding-128-llama3.1-8b-malaysian-8k/checkpoint-5000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
lora-embedding-128-llama3.1-8b-malaysian-8k/checkpoint-3200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
lora-embedding-128-llama3.1-8b-malaysian-8k/checkpoint-4000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
lora-embedding-128-llama3.1-8b-malaysian-8k/checkpoint-2800/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
lora-embedding-128-llama3.1-8b-malaysian-8k/checkpoint-5400/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
lora-embedding-128-llama3.1-8b-malaysian-8k/checkpoint-3800/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
lora-embedding-128-llama3.1-8b-malaysian-8k/checkpoint-400/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
lora-embedding-128-llama3.1-8b-malaysian-8k/checkpoint-2200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
lora-embedding-128-llama3.1-8b-malaysian-8k/checkpoint-4200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
lora-embedding-128-llama3.1-8b-malaysian-8k/checkpoint-1200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
lora-embedding-128-llama3.1-8b-malaysian-8k/checkpoint-5600/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
lora-embedding-128-llama3.1-8b-malaysian-8k/checkpoint-3000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
125
README.md
Normal file
125
README.md
Normal file
@@ -0,0 +1,125 @@
|
||||
---
|
||||
language:
|
||||
- ms
|
||||
- en
|
||||
- zh
|
||||
- ta
|
||||
---
|
||||
|
||||
# Malaysian Llama-3.1-8B-Instruct
|
||||
|
||||
Continue finetuning https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct on highly curated 1.5B tokens Malaysian instruction dataset.
|
||||
|
||||
## Improvement
|
||||
|
||||
1. Support respond in Mandarin, Tamil, Jawi, Manglish, Johor, Kedah, Kelantan, Pahang, Perak, Sabah, Sarawak, Selangor, Negeri Sembilan and Terengganu.
|
||||
2. Able to code in Mandarin, Tamil, Jawi, Manglish, Johor, Kedah, Kelantan, Pahang, Perak, Sabah, Sarawak, Selangor, Negeri Sembilan and Terengganu.
|
||||
3. Multi-turn Malaysian context such as related to Malaysian Legislation, politics, religions and languages.
|
||||
|
||||
## Training session
|
||||
|
||||
Finetune on [mesolitica/Malaysian-SFT](https://huggingface.co/datasets/mesolitica/Malaysian-SFT) to make the model understand Malaysian context.
|
||||
|
||||
## How we train
|
||||
|
||||
1. LoRA on `["q_proj", "k_proj", "v_proj", "o_proj", "gate_proj", "up_proj", "down_proj", "embed_tokens", "lm_head"]`.
|
||||
2. 128 Rank with alpha 256, or alpha of 2.0
|
||||
3. Multipacking 8192 context length with proper SDPA causal masking to prevent document contamination and also make sure proper position ids.
|
||||
4. Chunk CCE loss for LoRA.
|
||||
5. WanDB at https://wandb.ai/huseinzol05/lora-embedding-128-llama3.1-8b-malaysian-8k?nw=nwuserhuseinzol05
|
||||
|
||||
Source code at https://github.com/mesolitica/malaya/tree/master/session/llama3
|
||||
|
||||
## Benchmark
|
||||
|
||||
### MalayMMLU
|
||||
|
||||
#### Probability next tokens
|
||||
|
||||
Based on 0-shot official MalayMMLU First token accuracy,
|
||||
|
||||
```
|
||||
Model Accuracy shot by_letter category
|
||||
0 Malaysian-Llama-3.1-8B-Instruct 61.522718 0shot True STEM
|
||||
1 Malaysian-Llama-3.1-8B-Instruct 61.784351 0shot True Language
|
||||
2 Malaysian-Llama-3.1-8B-Instruct 60.610003 0shot True Social science
|
||||
3 Malaysian-Llama-3.1-8B-Instruct 60.254258 0shot True Others
|
||||
4 Malaysian-Llama-3.1-8B-Instruct 62.434585 0shot True Humanities
|
||||
{'Social science': 6918, 'Language': 6288, 'Humanities': 4395, 'Others': 4169, 'STEM': 2443}
|
||||
Model : Malaysian-Llama-3.1-8B-Instruct
|
||||
Metric : first
|
||||
Shot : 0shot
|
||||
average accuracy 61.276999958699875
|
||||
accuracy for STEM 61.522717969709376
|
||||
accuracy for Language 61.784351145038165
|
||||
accuracy for Social science 60.61000289100896
|
||||
accuracy for Others 60.254257615735185
|
||||
accuracy for Humanities 62.43458475540387
|
||||
```
|
||||
|
||||
While the original model,
|
||||
|
||||
```
|
||||
Model Accuracy shot by_letter category
|
||||
0 Llama-3.1-8B-Instruct 64.019648 0shot True STEM
|
||||
1 Llama-3.1-8B-Instruct 65.505725 0shot True Language
|
||||
2 Llama-3.1-8B-Instruct 62.604799 0shot True Social science
|
||||
3 Llama-3.1-8B-Instruct 62.197170 0shot True Others
|
||||
4 Llama-3.1-8B-Instruct 67.167235 0shot True Humanities
|
||||
{'Social science': 6918, 'Language': 6288, 'Humanities': 4395, 'Others': 4169, 'STEM': 2443}
|
||||
Model : Llama-3.1-8B-Instruct
|
||||
Metric : first
|
||||
Shot : 0shot
|
||||
average accuracy 64.25886920249452
|
||||
accuracy for STEM 64.0196479738027
|
||||
accuracy for Language 65.5057251908397
|
||||
accuracy for Social science 62.60479907487713
|
||||
accuracy for Others 62.197169585032384
|
||||
accuracy for Humanities 67.16723549488054
|
||||
```
|
||||
|
||||
#### First token match using vLLM
|
||||
|
||||
Based on 0-shot exact first token match using vLLM Guided Decoding,
|
||||
|
||||
```
|
||||
Model Accuracy shot category
|
||||
0 Malaysian-Llama-3.1-8B-Instruct 58.616455 0 STEM
|
||||
1 Malaysian-Llama-3.1-8B-Instruct 60.178117 0 Language
|
||||
2 Malaysian-Llama-3.1-8B-Instruct 57.213067 0 Social science
|
||||
3 Malaysian-Llama-3.1-8B-Instruct 56.896138 0 Others
|
||||
4 Malaysian-Llama-3.1-8B-Instruct 59.704209 0 Humanities
|
||||
Model : Malaysian-Llama-3.1-8B-Instruct
|
||||
Metric : full
|
||||
Shot : 0
|
||||
average accuracy 58.5222814190724
|
||||
accuracy for STEM 58.616455178059766
|
||||
accuracy for Language 60.17811704834606
|
||||
accuracy for Social science 57.213067360508816
|
||||
accuracy for Others 56.89613816262893
|
||||
accuracy for Humanities 59.70420932878271
|
||||
```
|
||||
|
||||
While the original model,
|
||||
|
||||
```
|
||||
Model Accuracy shot category
|
||||
0 Llama-3.1-8B-Instruct 58.739255 0 STEM
|
||||
1 Llama-3.1-8B-Instruct 61.577608 0 Language
|
||||
2 Llama-3.1-8B-Instruct 57.487713 0 Social science
|
||||
3 Llama-3.1-8B-Instruct 56.872152 0 Others
|
||||
4 Llama-3.1-8B-Instruct 63.890785 0 Humanities
|
||||
Model : Llama-3.1-8B-Instruct
|
||||
Metric : full
|
||||
Shot : 0
|
||||
average accuracy 59.73237517036303
|
||||
accuracy for STEM 58.73925501432665
|
||||
accuracy for Language 61.57760814249363
|
||||
accuracy for Social science 57.487713211910965
|
||||
accuracy for Others 56.872151595106736
|
||||
accuracy for Humanities 63.89078498293516
|
||||
```
|
||||
|
||||
## Acknowledgement
|
||||
|
||||
Special thanks to https://www.sns.com.my and Nvidia for 8x H100 node!
|
||||
39
config.json
Normal file
39
config.json
Normal file
@@ -0,0 +1,39 @@
|
||||
{
|
||||
"architectures": [
|
||||
"LlamaForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 128000,
|
||||
"eos_token_id": [
|
||||
128001,
|
||||
128008,
|
||||
128009
|
||||
],
|
||||
"head_dim": 128,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 4096,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 14336,
|
||||
"max_position_embeddings": 131072,
|
||||
"mlp_bias": false,
|
||||
"model_type": "llama",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 32,
|
||||
"num_key_value_heads": 8,
|
||||
"pretraining_tp": 1,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_scaling": {
|
||||
"factor": 8.0,
|
||||
"high_freq_factor": 4.0,
|
||||
"low_freq_factor": 1.0,
|
||||
"original_max_position_embeddings": 8192,
|
||||
"rope_type": "llama3"
|
||||
},
|
||||
"rope_theta": 500000.0,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.51.3",
|
||||
"use_cache": true,
|
||||
"vocab_size": 128256
|
||||
}
|
||||
12
generation_config.json
Normal file
12
generation_config.json
Normal file
@@ -0,0 +1,12 @@
|
||||
{
|
||||
"bos_token_id": 128000,
|
||||
"do_sample": true,
|
||||
"eos_token_id": [
|
||||
128001,
|
||||
128008,
|
||||
128009
|
||||
],
|
||||
"temperature": 0.6,
|
||||
"top_p": 0.9,
|
||||
"transformers_version": "4.51.3"
|
||||
}
|
||||
@@ -0,0 +1,202 @@
|
||||
---
|
||||
base_model: meta-llama/Llama-3.1-8B-Instruct
|
||||
library_name: peft
|
||||
---
|
||||
|
||||
# Model Card for Model ID
|
||||
|
||||
<!-- Provide a quick summary of what the model is/does. -->
|
||||
|
||||
|
||||
|
||||
## Model Details
|
||||
|
||||
### Model Description
|
||||
|
||||
<!-- Provide a longer summary of what this model is. -->
|
||||
|
||||
|
||||
|
||||
- **Developed by:** [More Information Needed]
|
||||
- **Funded by [optional]:** [More Information Needed]
|
||||
- **Shared by [optional]:** [More Information Needed]
|
||||
- **Model type:** [More Information Needed]
|
||||
- **Language(s) (NLP):** [More Information Needed]
|
||||
- **License:** [More Information Needed]
|
||||
- **Finetuned from model [optional]:** [More Information Needed]
|
||||
|
||||
### Model Sources [optional]
|
||||
|
||||
<!-- Provide the basic links for the model. -->
|
||||
|
||||
- **Repository:** [More Information Needed]
|
||||
- **Paper [optional]:** [More Information Needed]
|
||||
- **Demo [optional]:** [More Information Needed]
|
||||
|
||||
## Uses
|
||||
|
||||
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
||||
|
||||
### Direct Use
|
||||
|
||||
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Downstream Use [optional]
|
||||
|
||||
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Out-of-Scope Use
|
||||
|
||||
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Bias, Risks, and Limitations
|
||||
|
||||
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Recommendations
|
||||
|
||||
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
||||
|
||||
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
||||
|
||||
## How to Get Started with the Model
|
||||
|
||||
Use the code below to get started with the model.
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Training Details
|
||||
|
||||
### Training Data
|
||||
|
||||
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Training Procedure
|
||||
|
||||
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
||||
|
||||
#### Preprocessing [optional]
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
|
||||
#### Training Hyperparameters
|
||||
|
||||
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
||||
|
||||
#### Speeds, Sizes, Times [optional]
|
||||
|
||||
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Evaluation
|
||||
|
||||
<!-- This section describes the evaluation protocols and provides the results. -->
|
||||
|
||||
### Testing Data, Factors & Metrics
|
||||
|
||||
#### Testing Data
|
||||
|
||||
<!-- This should link to a Dataset Card if possible. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Factors
|
||||
|
||||
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Metrics
|
||||
|
||||
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Results
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Summary
|
||||
|
||||
|
||||
|
||||
## Model Examination [optional]
|
||||
|
||||
<!-- Relevant interpretability work for the model goes here -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Environmental Impact
|
||||
|
||||
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
||||
|
||||
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
||||
|
||||
- **Hardware Type:** [More Information Needed]
|
||||
- **Hours used:** [More Information Needed]
|
||||
- **Cloud Provider:** [More Information Needed]
|
||||
- **Compute Region:** [More Information Needed]
|
||||
- **Carbon Emitted:** [More Information Needed]
|
||||
|
||||
## Technical Specifications [optional]
|
||||
|
||||
### Model Architecture and Objective
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Compute Infrastructure
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Hardware
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Software
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Citation [optional]
|
||||
|
||||
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
||||
|
||||
**BibTeX:**
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
**APA:**
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Glossary [optional]
|
||||
|
||||
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## More Information [optional]
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Model Card Authors [optional]
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Model Card Contact
|
||||
|
||||
[More Information Needed]
|
||||
### Framework versions
|
||||
|
||||
- PEFT 0.15.2
|
||||
@@ -0,0 +1,41 @@
|
||||
{
|
||||
"alpha_pattern": {},
|
||||
"auto_mapping": null,
|
||||
"base_model_name_or_path": "meta-llama/Llama-3.1-8B-Instruct",
|
||||
"bias": "none",
|
||||
"corda_config": null,
|
||||
"eva_config": null,
|
||||
"exclude_modules": null,
|
||||
"fan_in_fan_out": false,
|
||||
"inference_mode": true,
|
||||
"init_lora_weights": true,
|
||||
"layer_replication": null,
|
||||
"layers_pattern": null,
|
||||
"layers_to_transform": null,
|
||||
"loftq_config": {},
|
||||
"lora_alpha": 256,
|
||||
"lora_bias": false,
|
||||
"lora_dropout": 0.0,
|
||||
"megatron_config": null,
|
||||
"megatron_core": "megatron.core",
|
||||
"modules_to_save": null,
|
||||
"peft_type": "LORA",
|
||||
"r": 128,
|
||||
"rank_pattern": {},
|
||||
"revision": null,
|
||||
"target_modules": [
|
||||
"o_proj",
|
||||
"up_proj",
|
||||
"k_proj",
|
||||
"down_proj",
|
||||
"lm_head",
|
||||
"gate_proj",
|
||||
"q_proj",
|
||||
"v_proj",
|
||||
"embed_tokens"
|
||||
],
|
||||
"task_type": "CAUSAL_LM",
|
||||
"trainable_token_indices": null,
|
||||
"use_dora": false,
|
||||
"use_rslora": false
|
||||
}
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:f918086fd00b4d1ef2183ca549efb803de3101ffc1506c52d9e44c7ec752d25c
|
||||
size 2840262376
|
||||
@@ -0,0 +1 @@
|
||||
global_step1000
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b48ada521fe4b56ddf8775cca5084d4f8c456ca1c9dd18ea1372724ec7aba6c2
|
||||
size 14960
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c6391b8235d35e272622a27f02c4433283fd14d4a3899e6b906252bf125a1d19
|
||||
size 14960
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:89469fb6657dc3b34c76c50e2680981449ddaf38706b7b93f9680bccc5dcbac2
|
||||
size 14960
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:2723e5e8a33d704326f806e4e3046e52ed976f05b0fc9312989ac37b552e46aa
|
||||
size 14960
|
||||
@@ -0,0 +1,16 @@
|
||||
{
|
||||
"bos_token": {
|
||||
"content": "<|begin_of_text|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "<|eot_id|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
BIN
lora-embedding-128-llama3.1-8b-malaysian-8k/checkpoint-1000/tokenizer.json
(Stored with Git LFS)
Normal file
BIN
lora-embedding-128-llama3.1-8b-malaysian-8k/checkpoint-1000/tokenizer.json
(Stored with Git LFS)
Normal file
Binary file not shown.
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:922c4272bf2cd66460df74f5c309b6b97e5e3f4c0ba57215852b5b38fbe927c2
|
||||
size 7800
|
||||
@@ -0,0 +1,760 @@
|
||||
#!/usr/bin/env python
|
||||
|
||||
# Copyright (c) Microsoft Corporation.
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
|
||||
# DeepSpeed Team
|
||||
|
||||
# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
|
||||
# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
|
||||
# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
|
||||
# application.
|
||||
#
|
||||
# example:
|
||||
# python zero_to_fp32.py . output_dir/
|
||||
# or
|
||||
# python zero_to_fp32.py . output_dir/ --safe_serialization
|
||||
|
||||
import argparse
|
||||
import torch
|
||||
import glob
|
||||
import math
|
||||
import os
|
||||
import re
|
||||
import gc
|
||||
import json
|
||||
import numpy as np
|
||||
from tqdm import tqdm
|
||||
from collections import OrderedDict
|
||||
from dataclasses import dataclass
|
||||
|
||||
# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
|
||||
# DeepSpeed data structures it has to be available in the current python environment.
|
||||
from deepspeed.utils import logger
|
||||
from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
|
||||
FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
|
||||
FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
|
||||
|
||||
|
||||
@dataclass
|
||||
class zero_model_state:
|
||||
buffers: dict()
|
||||
param_shapes: dict()
|
||||
shared_params: list
|
||||
ds_version: int
|
||||
frozen_param_shapes: dict()
|
||||
frozen_param_fragments: dict()
|
||||
|
||||
|
||||
debug = 0
|
||||
|
||||
# load to cpu
|
||||
device = torch.device('cpu')
|
||||
|
||||
|
||||
def atoi(text):
|
||||
return int(text) if text.isdigit() else text
|
||||
|
||||
|
||||
def natural_keys(text):
|
||||
'''
|
||||
alist.sort(key=natural_keys) sorts in human order
|
||||
http://nedbatchelder.com/blog/200712/human_sorting.html
|
||||
(See Toothy's implementation in the comments)
|
||||
'''
|
||||
return [atoi(c) for c in re.split(r'(\d+)', text)]
|
||||
|
||||
|
||||
def get_model_state_file(checkpoint_dir, zero_stage):
|
||||
if not os.path.isdir(checkpoint_dir):
|
||||
raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
|
||||
|
||||
# there should be only one file
|
||||
if zero_stage <= 2:
|
||||
file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
|
||||
elif zero_stage == 3:
|
||||
file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
|
||||
|
||||
if not os.path.exists(file):
|
||||
raise FileNotFoundError(f"can't find model states file at '{file}'")
|
||||
|
||||
return file
|
||||
|
||||
|
||||
def get_checkpoint_files(checkpoint_dir, glob_pattern):
|
||||
# XXX: need to test that this simple glob rule works for multi-node setup too
|
||||
ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
|
||||
|
||||
if len(ckpt_files) == 0:
|
||||
raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
|
||||
|
||||
return ckpt_files
|
||||
|
||||
|
||||
def get_optim_files(checkpoint_dir):
|
||||
return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
|
||||
|
||||
|
||||
def get_model_state_files(checkpoint_dir):
|
||||
return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
|
||||
|
||||
|
||||
def parse_model_states(files):
|
||||
zero_model_states = []
|
||||
for file in files:
|
||||
state_dict = torch.load(file, map_location=device, weights_only=False)
|
||||
|
||||
if BUFFER_NAMES not in state_dict:
|
||||
raise ValueError(f"{file} is not a model state checkpoint")
|
||||
buffer_names = state_dict[BUFFER_NAMES]
|
||||
if debug:
|
||||
print("Found buffers:", buffer_names)
|
||||
|
||||
# recover just the buffers while restoring them to fp32 if they were saved in fp16
|
||||
buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
|
||||
param_shapes = state_dict[PARAM_SHAPES]
|
||||
|
||||
# collect parameters that are included in param_shapes
|
||||
param_names = []
|
||||
for s in param_shapes:
|
||||
for name in s.keys():
|
||||
param_names.append(name)
|
||||
|
||||
# update with frozen parameters
|
||||
frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
|
||||
if frozen_param_shapes is not None:
|
||||
if debug:
|
||||
print(f"Found frozen_param_shapes: {frozen_param_shapes}")
|
||||
param_names += list(frozen_param_shapes.keys())
|
||||
|
||||
# handle shared params
|
||||
shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
|
||||
|
||||
ds_version = state_dict.get(DS_VERSION, None)
|
||||
|
||||
frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
|
||||
|
||||
z_model_state = zero_model_state(buffers=buffers,
|
||||
param_shapes=param_shapes,
|
||||
shared_params=shared_params,
|
||||
ds_version=ds_version,
|
||||
frozen_param_shapes=frozen_param_shapes,
|
||||
frozen_param_fragments=frozen_param_fragments)
|
||||
zero_model_states.append(z_model_state)
|
||||
|
||||
return zero_model_states
|
||||
|
||||
|
||||
def parse_optim_states(files, ds_checkpoint_dir):
|
||||
total_files = len(files)
|
||||
state_dicts = []
|
||||
for f in tqdm(files, desc='Loading checkpoint shards'):
|
||||
state_dict = torch.load(f, map_location=device, mmap=True, weights_only=False)
|
||||
# immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
|
||||
# and also handle the case where it was already removed by another helper script
|
||||
state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
|
||||
state_dicts.append(state_dict)
|
||||
|
||||
if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
|
||||
raise ValueError(f"{files[0]} is not a zero checkpoint")
|
||||
zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
|
||||
world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
|
||||
|
||||
# For ZeRO-2 each param group can have different partition_count as data parallelism for expert
|
||||
# parameters can be different from data parallelism for non-expert parameters. So we can just
|
||||
# use the max of the partition_count to get the dp world_size.
|
||||
|
||||
if type(world_size) is list:
|
||||
world_size = max(world_size)
|
||||
|
||||
if world_size != total_files:
|
||||
raise ValueError(
|
||||
f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
|
||||
"Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
|
||||
)
|
||||
|
||||
# the groups are named differently in each stage
|
||||
if zero_stage <= 2:
|
||||
fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
|
||||
elif zero_stage == 3:
|
||||
fp32_groups_key = FP32_FLAT_GROUPS
|
||||
else:
|
||||
raise ValueError(f"unknown zero stage {zero_stage}")
|
||||
|
||||
fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
|
||||
return zero_stage, world_size, fp32_flat_groups
|
||||
|
||||
|
||||
def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
|
||||
"""
|
||||
Returns fp32 state_dict reconstructed from ds checkpoint
|
||||
|
||||
Args:
|
||||
- ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
|
||||
|
||||
"""
|
||||
print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
|
||||
|
||||
optim_files = get_optim_files(ds_checkpoint_dir)
|
||||
zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
|
||||
print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
|
||||
|
||||
model_files = get_model_state_files(ds_checkpoint_dir)
|
||||
|
||||
zero_model_states = parse_model_states(model_files)
|
||||
print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
|
||||
|
||||
if zero_stage <= 2:
|
||||
return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
||||
exclude_frozen_parameters)
|
||||
elif zero_stage == 3:
|
||||
return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
||||
exclude_frozen_parameters)
|
||||
|
||||
|
||||
def _zero2_merge_frozen_params(state_dict, zero_model_states):
|
||||
if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
|
||||
return
|
||||
|
||||
frozen_param_shapes = zero_model_states[0].frozen_param_shapes
|
||||
frozen_param_fragments = zero_model_states[0].frozen_param_fragments
|
||||
|
||||
if debug:
|
||||
num_elem = sum(s.numel() for s in frozen_param_shapes.values())
|
||||
print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
|
||||
|
||||
wanted_params = len(frozen_param_shapes)
|
||||
wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
|
||||
avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
|
||||
print(f'Frozen params: Have {avail_numel} numels to process.')
|
||||
print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
|
||||
|
||||
total_params = 0
|
||||
total_numel = 0
|
||||
for name, shape in frozen_param_shapes.items():
|
||||
total_params += 1
|
||||
unpartitioned_numel = shape.numel()
|
||||
total_numel += unpartitioned_numel
|
||||
|
||||
state_dict[name] = frozen_param_fragments[name]
|
||||
|
||||
if debug:
|
||||
print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
|
||||
|
||||
print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
|
||||
|
||||
|
||||
def _has_callable(obj, fn):
|
||||
attr = getattr(obj, fn, None)
|
||||
return callable(attr)
|
||||
|
||||
|
||||
def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
|
||||
param_shapes = zero_model_states[0].param_shapes
|
||||
|
||||
# Reconstruction protocol:
|
||||
#
|
||||
# XXX: document this
|
||||
|
||||
if debug:
|
||||
for i in range(world_size):
|
||||
for j in range(len(fp32_flat_groups[0])):
|
||||
print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
|
||||
|
||||
# XXX: memory usage doubles here (zero2)
|
||||
num_param_groups = len(fp32_flat_groups[0])
|
||||
merged_single_partition_of_fp32_groups = []
|
||||
for i in range(num_param_groups):
|
||||
merged_partitions = [sd[i] for sd in fp32_flat_groups]
|
||||
full_single_fp32_vector = torch.cat(merged_partitions, 0)
|
||||
merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
|
||||
avail_numel = sum(
|
||||
[full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
|
||||
|
||||
if debug:
|
||||
wanted_params = sum([len(shapes) for shapes in param_shapes])
|
||||
wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
|
||||
# not asserting if there is a mismatch due to possible padding
|
||||
print(f"Have {avail_numel} numels to process.")
|
||||
print(f"Need {wanted_numel} numels in {wanted_params} params.")
|
||||
|
||||
# params
|
||||
# XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
|
||||
# out-of-core computing solution
|
||||
total_numel = 0
|
||||
total_params = 0
|
||||
for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
|
||||
offset = 0
|
||||
avail_numel = full_single_fp32_vector.numel()
|
||||
for name, shape in shapes.items():
|
||||
|
||||
unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
|
||||
total_numel += unpartitioned_numel
|
||||
total_params += 1
|
||||
|
||||
if debug:
|
||||
print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
|
||||
state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
|
||||
offset += unpartitioned_numel
|
||||
|
||||
# Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
|
||||
# avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
|
||||
# paddings performed in the code it's almost impossible to predict the exact numbers w/o the
|
||||
# live optimizer object, so we are checking that the numbers are within the right range
|
||||
align_to = 2 * world_size
|
||||
|
||||
def zero2_align(x):
|
||||
return align_to * math.ceil(x / align_to)
|
||||
|
||||
if debug:
|
||||
print(f"original offset={offset}, avail_numel={avail_numel}")
|
||||
|
||||
offset = zero2_align(offset)
|
||||
avail_numel = zero2_align(avail_numel)
|
||||
|
||||
if debug:
|
||||
print(f"aligned offset={offset}, avail_numel={avail_numel}")
|
||||
|
||||
# Sanity check
|
||||
if offset != avail_numel:
|
||||
raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
|
||||
|
||||
print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
|
||||
|
||||
|
||||
def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
||||
exclude_frozen_parameters):
|
||||
state_dict = OrderedDict()
|
||||
|
||||
# buffers
|
||||
buffers = zero_model_states[0].buffers
|
||||
state_dict.update(buffers)
|
||||
if debug:
|
||||
print(f"added {len(buffers)} buffers")
|
||||
|
||||
if not exclude_frozen_parameters:
|
||||
_zero2_merge_frozen_params(state_dict, zero_model_states)
|
||||
|
||||
_zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
|
||||
|
||||
# recover shared parameters
|
||||
for pair in zero_model_states[0].shared_params:
|
||||
if pair[1] in state_dict:
|
||||
state_dict[pair[0]] = state_dict[pair[1]]
|
||||
|
||||
return state_dict
|
||||
|
||||
|
||||
def zero3_partitioned_param_info(unpartitioned_numel, world_size):
|
||||
remainder = unpartitioned_numel % world_size
|
||||
padding_numel = (world_size - remainder) if remainder else 0
|
||||
partitioned_numel = math.ceil(unpartitioned_numel / world_size)
|
||||
return partitioned_numel, padding_numel
|
||||
|
||||
|
||||
def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
|
||||
if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
|
||||
return
|
||||
|
||||
if debug:
|
||||
for i in range(world_size):
|
||||
num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
|
||||
print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
|
||||
|
||||
frozen_param_shapes = zero_model_states[0].frozen_param_shapes
|
||||
wanted_params = len(frozen_param_shapes)
|
||||
wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
|
||||
avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
|
||||
print(f'Frozen params: Have {avail_numel} numels to process.')
|
||||
print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
|
||||
|
||||
total_params = 0
|
||||
total_numel = 0
|
||||
for name, shape in zero_model_states[0].frozen_param_shapes.items():
|
||||
total_params += 1
|
||||
unpartitioned_numel = shape.numel()
|
||||
total_numel += unpartitioned_numel
|
||||
|
||||
param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
|
||||
state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
|
||||
|
||||
partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
|
||||
|
||||
if debug:
|
||||
print(
|
||||
f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
|
||||
)
|
||||
|
||||
print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
|
||||
|
||||
|
||||
class GatheredTensor:
|
||||
"""
|
||||
A pseudo tensor that collects partitioned weights.
|
||||
It is more memory efficient when there are multiple groups.
|
||||
"""
|
||||
|
||||
def __init__(self, flat_groups, flat_groups_offset, offset, partitioned_numel, shape):
|
||||
self.flat_groups = flat_groups
|
||||
self.flat_groups_offset = flat_groups_offset
|
||||
self.offset = offset
|
||||
self.partitioned_numel = partitioned_numel
|
||||
self.shape = shape
|
||||
self.dtype = self.flat_groups[0][0].dtype
|
||||
|
||||
def contiguous(self):
|
||||
"""
|
||||
Merge partitioned weights from flat_groups into a single tensor.
|
||||
"""
|
||||
end_idx = self.offset + self.partitioned_numel
|
||||
world_size = len(self.flat_groups)
|
||||
pad_flat_param_chunks = []
|
||||
|
||||
for rank_i in range(world_size):
|
||||
# for each rank, we need to collect weights from related group/groups
|
||||
flat_groups_at_rank_i = self.flat_groups[rank_i]
|
||||
start_group_id = None
|
||||
end_group_id = None
|
||||
for group_id in range(len(self.flat_groups_offset)):
|
||||
if self.flat_groups_offset[group_id] <= self.offset < self.flat_groups_offset[group_id + 1]:
|
||||
start_group_id = group_id
|
||||
if self.flat_groups_offset[group_id] < end_idx <= self.flat_groups_offset[group_id + 1]:
|
||||
end_group_id = group_id
|
||||
break
|
||||
# collect weights from related group/groups
|
||||
for group_id in range(start_group_id, end_group_id + 1):
|
||||
flat_tensor = flat_groups_at_rank_i[group_id]
|
||||
start_offset = self.offset - self.flat_groups_offset[group_id]
|
||||
end_offset = min(end_idx, self.flat_groups_offset[group_id + 1]) - self.flat_groups_offset[group_id]
|
||||
pad_flat_param_chunks.append(flat_tensor[start_offset:end_offset])
|
||||
|
||||
# collect weights from all ranks
|
||||
pad_flat_param = torch.cat(pad_flat_param_chunks, dim=0)
|
||||
param = pad_flat_param[:self.shape.numel()].view(self.shape).contiguous()
|
||||
return param
|
||||
|
||||
|
||||
def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
|
||||
param_shapes = zero_model_states[0].param_shapes
|
||||
avail_numel = sum([flat_group.numel() for flat_group in fp32_flat_groups[0]]) * world_size
|
||||
|
||||
# Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
|
||||
# param, re-consolidating each param, while dealing with padding if any
|
||||
|
||||
# merge list of dicts, preserving order
|
||||
param_shapes = {k: v for d in param_shapes for k, v in d.items()}
|
||||
|
||||
if debug:
|
||||
for i in range(world_size):
|
||||
print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
|
||||
|
||||
wanted_params = len(param_shapes)
|
||||
wanted_numel = sum(shape.numel() for shape in param_shapes.values())
|
||||
# not asserting if there is a mismatch due to possible padding
|
||||
avail_numel = fp32_flat_groups[0].numel() * world_size
|
||||
print(f"Trainable params: Have {avail_numel} numels to process.")
|
||||
print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
|
||||
|
||||
# params
|
||||
# XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
|
||||
# out-of-core computing solution
|
||||
offset = 0
|
||||
total_numel = 0
|
||||
total_params = 0
|
||||
flat_groups_offset = [0] + list(np.cumsum([flat_tensor.numel() for flat_tensor in fp32_flat_groups[0]]))
|
||||
for name, shape in tqdm(param_shapes.items(), desc='Gathering sharded weights'):
|
||||
unpartitioned_numel = shape.numel()
|
||||
total_numel += unpartitioned_numel
|
||||
total_params += 1
|
||||
partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
|
||||
|
||||
if debug:
|
||||
print(
|
||||
f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
|
||||
)
|
||||
|
||||
# memory efficient tensor
|
||||
tensor = GatheredTensor(fp32_flat_groups, flat_groups_offset, offset, partitioned_numel, shape)
|
||||
state_dict[name] = tensor
|
||||
offset += partitioned_numel
|
||||
|
||||
offset *= world_size
|
||||
|
||||
# Sanity check
|
||||
if offset != avail_numel:
|
||||
raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
|
||||
|
||||
print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
|
||||
|
||||
|
||||
def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
||||
exclude_frozen_parameters):
|
||||
state_dict = OrderedDict()
|
||||
|
||||
# buffers
|
||||
buffers = zero_model_states[0].buffers
|
||||
state_dict.update(buffers)
|
||||
if debug:
|
||||
print(f"added {len(buffers)} buffers")
|
||||
|
||||
if not exclude_frozen_parameters:
|
||||
_zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
|
||||
|
||||
_zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
|
||||
|
||||
# recover shared parameters
|
||||
for pair in zero_model_states[0].shared_params:
|
||||
if pair[1] in state_dict:
|
||||
state_dict[pair[0]] = state_dict[pair[1]]
|
||||
|
||||
return state_dict
|
||||
|
||||
|
||||
def to_torch_tensor(state_dict, return_empty_tensor=False):
|
||||
"""
|
||||
Convert state_dict of GatheredTensor to torch tensor
|
||||
"""
|
||||
torch_state_dict = {}
|
||||
converted_tensors = {}
|
||||
for name, tensor in state_dict.items():
|
||||
tensor_id = id(tensor)
|
||||
if tensor_id in converted_tensors: # shared tensors
|
||||
shared_tensor = torch_state_dict[converted_tensors[tensor_id]]
|
||||
torch_state_dict[name] = shared_tensor
|
||||
else:
|
||||
converted_tensors[tensor_id] = name
|
||||
if return_empty_tensor:
|
||||
torch_state_dict[name] = torch.empty(tensor.shape, dtype=tensor.dtype)
|
||||
else:
|
||||
torch_state_dict[name] = tensor.contiguous()
|
||||
return torch_state_dict
|
||||
|
||||
|
||||
def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
|
||||
tag=None,
|
||||
exclude_frozen_parameters=False,
|
||||
lazy_mode=False):
|
||||
"""
|
||||
Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
|
||||
``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
|
||||
via a model hub.
|
||||
|
||||
Args:
|
||||
- ``checkpoint_dir``: path to the desired checkpoint folder
|
||||
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
|
||||
- ``exclude_frozen_parameters``: exclude frozen parameters
|
||||
- ``lazy_mode``: get state_dict in lazy mode. It returns a dict of pesduo tensor instead of torch tensor, which is more memory efficient.
|
||||
Convert the pesduo tensor to torch tensor by ``.contiguous()``
|
||||
|
||||
Returns:
|
||||
- pytorch ``state_dict``
|
||||
|
||||
A typical usage might be ::
|
||||
|
||||
from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
|
||||
# do the training and checkpoint saving
|
||||
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
|
||||
model = model.cpu() # move to cpu
|
||||
model.load_state_dict(state_dict)
|
||||
# submit to model hub or save the model to share with others
|
||||
|
||||
In this example the ``model`` will no longer be usable in the deepspeed context of the same
|
||||
application. i.e. you will need to re-initialize the deepspeed engine, since
|
||||
``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
|
||||
|
||||
If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
|
||||
|
||||
Note: the above usage may not work if your application doesn't have sufficient free CPU memory.
|
||||
You may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
|
||||
the checkpoint. Or you can load state_dict in lazy mode ::
|
||||
|
||||
from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
|
||||
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, lazy_mode=True) # not on cpu
|
||||
for name, lazy_tensor in state_dict.item():
|
||||
tensor = lazy_tensor.contiguous() # to cpu
|
||||
print(name, tensor)
|
||||
# del tensor to release memory if it no longer in use
|
||||
"""
|
||||
if tag is None:
|
||||
latest_path = os.path.join(checkpoint_dir, 'latest')
|
||||
if os.path.isfile(latest_path):
|
||||
with open(latest_path, 'r') as fd:
|
||||
tag = fd.read().strip()
|
||||
else:
|
||||
raise ValueError(f"Unable to find 'latest' file at {latest_path}")
|
||||
|
||||
ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
|
||||
|
||||
if not os.path.isdir(ds_checkpoint_dir):
|
||||
raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
|
||||
|
||||
state_dict = _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
|
||||
if lazy_mode:
|
||||
return state_dict
|
||||
else:
|
||||
return to_torch_tensor(state_dict)
|
||||
|
||||
|
||||
def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir,
|
||||
output_dir,
|
||||
max_shard_size="5GB",
|
||||
safe_serialization=False,
|
||||
tag=None,
|
||||
exclude_frozen_parameters=False):
|
||||
"""
|
||||
Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
|
||||
loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
|
||||
|
||||
Args:
|
||||
- ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
|
||||
- ``output_dir``: directory to the pytorch fp32 state_dict output files
|
||||
- ``max_shard_size``: the maximum size for a checkpoint before being sharded, default value is 5GB
|
||||
- ``safe_serialization``: whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).
|
||||
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
|
||||
- ``exclude_frozen_parameters``: exclude frozen parameters
|
||||
"""
|
||||
|
||||
# Dependency pre-check
|
||||
if safe_serialization:
|
||||
try:
|
||||
from safetensors.torch import save_file
|
||||
except ImportError:
|
||||
print('If you want to use `safe_serialization`, please `pip install safetensors`')
|
||||
raise
|
||||
if max_shard_size is not None:
|
||||
try:
|
||||
from huggingface_hub import split_torch_state_dict_into_shards
|
||||
except ImportError:
|
||||
print('If you want to use `max_shard_size`, please `pip install huggingface_hub`')
|
||||
raise
|
||||
|
||||
# Convert zero checkpoint to state_dict
|
||||
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
|
||||
tag,
|
||||
exclude_frozen_parameters,
|
||||
lazy_mode=True)
|
||||
|
||||
# Shard the model if it is too big.
|
||||
weights_name = "model.safetensors" if safe_serialization else "pytorch_model.bin"
|
||||
if max_shard_size is not None:
|
||||
filename_pattern = weights_name.replace(".bin", "{suffix}.bin").replace(".safetensors", "{suffix}.safetensors")
|
||||
# an memory-efficient approach for sharding
|
||||
empty_state_dict = to_torch_tensor(state_dict, return_empty_tensor=True)
|
||||
state_dict_split = split_torch_state_dict_into_shards(empty_state_dict,
|
||||
filename_pattern=filename_pattern,
|
||||
max_shard_size=max_shard_size)
|
||||
else:
|
||||
from collections import namedtuple
|
||||
StateDictSplit = namedtuple("StateDictSplit", ["is_sharded", "filename_to_tensors"])
|
||||
state_dict_split = StateDictSplit(is_sharded=False,
|
||||
filename_to_tensors={weights_name: list(state_dict.keys())})
|
||||
|
||||
# Save the model by shard
|
||||
os.makedirs(output_dir, exist_ok=True)
|
||||
filename_to_tensors = state_dict_split.filename_to_tensors.items()
|
||||
for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"):
|
||||
shard_state_dict = {tensor_name: state_dict[tensor_name] for tensor_name in tensors}
|
||||
shard_state_dict = to_torch_tensor(shard_state_dict)
|
||||
output_path = os.path.join(output_dir, shard_file)
|
||||
if safe_serialization:
|
||||
save_file(shard_state_dict, output_path, metadata={"format": "pt"})
|
||||
else:
|
||||
torch.save(shard_state_dict, output_path)
|
||||
# release the memory of current shard
|
||||
for tensor_name in list(shard_state_dict.keys()):
|
||||
del state_dict[tensor_name]
|
||||
del shard_state_dict[tensor_name]
|
||||
del shard_state_dict
|
||||
gc.collect()
|
||||
|
||||
# Save index if sharded
|
||||
if state_dict_split.is_sharded:
|
||||
index = {
|
||||
"metadata": state_dict_split.metadata,
|
||||
"weight_map": state_dict_split.tensor_to_filename,
|
||||
}
|
||||
save_index_file = "model.safetensors.index.json" if safe_serialization else "pytorch_model.bin.index.json"
|
||||
save_index_file = os.path.join(output_dir, save_index_file)
|
||||
with open(save_index_file, "w", encoding="utf-8") as f:
|
||||
content = json.dumps(index, indent=2, sort_keys=True) + "\n"
|
||||
f.write(content)
|
||||
|
||||
|
||||
def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
|
||||
"""
|
||||
1. Put the provided model to cpu
|
||||
2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
|
||||
3. Load it into the provided model
|
||||
|
||||
Args:
|
||||
- ``model``: the model object to update
|
||||
- ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
|
||||
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
|
||||
|
||||
Returns:
|
||||
- ``model`: modified model
|
||||
|
||||
Make sure you have plenty of CPU memory available before you call this function. If you don't
|
||||
have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
|
||||
conveniently placed for you in the checkpoint folder.
|
||||
|
||||
A typical usage might be ::
|
||||
|
||||
from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
|
||||
model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
|
||||
# submit to model hub or save the model to share with others
|
||||
|
||||
Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
|
||||
of the same application. i.e. you will need to re-initialize the deepspeed engine, since
|
||||
``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
|
||||
|
||||
"""
|
||||
logger.info(f"Extracting fp32 weights")
|
||||
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
|
||||
|
||||
logger.info(f"Overwriting model with fp32 weights")
|
||||
model = model.cpu()
|
||||
model.load_state_dict(state_dict, strict=False)
|
||||
|
||||
return model
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
parser = argparse.ArgumentParser()
|
||||
parser.add_argument("checkpoint_dir",
|
||||
type=str,
|
||||
help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
|
||||
parser.add_argument("output_dir",
|
||||
type=str,
|
||||
help="directory to the pytorch fp32 state_dict output files"
|
||||
"(e.g. path/checkpoint-12-output/)")
|
||||
parser.add_argument(
|
||||
"--max_shard_size",
|
||||
type=str,
|
||||
default="5GB",
|
||||
help="The maximum size for a checkpoint before being sharded. Checkpoints shard will then be each of size"
|
||||
"lower than this size. If expressed as a string, needs to be digits followed by a unit (like `5MB`"
|
||||
"We default it to 5GB in order for models to be able to run easily on free-tier google colab instances"
|
||||
"without CPU OOM issues.")
|
||||
parser.add_argument(
|
||||
"--safe_serialization",
|
||||
default=False,
|
||||
action='store_true',
|
||||
help="Whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).")
|
||||
parser.add_argument("-t",
|
||||
"--tag",
|
||||
type=str,
|
||||
default=None,
|
||||
help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
|
||||
parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
|
||||
parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
|
||||
args = parser.parse_args()
|
||||
|
||||
debug = args.debug
|
||||
|
||||
convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
|
||||
args.output_dir,
|
||||
max_shard_size=args.max_shard_size,
|
||||
safe_serialization=args.safe_serialization,
|
||||
tag=args.tag,
|
||||
exclude_frozen_parameters=args.exclude_frozen_parameters)
|
||||
@@ -0,0 +1,202 @@
|
||||
---
|
||||
base_model: meta-llama/Llama-3.1-8B-Instruct
|
||||
library_name: peft
|
||||
---
|
||||
|
||||
# Model Card for Model ID
|
||||
|
||||
<!-- Provide a quick summary of what the model is/does. -->
|
||||
|
||||
|
||||
|
||||
## Model Details
|
||||
|
||||
### Model Description
|
||||
|
||||
<!-- Provide a longer summary of what this model is. -->
|
||||
|
||||
|
||||
|
||||
- **Developed by:** [More Information Needed]
|
||||
- **Funded by [optional]:** [More Information Needed]
|
||||
- **Shared by [optional]:** [More Information Needed]
|
||||
- **Model type:** [More Information Needed]
|
||||
- **Language(s) (NLP):** [More Information Needed]
|
||||
- **License:** [More Information Needed]
|
||||
- **Finetuned from model [optional]:** [More Information Needed]
|
||||
|
||||
### Model Sources [optional]
|
||||
|
||||
<!-- Provide the basic links for the model. -->
|
||||
|
||||
- **Repository:** [More Information Needed]
|
||||
- **Paper [optional]:** [More Information Needed]
|
||||
- **Demo [optional]:** [More Information Needed]
|
||||
|
||||
## Uses
|
||||
|
||||
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
||||
|
||||
### Direct Use
|
||||
|
||||
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Downstream Use [optional]
|
||||
|
||||
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Out-of-Scope Use
|
||||
|
||||
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Bias, Risks, and Limitations
|
||||
|
||||
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Recommendations
|
||||
|
||||
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
||||
|
||||
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
||||
|
||||
## How to Get Started with the Model
|
||||
|
||||
Use the code below to get started with the model.
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Training Details
|
||||
|
||||
### Training Data
|
||||
|
||||
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Training Procedure
|
||||
|
||||
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
||||
|
||||
#### Preprocessing [optional]
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
|
||||
#### Training Hyperparameters
|
||||
|
||||
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
||||
|
||||
#### Speeds, Sizes, Times [optional]
|
||||
|
||||
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Evaluation
|
||||
|
||||
<!-- This section describes the evaluation protocols and provides the results. -->
|
||||
|
||||
### Testing Data, Factors & Metrics
|
||||
|
||||
#### Testing Data
|
||||
|
||||
<!-- This should link to a Dataset Card if possible. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Factors
|
||||
|
||||
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Metrics
|
||||
|
||||
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Results
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Summary
|
||||
|
||||
|
||||
|
||||
## Model Examination [optional]
|
||||
|
||||
<!-- Relevant interpretability work for the model goes here -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Environmental Impact
|
||||
|
||||
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
||||
|
||||
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
||||
|
||||
- **Hardware Type:** [More Information Needed]
|
||||
- **Hours used:** [More Information Needed]
|
||||
- **Cloud Provider:** [More Information Needed]
|
||||
- **Compute Region:** [More Information Needed]
|
||||
- **Carbon Emitted:** [More Information Needed]
|
||||
|
||||
## Technical Specifications [optional]
|
||||
|
||||
### Model Architecture and Objective
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Compute Infrastructure
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Hardware
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Software
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Citation [optional]
|
||||
|
||||
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
||||
|
||||
**BibTeX:**
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
**APA:**
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Glossary [optional]
|
||||
|
||||
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## More Information [optional]
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Model Card Authors [optional]
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Model Card Contact
|
||||
|
||||
[More Information Needed]
|
||||
### Framework versions
|
||||
|
||||
- PEFT 0.15.2
|
||||
@@ -0,0 +1,41 @@
|
||||
{
|
||||
"alpha_pattern": {},
|
||||
"auto_mapping": null,
|
||||
"base_model_name_or_path": "meta-llama/Llama-3.1-8B-Instruct",
|
||||
"bias": "none",
|
||||
"corda_config": null,
|
||||
"eva_config": null,
|
||||
"exclude_modules": null,
|
||||
"fan_in_fan_out": false,
|
||||
"inference_mode": true,
|
||||
"init_lora_weights": true,
|
||||
"layer_replication": null,
|
||||
"layers_pattern": null,
|
||||
"layers_to_transform": null,
|
||||
"loftq_config": {},
|
||||
"lora_alpha": 256,
|
||||
"lora_bias": false,
|
||||
"lora_dropout": 0.0,
|
||||
"megatron_config": null,
|
||||
"megatron_core": "megatron.core",
|
||||
"modules_to_save": null,
|
||||
"peft_type": "LORA",
|
||||
"r": 128,
|
||||
"rank_pattern": {},
|
||||
"revision": null,
|
||||
"target_modules": [
|
||||
"o_proj",
|
||||
"up_proj",
|
||||
"k_proj",
|
||||
"down_proj",
|
||||
"lm_head",
|
||||
"gate_proj",
|
||||
"q_proj",
|
||||
"v_proj",
|
||||
"embed_tokens"
|
||||
],
|
||||
"task_type": "CAUSAL_LM",
|
||||
"trainable_token_indices": null,
|
||||
"use_dora": false,
|
||||
"use_rslora": false
|
||||
}
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:4699789e7e7c790abbc846a9f630baeb5fed556c1d06a8487a31c537df2a54b9
|
||||
size 2840262376
|
||||
@@ -0,0 +1 @@
|
||||
global_step1200
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:9e33eafdb0152b8343d06ece3665066b1007292d854f01b7944833a07faa7292
|
||||
size 14960
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:ad08f16e319ba5ef0331888378ae78bb447716be72dec2578593d169e431b15f
|
||||
size 14960
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:7dd3fa2fc05788df16d0ed01e300367f5f9d74f02bace9bbbb185dc32285ba38
|
||||
size 14960
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:02a828e28876a96a5d1b1851cb8e61a4cd1cb492d9adc75259ac32b40cdf7468
|
||||
size 14960
|
||||
@@ -0,0 +1,16 @@
|
||||
{
|
||||
"bos_token": {
|
||||
"content": "<|begin_of_text|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "<|eot_id|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
BIN
lora-embedding-128-llama3.1-8b-malaysian-8k/checkpoint-1200/tokenizer.json
(Stored with Git LFS)
Normal file
BIN
lora-embedding-128-llama3.1-8b-malaysian-8k/checkpoint-1200/tokenizer.json
(Stored with Git LFS)
Normal file
Binary file not shown.
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:922c4272bf2cd66460df74f5c309b6b97e5e3f4c0ba57215852b5b38fbe927c2
|
||||
size 7800
|
||||
@@ -0,0 +1,760 @@
|
||||
#!/usr/bin/env python
|
||||
|
||||
# Copyright (c) Microsoft Corporation.
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
|
||||
# DeepSpeed Team
|
||||
|
||||
# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
|
||||
# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
|
||||
# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
|
||||
# application.
|
||||
#
|
||||
# example:
|
||||
# python zero_to_fp32.py . output_dir/
|
||||
# or
|
||||
# python zero_to_fp32.py . output_dir/ --safe_serialization
|
||||
|
||||
import argparse
|
||||
import torch
|
||||
import glob
|
||||
import math
|
||||
import os
|
||||
import re
|
||||
import gc
|
||||
import json
|
||||
import numpy as np
|
||||
from tqdm import tqdm
|
||||
from collections import OrderedDict
|
||||
from dataclasses import dataclass
|
||||
|
||||
# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
|
||||
# DeepSpeed data structures it has to be available in the current python environment.
|
||||
from deepspeed.utils import logger
|
||||
from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
|
||||
FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
|
||||
FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
|
||||
|
||||
|
||||
@dataclass
|
||||
class zero_model_state:
|
||||
buffers: dict()
|
||||
param_shapes: dict()
|
||||
shared_params: list
|
||||
ds_version: int
|
||||
frozen_param_shapes: dict()
|
||||
frozen_param_fragments: dict()
|
||||
|
||||
|
||||
debug = 0
|
||||
|
||||
# load to cpu
|
||||
device = torch.device('cpu')
|
||||
|
||||
|
||||
def atoi(text):
|
||||
return int(text) if text.isdigit() else text
|
||||
|
||||
|
||||
def natural_keys(text):
|
||||
'''
|
||||
alist.sort(key=natural_keys) sorts in human order
|
||||
http://nedbatchelder.com/blog/200712/human_sorting.html
|
||||
(See Toothy's implementation in the comments)
|
||||
'''
|
||||
return [atoi(c) for c in re.split(r'(\d+)', text)]
|
||||
|
||||
|
||||
def get_model_state_file(checkpoint_dir, zero_stage):
|
||||
if not os.path.isdir(checkpoint_dir):
|
||||
raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
|
||||
|
||||
# there should be only one file
|
||||
if zero_stage <= 2:
|
||||
file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
|
||||
elif zero_stage == 3:
|
||||
file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
|
||||
|
||||
if not os.path.exists(file):
|
||||
raise FileNotFoundError(f"can't find model states file at '{file}'")
|
||||
|
||||
return file
|
||||
|
||||
|
||||
def get_checkpoint_files(checkpoint_dir, glob_pattern):
|
||||
# XXX: need to test that this simple glob rule works for multi-node setup too
|
||||
ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
|
||||
|
||||
if len(ckpt_files) == 0:
|
||||
raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
|
||||
|
||||
return ckpt_files
|
||||
|
||||
|
||||
def get_optim_files(checkpoint_dir):
|
||||
return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
|
||||
|
||||
|
||||
def get_model_state_files(checkpoint_dir):
|
||||
return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
|
||||
|
||||
|
||||
def parse_model_states(files):
|
||||
zero_model_states = []
|
||||
for file in files:
|
||||
state_dict = torch.load(file, map_location=device, weights_only=False)
|
||||
|
||||
if BUFFER_NAMES not in state_dict:
|
||||
raise ValueError(f"{file} is not a model state checkpoint")
|
||||
buffer_names = state_dict[BUFFER_NAMES]
|
||||
if debug:
|
||||
print("Found buffers:", buffer_names)
|
||||
|
||||
# recover just the buffers while restoring them to fp32 if they were saved in fp16
|
||||
buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
|
||||
param_shapes = state_dict[PARAM_SHAPES]
|
||||
|
||||
# collect parameters that are included in param_shapes
|
||||
param_names = []
|
||||
for s in param_shapes:
|
||||
for name in s.keys():
|
||||
param_names.append(name)
|
||||
|
||||
# update with frozen parameters
|
||||
frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
|
||||
if frozen_param_shapes is not None:
|
||||
if debug:
|
||||
print(f"Found frozen_param_shapes: {frozen_param_shapes}")
|
||||
param_names += list(frozen_param_shapes.keys())
|
||||
|
||||
# handle shared params
|
||||
shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
|
||||
|
||||
ds_version = state_dict.get(DS_VERSION, None)
|
||||
|
||||
frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
|
||||
|
||||
z_model_state = zero_model_state(buffers=buffers,
|
||||
param_shapes=param_shapes,
|
||||
shared_params=shared_params,
|
||||
ds_version=ds_version,
|
||||
frozen_param_shapes=frozen_param_shapes,
|
||||
frozen_param_fragments=frozen_param_fragments)
|
||||
zero_model_states.append(z_model_state)
|
||||
|
||||
return zero_model_states
|
||||
|
||||
|
||||
def parse_optim_states(files, ds_checkpoint_dir):
|
||||
total_files = len(files)
|
||||
state_dicts = []
|
||||
for f in tqdm(files, desc='Loading checkpoint shards'):
|
||||
state_dict = torch.load(f, map_location=device, mmap=True, weights_only=False)
|
||||
# immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
|
||||
# and also handle the case where it was already removed by another helper script
|
||||
state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
|
||||
state_dicts.append(state_dict)
|
||||
|
||||
if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
|
||||
raise ValueError(f"{files[0]} is not a zero checkpoint")
|
||||
zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
|
||||
world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
|
||||
|
||||
# For ZeRO-2 each param group can have different partition_count as data parallelism for expert
|
||||
# parameters can be different from data parallelism for non-expert parameters. So we can just
|
||||
# use the max of the partition_count to get the dp world_size.
|
||||
|
||||
if type(world_size) is list:
|
||||
world_size = max(world_size)
|
||||
|
||||
if world_size != total_files:
|
||||
raise ValueError(
|
||||
f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
|
||||
"Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
|
||||
)
|
||||
|
||||
# the groups are named differently in each stage
|
||||
if zero_stage <= 2:
|
||||
fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
|
||||
elif zero_stage == 3:
|
||||
fp32_groups_key = FP32_FLAT_GROUPS
|
||||
else:
|
||||
raise ValueError(f"unknown zero stage {zero_stage}")
|
||||
|
||||
fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
|
||||
return zero_stage, world_size, fp32_flat_groups
|
||||
|
||||
|
||||
def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
|
||||
"""
|
||||
Returns fp32 state_dict reconstructed from ds checkpoint
|
||||
|
||||
Args:
|
||||
- ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
|
||||
|
||||
"""
|
||||
print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
|
||||
|
||||
optim_files = get_optim_files(ds_checkpoint_dir)
|
||||
zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
|
||||
print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
|
||||
|
||||
model_files = get_model_state_files(ds_checkpoint_dir)
|
||||
|
||||
zero_model_states = parse_model_states(model_files)
|
||||
print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
|
||||
|
||||
if zero_stage <= 2:
|
||||
return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
||||
exclude_frozen_parameters)
|
||||
elif zero_stage == 3:
|
||||
return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
||||
exclude_frozen_parameters)
|
||||
|
||||
|
||||
def _zero2_merge_frozen_params(state_dict, zero_model_states):
|
||||
if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
|
||||
return
|
||||
|
||||
frozen_param_shapes = zero_model_states[0].frozen_param_shapes
|
||||
frozen_param_fragments = zero_model_states[0].frozen_param_fragments
|
||||
|
||||
if debug:
|
||||
num_elem = sum(s.numel() for s in frozen_param_shapes.values())
|
||||
print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
|
||||
|
||||
wanted_params = len(frozen_param_shapes)
|
||||
wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
|
||||
avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
|
||||
print(f'Frozen params: Have {avail_numel} numels to process.')
|
||||
print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
|
||||
|
||||
total_params = 0
|
||||
total_numel = 0
|
||||
for name, shape in frozen_param_shapes.items():
|
||||
total_params += 1
|
||||
unpartitioned_numel = shape.numel()
|
||||
total_numel += unpartitioned_numel
|
||||
|
||||
state_dict[name] = frozen_param_fragments[name]
|
||||
|
||||
if debug:
|
||||
print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
|
||||
|
||||
print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
|
||||
|
||||
|
||||
def _has_callable(obj, fn):
|
||||
attr = getattr(obj, fn, None)
|
||||
return callable(attr)
|
||||
|
||||
|
||||
def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
|
||||
param_shapes = zero_model_states[0].param_shapes
|
||||
|
||||
# Reconstruction protocol:
|
||||
#
|
||||
# XXX: document this
|
||||
|
||||
if debug:
|
||||
for i in range(world_size):
|
||||
for j in range(len(fp32_flat_groups[0])):
|
||||
print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
|
||||
|
||||
# XXX: memory usage doubles here (zero2)
|
||||
num_param_groups = len(fp32_flat_groups[0])
|
||||
merged_single_partition_of_fp32_groups = []
|
||||
for i in range(num_param_groups):
|
||||
merged_partitions = [sd[i] for sd in fp32_flat_groups]
|
||||
full_single_fp32_vector = torch.cat(merged_partitions, 0)
|
||||
merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
|
||||
avail_numel = sum(
|
||||
[full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
|
||||
|
||||
if debug:
|
||||
wanted_params = sum([len(shapes) for shapes in param_shapes])
|
||||
wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
|
||||
# not asserting if there is a mismatch due to possible padding
|
||||
print(f"Have {avail_numel} numels to process.")
|
||||
print(f"Need {wanted_numel} numels in {wanted_params} params.")
|
||||
|
||||
# params
|
||||
# XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
|
||||
# out-of-core computing solution
|
||||
total_numel = 0
|
||||
total_params = 0
|
||||
for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
|
||||
offset = 0
|
||||
avail_numel = full_single_fp32_vector.numel()
|
||||
for name, shape in shapes.items():
|
||||
|
||||
unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
|
||||
total_numel += unpartitioned_numel
|
||||
total_params += 1
|
||||
|
||||
if debug:
|
||||
print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
|
||||
state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
|
||||
offset += unpartitioned_numel
|
||||
|
||||
# Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
|
||||
# avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
|
||||
# paddings performed in the code it's almost impossible to predict the exact numbers w/o the
|
||||
# live optimizer object, so we are checking that the numbers are within the right range
|
||||
align_to = 2 * world_size
|
||||
|
||||
def zero2_align(x):
|
||||
return align_to * math.ceil(x / align_to)
|
||||
|
||||
if debug:
|
||||
print(f"original offset={offset}, avail_numel={avail_numel}")
|
||||
|
||||
offset = zero2_align(offset)
|
||||
avail_numel = zero2_align(avail_numel)
|
||||
|
||||
if debug:
|
||||
print(f"aligned offset={offset}, avail_numel={avail_numel}")
|
||||
|
||||
# Sanity check
|
||||
if offset != avail_numel:
|
||||
raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
|
||||
|
||||
print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
|
||||
|
||||
|
||||
def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
||||
exclude_frozen_parameters):
|
||||
state_dict = OrderedDict()
|
||||
|
||||
# buffers
|
||||
buffers = zero_model_states[0].buffers
|
||||
state_dict.update(buffers)
|
||||
if debug:
|
||||
print(f"added {len(buffers)} buffers")
|
||||
|
||||
if not exclude_frozen_parameters:
|
||||
_zero2_merge_frozen_params(state_dict, zero_model_states)
|
||||
|
||||
_zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
|
||||
|
||||
# recover shared parameters
|
||||
for pair in zero_model_states[0].shared_params:
|
||||
if pair[1] in state_dict:
|
||||
state_dict[pair[0]] = state_dict[pair[1]]
|
||||
|
||||
return state_dict
|
||||
|
||||
|
||||
def zero3_partitioned_param_info(unpartitioned_numel, world_size):
|
||||
remainder = unpartitioned_numel % world_size
|
||||
padding_numel = (world_size - remainder) if remainder else 0
|
||||
partitioned_numel = math.ceil(unpartitioned_numel / world_size)
|
||||
return partitioned_numel, padding_numel
|
||||
|
||||
|
||||
def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
|
||||
if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
|
||||
return
|
||||
|
||||
if debug:
|
||||
for i in range(world_size):
|
||||
num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
|
||||
print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
|
||||
|
||||
frozen_param_shapes = zero_model_states[0].frozen_param_shapes
|
||||
wanted_params = len(frozen_param_shapes)
|
||||
wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
|
||||
avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
|
||||
print(f'Frozen params: Have {avail_numel} numels to process.')
|
||||
print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
|
||||
|
||||
total_params = 0
|
||||
total_numel = 0
|
||||
for name, shape in zero_model_states[0].frozen_param_shapes.items():
|
||||
total_params += 1
|
||||
unpartitioned_numel = shape.numel()
|
||||
total_numel += unpartitioned_numel
|
||||
|
||||
param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
|
||||
state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
|
||||
|
||||
partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
|
||||
|
||||
if debug:
|
||||
print(
|
||||
f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
|
||||
)
|
||||
|
||||
print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
|
||||
|
||||
|
||||
class GatheredTensor:
|
||||
"""
|
||||
A pseudo tensor that collects partitioned weights.
|
||||
It is more memory efficient when there are multiple groups.
|
||||
"""
|
||||
|
||||
def __init__(self, flat_groups, flat_groups_offset, offset, partitioned_numel, shape):
|
||||
self.flat_groups = flat_groups
|
||||
self.flat_groups_offset = flat_groups_offset
|
||||
self.offset = offset
|
||||
self.partitioned_numel = partitioned_numel
|
||||
self.shape = shape
|
||||
self.dtype = self.flat_groups[0][0].dtype
|
||||
|
||||
def contiguous(self):
|
||||
"""
|
||||
Merge partitioned weights from flat_groups into a single tensor.
|
||||
"""
|
||||
end_idx = self.offset + self.partitioned_numel
|
||||
world_size = len(self.flat_groups)
|
||||
pad_flat_param_chunks = []
|
||||
|
||||
for rank_i in range(world_size):
|
||||
# for each rank, we need to collect weights from related group/groups
|
||||
flat_groups_at_rank_i = self.flat_groups[rank_i]
|
||||
start_group_id = None
|
||||
end_group_id = None
|
||||
for group_id in range(len(self.flat_groups_offset)):
|
||||
if self.flat_groups_offset[group_id] <= self.offset < self.flat_groups_offset[group_id + 1]:
|
||||
start_group_id = group_id
|
||||
if self.flat_groups_offset[group_id] < end_idx <= self.flat_groups_offset[group_id + 1]:
|
||||
end_group_id = group_id
|
||||
break
|
||||
# collect weights from related group/groups
|
||||
for group_id in range(start_group_id, end_group_id + 1):
|
||||
flat_tensor = flat_groups_at_rank_i[group_id]
|
||||
start_offset = self.offset - self.flat_groups_offset[group_id]
|
||||
end_offset = min(end_idx, self.flat_groups_offset[group_id + 1]) - self.flat_groups_offset[group_id]
|
||||
pad_flat_param_chunks.append(flat_tensor[start_offset:end_offset])
|
||||
|
||||
# collect weights from all ranks
|
||||
pad_flat_param = torch.cat(pad_flat_param_chunks, dim=0)
|
||||
param = pad_flat_param[:self.shape.numel()].view(self.shape).contiguous()
|
||||
return param
|
||||
|
||||
|
||||
def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
|
||||
param_shapes = zero_model_states[0].param_shapes
|
||||
avail_numel = sum([flat_group.numel() for flat_group in fp32_flat_groups[0]]) * world_size
|
||||
|
||||
# Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
|
||||
# param, re-consolidating each param, while dealing with padding if any
|
||||
|
||||
# merge list of dicts, preserving order
|
||||
param_shapes = {k: v for d in param_shapes for k, v in d.items()}
|
||||
|
||||
if debug:
|
||||
for i in range(world_size):
|
||||
print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
|
||||
|
||||
wanted_params = len(param_shapes)
|
||||
wanted_numel = sum(shape.numel() for shape in param_shapes.values())
|
||||
# not asserting if there is a mismatch due to possible padding
|
||||
avail_numel = fp32_flat_groups[0].numel() * world_size
|
||||
print(f"Trainable params: Have {avail_numel} numels to process.")
|
||||
print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
|
||||
|
||||
# params
|
||||
# XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
|
||||
# out-of-core computing solution
|
||||
offset = 0
|
||||
total_numel = 0
|
||||
total_params = 0
|
||||
flat_groups_offset = [0] + list(np.cumsum([flat_tensor.numel() for flat_tensor in fp32_flat_groups[0]]))
|
||||
for name, shape in tqdm(param_shapes.items(), desc='Gathering sharded weights'):
|
||||
unpartitioned_numel = shape.numel()
|
||||
total_numel += unpartitioned_numel
|
||||
total_params += 1
|
||||
partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
|
||||
|
||||
if debug:
|
||||
print(
|
||||
f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
|
||||
)
|
||||
|
||||
# memory efficient tensor
|
||||
tensor = GatheredTensor(fp32_flat_groups, flat_groups_offset, offset, partitioned_numel, shape)
|
||||
state_dict[name] = tensor
|
||||
offset += partitioned_numel
|
||||
|
||||
offset *= world_size
|
||||
|
||||
# Sanity check
|
||||
if offset != avail_numel:
|
||||
raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
|
||||
|
||||
print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
|
||||
|
||||
|
||||
def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
||||
exclude_frozen_parameters):
|
||||
state_dict = OrderedDict()
|
||||
|
||||
# buffers
|
||||
buffers = zero_model_states[0].buffers
|
||||
state_dict.update(buffers)
|
||||
if debug:
|
||||
print(f"added {len(buffers)} buffers")
|
||||
|
||||
if not exclude_frozen_parameters:
|
||||
_zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
|
||||
|
||||
_zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
|
||||
|
||||
# recover shared parameters
|
||||
for pair in zero_model_states[0].shared_params:
|
||||
if pair[1] in state_dict:
|
||||
state_dict[pair[0]] = state_dict[pair[1]]
|
||||
|
||||
return state_dict
|
||||
|
||||
|
||||
def to_torch_tensor(state_dict, return_empty_tensor=False):
|
||||
"""
|
||||
Convert state_dict of GatheredTensor to torch tensor
|
||||
"""
|
||||
torch_state_dict = {}
|
||||
converted_tensors = {}
|
||||
for name, tensor in state_dict.items():
|
||||
tensor_id = id(tensor)
|
||||
if tensor_id in converted_tensors: # shared tensors
|
||||
shared_tensor = torch_state_dict[converted_tensors[tensor_id]]
|
||||
torch_state_dict[name] = shared_tensor
|
||||
else:
|
||||
converted_tensors[tensor_id] = name
|
||||
if return_empty_tensor:
|
||||
torch_state_dict[name] = torch.empty(tensor.shape, dtype=tensor.dtype)
|
||||
else:
|
||||
torch_state_dict[name] = tensor.contiguous()
|
||||
return torch_state_dict
|
||||
|
||||
|
||||
def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
|
||||
tag=None,
|
||||
exclude_frozen_parameters=False,
|
||||
lazy_mode=False):
|
||||
"""
|
||||
Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
|
||||
``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
|
||||
via a model hub.
|
||||
|
||||
Args:
|
||||
- ``checkpoint_dir``: path to the desired checkpoint folder
|
||||
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
|
||||
- ``exclude_frozen_parameters``: exclude frozen parameters
|
||||
- ``lazy_mode``: get state_dict in lazy mode. It returns a dict of pesduo tensor instead of torch tensor, which is more memory efficient.
|
||||
Convert the pesduo tensor to torch tensor by ``.contiguous()``
|
||||
|
||||
Returns:
|
||||
- pytorch ``state_dict``
|
||||
|
||||
A typical usage might be ::
|
||||
|
||||
from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
|
||||
# do the training and checkpoint saving
|
||||
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
|
||||
model = model.cpu() # move to cpu
|
||||
model.load_state_dict(state_dict)
|
||||
# submit to model hub or save the model to share with others
|
||||
|
||||
In this example the ``model`` will no longer be usable in the deepspeed context of the same
|
||||
application. i.e. you will need to re-initialize the deepspeed engine, since
|
||||
``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
|
||||
|
||||
If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
|
||||
|
||||
Note: the above usage may not work if your application doesn't have sufficient free CPU memory.
|
||||
You may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
|
||||
the checkpoint. Or you can load state_dict in lazy mode ::
|
||||
|
||||
from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
|
||||
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, lazy_mode=True) # not on cpu
|
||||
for name, lazy_tensor in state_dict.item():
|
||||
tensor = lazy_tensor.contiguous() # to cpu
|
||||
print(name, tensor)
|
||||
# del tensor to release memory if it no longer in use
|
||||
"""
|
||||
if tag is None:
|
||||
latest_path = os.path.join(checkpoint_dir, 'latest')
|
||||
if os.path.isfile(latest_path):
|
||||
with open(latest_path, 'r') as fd:
|
||||
tag = fd.read().strip()
|
||||
else:
|
||||
raise ValueError(f"Unable to find 'latest' file at {latest_path}")
|
||||
|
||||
ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
|
||||
|
||||
if not os.path.isdir(ds_checkpoint_dir):
|
||||
raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
|
||||
|
||||
state_dict = _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
|
||||
if lazy_mode:
|
||||
return state_dict
|
||||
else:
|
||||
return to_torch_tensor(state_dict)
|
||||
|
||||
|
||||
def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir,
|
||||
output_dir,
|
||||
max_shard_size="5GB",
|
||||
safe_serialization=False,
|
||||
tag=None,
|
||||
exclude_frozen_parameters=False):
|
||||
"""
|
||||
Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
|
||||
loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
|
||||
|
||||
Args:
|
||||
- ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
|
||||
- ``output_dir``: directory to the pytorch fp32 state_dict output files
|
||||
- ``max_shard_size``: the maximum size for a checkpoint before being sharded, default value is 5GB
|
||||
- ``safe_serialization``: whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).
|
||||
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
|
||||
- ``exclude_frozen_parameters``: exclude frozen parameters
|
||||
"""
|
||||
|
||||
# Dependency pre-check
|
||||
if safe_serialization:
|
||||
try:
|
||||
from safetensors.torch import save_file
|
||||
except ImportError:
|
||||
print('If you want to use `safe_serialization`, please `pip install safetensors`')
|
||||
raise
|
||||
if max_shard_size is not None:
|
||||
try:
|
||||
from huggingface_hub import split_torch_state_dict_into_shards
|
||||
except ImportError:
|
||||
print('If you want to use `max_shard_size`, please `pip install huggingface_hub`')
|
||||
raise
|
||||
|
||||
# Convert zero checkpoint to state_dict
|
||||
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
|
||||
tag,
|
||||
exclude_frozen_parameters,
|
||||
lazy_mode=True)
|
||||
|
||||
# Shard the model if it is too big.
|
||||
weights_name = "model.safetensors" if safe_serialization else "pytorch_model.bin"
|
||||
if max_shard_size is not None:
|
||||
filename_pattern = weights_name.replace(".bin", "{suffix}.bin").replace(".safetensors", "{suffix}.safetensors")
|
||||
# an memory-efficient approach for sharding
|
||||
empty_state_dict = to_torch_tensor(state_dict, return_empty_tensor=True)
|
||||
state_dict_split = split_torch_state_dict_into_shards(empty_state_dict,
|
||||
filename_pattern=filename_pattern,
|
||||
max_shard_size=max_shard_size)
|
||||
else:
|
||||
from collections import namedtuple
|
||||
StateDictSplit = namedtuple("StateDictSplit", ["is_sharded", "filename_to_tensors"])
|
||||
state_dict_split = StateDictSplit(is_sharded=False,
|
||||
filename_to_tensors={weights_name: list(state_dict.keys())})
|
||||
|
||||
# Save the model by shard
|
||||
os.makedirs(output_dir, exist_ok=True)
|
||||
filename_to_tensors = state_dict_split.filename_to_tensors.items()
|
||||
for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"):
|
||||
shard_state_dict = {tensor_name: state_dict[tensor_name] for tensor_name in tensors}
|
||||
shard_state_dict = to_torch_tensor(shard_state_dict)
|
||||
output_path = os.path.join(output_dir, shard_file)
|
||||
if safe_serialization:
|
||||
save_file(shard_state_dict, output_path, metadata={"format": "pt"})
|
||||
else:
|
||||
torch.save(shard_state_dict, output_path)
|
||||
# release the memory of current shard
|
||||
for tensor_name in list(shard_state_dict.keys()):
|
||||
del state_dict[tensor_name]
|
||||
del shard_state_dict[tensor_name]
|
||||
del shard_state_dict
|
||||
gc.collect()
|
||||
|
||||
# Save index if sharded
|
||||
if state_dict_split.is_sharded:
|
||||
index = {
|
||||
"metadata": state_dict_split.metadata,
|
||||
"weight_map": state_dict_split.tensor_to_filename,
|
||||
}
|
||||
save_index_file = "model.safetensors.index.json" if safe_serialization else "pytorch_model.bin.index.json"
|
||||
save_index_file = os.path.join(output_dir, save_index_file)
|
||||
with open(save_index_file, "w", encoding="utf-8") as f:
|
||||
content = json.dumps(index, indent=2, sort_keys=True) + "\n"
|
||||
f.write(content)
|
||||
|
||||
|
||||
def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
|
||||
"""
|
||||
1. Put the provided model to cpu
|
||||
2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
|
||||
3. Load it into the provided model
|
||||
|
||||
Args:
|
||||
- ``model``: the model object to update
|
||||
- ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
|
||||
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
|
||||
|
||||
Returns:
|
||||
- ``model`: modified model
|
||||
|
||||
Make sure you have plenty of CPU memory available before you call this function. If you don't
|
||||
have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
|
||||
conveniently placed for you in the checkpoint folder.
|
||||
|
||||
A typical usage might be ::
|
||||
|
||||
from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
|
||||
model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
|
||||
# submit to model hub or save the model to share with others
|
||||
|
||||
Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
|
||||
of the same application. i.e. you will need to re-initialize the deepspeed engine, since
|
||||
``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
|
||||
|
||||
"""
|
||||
logger.info(f"Extracting fp32 weights")
|
||||
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
|
||||
|
||||
logger.info(f"Overwriting model with fp32 weights")
|
||||
model = model.cpu()
|
||||
model.load_state_dict(state_dict, strict=False)
|
||||
|
||||
return model
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
parser = argparse.ArgumentParser()
|
||||
parser.add_argument("checkpoint_dir",
|
||||
type=str,
|
||||
help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
|
||||
parser.add_argument("output_dir",
|
||||
type=str,
|
||||
help="directory to the pytorch fp32 state_dict output files"
|
||||
"(e.g. path/checkpoint-12-output/)")
|
||||
parser.add_argument(
|
||||
"--max_shard_size",
|
||||
type=str,
|
||||
default="5GB",
|
||||
help="The maximum size for a checkpoint before being sharded. Checkpoints shard will then be each of size"
|
||||
"lower than this size. If expressed as a string, needs to be digits followed by a unit (like `5MB`"
|
||||
"We default it to 5GB in order for models to be able to run easily on free-tier google colab instances"
|
||||
"without CPU OOM issues.")
|
||||
parser.add_argument(
|
||||
"--safe_serialization",
|
||||
default=False,
|
||||
action='store_true',
|
||||
help="Whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).")
|
||||
parser.add_argument("-t",
|
||||
"--tag",
|
||||
type=str,
|
||||
default=None,
|
||||
help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
|
||||
parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
|
||||
parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
|
||||
args = parser.parse_args()
|
||||
|
||||
debug = args.debug
|
||||
|
||||
convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
|
||||
args.output_dir,
|
||||
max_shard_size=args.max_shard_size,
|
||||
safe_serialization=args.safe_serialization,
|
||||
tag=args.tag,
|
||||
exclude_frozen_parameters=args.exclude_frozen_parameters)
|
||||
@@ -0,0 +1,202 @@
|
||||
---
|
||||
base_model: meta-llama/Llama-3.1-8B-Instruct
|
||||
library_name: peft
|
||||
---
|
||||
|
||||
# Model Card for Model ID
|
||||
|
||||
<!-- Provide a quick summary of what the model is/does. -->
|
||||
|
||||
|
||||
|
||||
## Model Details
|
||||
|
||||
### Model Description
|
||||
|
||||
<!-- Provide a longer summary of what this model is. -->
|
||||
|
||||
|
||||
|
||||
- **Developed by:** [More Information Needed]
|
||||
- **Funded by [optional]:** [More Information Needed]
|
||||
- **Shared by [optional]:** [More Information Needed]
|
||||
- **Model type:** [More Information Needed]
|
||||
- **Language(s) (NLP):** [More Information Needed]
|
||||
- **License:** [More Information Needed]
|
||||
- **Finetuned from model [optional]:** [More Information Needed]
|
||||
|
||||
### Model Sources [optional]
|
||||
|
||||
<!-- Provide the basic links for the model. -->
|
||||
|
||||
- **Repository:** [More Information Needed]
|
||||
- **Paper [optional]:** [More Information Needed]
|
||||
- **Demo [optional]:** [More Information Needed]
|
||||
|
||||
## Uses
|
||||
|
||||
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
||||
|
||||
### Direct Use
|
||||
|
||||
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Downstream Use [optional]
|
||||
|
||||
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Out-of-Scope Use
|
||||
|
||||
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Bias, Risks, and Limitations
|
||||
|
||||
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Recommendations
|
||||
|
||||
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
||||
|
||||
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
||||
|
||||
## How to Get Started with the Model
|
||||
|
||||
Use the code below to get started with the model.
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Training Details
|
||||
|
||||
### Training Data
|
||||
|
||||
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Training Procedure
|
||||
|
||||
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
||||
|
||||
#### Preprocessing [optional]
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
|
||||
#### Training Hyperparameters
|
||||
|
||||
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
||||
|
||||
#### Speeds, Sizes, Times [optional]
|
||||
|
||||
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Evaluation
|
||||
|
||||
<!-- This section describes the evaluation protocols and provides the results. -->
|
||||
|
||||
### Testing Data, Factors & Metrics
|
||||
|
||||
#### Testing Data
|
||||
|
||||
<!-- This should link to a Dataset Card if possible. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Factors
|
||||
|
||||
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Metrics
|
||||
|
||||
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Results
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Summary
|
||||
|
||||
|
||||
|
||||
## Model Examination [optional]
|
||||
|
||||
<!-- Relevant interpretability work for the model goes here -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Environmental Impact
|
||||
|
||||
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
||||
|
||||
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
||||
|
||||
- **Hardware Type:** [More Information Needed]
|
||||
- **Hours used:** [More Information Needed]
|
||||
- **Cloud Provider:** [More Information Needed]
|
||||
- **Compute Region:** [More Information Needed]
|
||||
- **Carbon Emitted:** [More Information Needed]
|
||||
|
||||
## Technical Specifications [optional]
|
||||
|
||||
### Model Architecture and Objective
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Compute Infrastructure
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Hardware
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Software
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Citation [optional]
|
||||
|
||||
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
||||
|
||||
**BibTeX:**
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
**APA:**
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Glossary [optional]
|
||||
|
||||
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## More Information [optional]
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Model Card Authors [optional]
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Model Card Contact
|
||||
|
||||
[More Information Needed]
|
||||
### Framework versions
|
||||
|
||||
- PEFT 0.15.2
|
||||
@@ -0,0 +1,41 @@
|
||||
{
|
||||
"alpha_pattern": {},
|
||||
"auto_mapping": null,
|
||||
"base_model_name_or_path": "meta-llama/Llama-3.1-8B-Instruct",
|
||||
"bias": "none",
|
||||
"corda_config": null,
|
||||
"eva_config": null,
|
||||
"exclude_modules": null,
|
||||
"fan_in_fan_out": false,
|
||||
"inference_mode": true,
|
||||
"init_lora_weights": true,
|
||||
"layer_replication": null,
|
||||
"layers_pattern": null,
|
||||
"layers_to_transform": null,
|
||||
"loftq_config": {},
|
||||
"lora_alpha": 256,
|
||||
"lora_bias": false,
|
||||
"lora_dropout": 0.0,
|
||||
"megatron_config": null,
|
||||
"megatron_core": "megatron.core",
|
||||
"modules_to_save": null,
|
||||
"peft_type": "LORA",
|
||||
"r": 128,
|
||||
"rank_pattern": {},
|
||||
"revision": null,
|
||||
"target_modules": [
|
||||
"o_proj",
|
||||
"up_proj",
|
||||
"k_proj",
|
||||
"down_proj",
|
||||
"lm_head",
|
||||
"gate_proj",
|
||||
"q_proj",
|
||||
"v_proj",
|
||||
"embed_tokens"
|
||||
],
|
||||
"task_type": "CAUSAL_LM",
|
||||
"trainable_token_indices": null,
|
||||
"use_dora": false,
|
||||
"use_rslora": false
|
||||
}
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:5cd71b0544f42841a73d8ac09db21a5ab343ee609e7b5bb13c5b7fe3b02d38a1
|
||||
size 2840262376
|
||||
@@ -0,0 +1 @@
|
||||
global_step1400
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:47db7c3e7836d368461f6a58bd240eb0ffff06cfacc0b3db2ed4c22d54c93b6a
|
||||
size 14960
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:1f08f865d0982bb469684dad7d9652159952d779de0db8c44e21279f3cebc918
|
||||
size 14960
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:aefe088f5d67932fbd78972b7f2e2e186c623473d22d00dca0231b00cdebb09f
|
||||
size 14960
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:5c534992ef997c8a2246052e7e016fc5dd8a99216a37c5874d2107990c9f3738
|
||||
size 14960
|
||||
@@ -0,0 +1,16 @@
|
||||
{
|
||||
"bos_token": {
|
||||
"content": "<|begin_of_text|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "<|eot_id|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
BIN
lora-embedding-128-llama3.1-8b-malaysian-8k/checkpoint-1400/tokenizer.json
(Stored with Git LFS)
Normal file
BIN
lora-embedding-128-llama3.1-8b-malaysian-8k/checkpoint-1400/tokenizer.json
(Stored with Git LFS)
Normal file
Binary file not shown.
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:922c4272bf2cd66460df74f5c309b6b97e5e3f4c0ba57215852b5b38fbe927c2
|
||||
size 7800
|
||||
@@ -0,0 +1,760 @@
|
||||
#!/usr/bin/env python
|
||||
|
||||
# Copyright (c) Microsoft Corporation.
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
|
||||
# DeepSpeed Team
|
||||
|
||||
# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
|
||||
# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
|
||||
# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
|
||||
# application.
|
||||
#
|
||||
# example:
|
||||
# python zero_to_fp32.py . output_dir/
|
||||
# or
|
||||
# python zero_to_fp32.py . output_dir/ --safe_serialization
|
||||
|
||||
import argparse
|
||||
import torch
|
||||
import glob
|
||||
import math
|
||||
import os
|
||||
import re
|
||||
import gc
|
||||
import json
|
||||
import numpy as np
|
||||
from tqdm import tqdm
|
||||
from collections import OrderedDict
|
||||
from dataclasses import dataclass
|
||||
|
||||
# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
|
||||
# DeepSpeed data structures it has to be available in the current python environment.
|
||||
from deepspeed.utils import logger
|
||||
from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
|
||||
FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
|
||||
FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
|
||||
|
||||
|
||||
@dataclass
|
||||
class zero_model_state:
|
||||
buffers: dict()
|
||||
param_shapes: dict()
|
||||
shared_params: list
|
||||
ds_version: int
|
||||
frozen_param_shapes: dict()
|
||||
frozen_param_fragments: dict()
|
||||
|
||||
|
||||
debug = 0
|
||||
|
||||
# load to cpu
|
||||
device = torch.device('cpu')
|
||||
|
||||
|
||||
def atoi(text):
|
||||
return int(text) if text.isdigit() else text
|
||||
|
||||
|
||||
def natural_keys(text):
|
||||
'''
|
||||
alist.sort(key=natural_keys) sorts in human order
|
||||
http://nedbatchelder.com/blog/200712/human_sorting.html
|
||||
(See Toothy's implementation in the comments)
|
||||
'''
|
||||
return [atoi(c) for c in re.split(r'(\d+)', text)]
|
||||
|
||||
|
||||
def get_model_state_file(checkpoint_dir, zero_stage):
|
||||
if not os.path.isdir(checkpoint_dir):
|
||||
raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
|
||||
|
||||
# there should be only one file
|
||||
if zero_stage <= 2:
|
||||
file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
|
||||
elif zero_stage == 3:
|
||||
file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
|
||||
|
||||
if not os.path.exists(file):
|
||||
raise FileNotFoundError(f"can't find model states file at '{file}'")
|
||||
|
||||
return file
|
||||
|
||||
|
||||
def get_checkpoint_files(checkpoint_dir, glob_pattern):
|
||||
# XXX: need to test that this simple glob rule works for multi-node setup too
|
||||
ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
|
||||
|
||||
if len(ckpt_files) == 0:
|
||||
raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
|
||||
|
||||
return ckpt_files
|
||||
|
||||
|
||||
def get_optim_files(checkpoint_dir):
|
||||
return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
|
||||
|
||||
|
||||
def get_model_state_files(checkpoint_dir):
|
||||
return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
|
||||
|
||||
|
||||
def parse_model_states(files):
|
||||
zero_model_states = []
|
||||
for file in files:
|
||||
state_dict = torch.load(file, map_location=device, weights_only=False)
|
||||
|
||||
if BUFFER_NAMES not in state_dict:
|
||||
raise ValueError(f"{file} is not a model state checkpoint")
|
||||
buffer_names = state_dict[BUFFER_NAMES]
|
||||
if debug:
|
||||
print("Found buffers:", buffer_names)
|
||||
|
||||
# recover just the buffers while restoring them to fp32 if they were saved in fp16
|
||||
buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
|
||||
param_shapes = state_dict[PARAM_SHAPES]
|
||||
|
||||
# collect parameters that are included in param_shapes
|
||||
param_names = []
|
||||
for s in param_shapes:
|
||||
for name in s.keys():
|
||||
param_names.append(name)
|
||||
|
||||
# update with frozen parameters
|
||||
frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
|
||||
if frozen_param_shapes is not None:
|
||||
if debug:
|
||||
print(f"Found frozen_param_shapes: {frozen_param_shapes}")
|
||||
param_names += list(frozen_param_shapes.keys())
|
||||
|
||||
# handle shared params
|
||||
shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
|
||||
|
||||
ds_version = state_dict.get(DS_VERSION, None)
|
||||
|
||||
frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
|
||||
|
||||
z_model_state = zero_model_state(buffers=buffers,
|
||||
param_shapes=param_shapes,
|
||||
shared_params=shared_params,
|
||||
ds_version=ds_version,
|
||||
frozen_param_shapes=frozen_param_shapes,
|
||||
frozen_param_fragments=frozen_param_fragments)
|
||||
zero_model_states.append(z_model_state)
|
||||
|
||||
return zero_model_states
|
||||
|
||||
|
||||
def parse_optim_states(files, ds_checkpoint_dir):
|
||||
total_files = len(files)
|
||||
state_dicts = []
|
||||
for f in tqdm(files, desc='Loading checkpoint shards'):
|
||||
state_dict = torch.load(f, map_location=device, mmap=True, weights_only=False)
|
||||
# immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
|
||||
# and also handle the case where it was already removed by another helper script
|
||||
state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
|
||||
state_dicts.append(state_dict)
|
||||
|
||||
if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
|
||||
raise ValueError(f"{files[0]} is not a zero checkpoint")
|
||||
zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
|
||||
world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
|
||||
|
||||
# For ZeRO-2 each param group can have different partition_count as data parallelism for expert
|
||||
# parameters can be different from data parallelism for non-expert parameters. So we can just
|
||||
# use the max of the partition_count to get the dp world_size.
|
||||
|
||||
if type(world_size) is list:
|
||||
world_size = max(world_size)
|
||||
|
||||
if world_size != total_files:
|
||||
raise ValueError(
|
||||
f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
|
||||
"Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
|
||||
)
|
||||
|
||||
# the groups are named differently in each stage
|
||||
if zero_stage <= 2:
|
||||
fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
|
||||
elif zero_stage == 3:
|
||||
fp32_groups_key = FP32_FLAT_GROUPS
|
||||
else:
|
||||
raise ValueError(f"unknown zero stage {zero_stage}")
|
||||
|
||||
fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
|
||||
return zero_stage, world_size, fp32_flat_groups
|
||||
|
||||
|
||||
def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
|
||||
"""
|
||||
Returns fp32 state_dict reconstructed from ds checkpoint
|
||||
|
||||
Args:
|
||||
- ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
|
||||
|
||||
"""
|
||||
print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
|
||||
|
||||
optim_files = get_optim_files(ds_checkpoint_dir)
|
||||
zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
|
||||
print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
|
||||
|
||||
model_files = get_model_state_files(ds_checkpoint_dir)
|
||||
|
||||
zero_model_states = parse_model_states(model_files)
|
||||
print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
|
||||
|
||||
if zero_stage <= 2:
|
||||
return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
||||
exclude_frozen_parameters)
|
||||
elif zero_stage == 3:
|
||||
return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
||||
exclude_frozen_parameters)
|
||||
|
||||
|
||||
def _zero2_merge_frozen_params(state_dict, zero_model_states):
|
||||
if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
|
||||
return
|
||||
|
||||
frozen_param_shapes = zero_model_states[0].frozen_param_shapes
|
||||
frozen_param_fragments = zero_model_states[0].frozen_param_fragments
|
||||
|
||||
if debug:
|
||||
num_elem = sum(s.numel() for s in frozen_param_shapes.values())
|
||||
print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
|
||||
|
||||
wanted_params = len(frozen_param_shapes)
|
||||
wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
|
||||
avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
|
||||
print(f'Frozen params: Have {avail_numel} numels to process.')
|
||||
print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
|
||||
|
||||
total_params = 0
|
||||
total_numel = 0
|
||||
for name, shape in frozen_param_shapes.items():
|
||||
total_params += 1
|
||||
unpartitioned_numel = shape.numel()
|
||||
total_numel += unpartitioned_numel
|
||||
|
||||
state_dict[name] = frozen_param_fragments[name]
|
||||
|
||||
if debug:
|
||||
print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
|
||||
|
||||
print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
|
||||
|
||||
|
||||
def _has_callable(obj, fn):
|
||||
attr = getattr(obj, fn, None)
|
||||
return callable(attr)
|
||||
|
||||
|
||||
def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
|
||||
param_shapes = zero_model_states[0].param_shapes
|
||||
|
||||
# Reconstruction protocol:
|
||||
#
|
||||
# XXX: document this
|
||||
|
||||
if debug:
|
||||
for i in range(world_size):
|
||||
for j in range(len(fp32_flat_groups[0])):
|
||||
print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
|
||||
|
||||
# XXX: memory usage doubles here (zero2)
|
||||
num_param_groups = len(fp32_flat_groups[0])
|
||||
merged_single_partition_of_fp32_groups = []
|
||||
for i in range(num_param_groups):
|
||||
merged_partitions = [sd[i] for sd in fp32_flat_groups]
|
||||
full_single_fp32_vector = torch.cat(merged_partitions, 0)
|
||||
merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
|
||||
avail_numel = sum(
|
||||
[full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
|
||||
|
||||
if debug:
|
||||
wanted_params = sum([len(shapes) for shapes in param_shapes])
|
||||
wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
|
||||
# not asserting if there is a mismatch due to possible padding
|
||||
print(f"Have {avail_numel} numels to process.")
|
||||
print(f"Need {wanted_numel} numels in {wanted_params} params.")
|
||||
|
||||
# params
|
||||
# XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
|
||||
# out-of-core computing solution
|
||||
total_numel = 0
|
||||
total_params = 0
|
||||
for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
|
||||
offset = 0
|
||||
avail_numel = full_single_fp32_vector.numel()
|
||||
for name, shape in shapes.items():
|
||||
|
||||
unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
|
||||
total_numel += unpartitioned_numel
|
||||
total_params += 1
|
||||
|
||||
if debug:
|
||||
print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
|
||||
state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
|
||||
offset += unpartitioned_numel
|
||||
|
||||
# Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
|
||||
# avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
|
||||
# paddings performed in the code it's almost impossible to predict the exact numbers w/o the
|
||||
# live optimizer object, so we are checking that the numbers are within the right range
|
||||
align_to = 2 * world_size
|
||||
|
||||
def zero2_align(x):
|
||||
return align_to * math.ceil(x / align_to)
|
||||
|
||||
if debug:
|
||||
print(f"original offset={offset}, avail_numel={avail_numel}")
|
||||
|
||||
offset = zero2_align(offset)
|
||||
avail_numel = zero2_align(avail_numel)
|
||||
|
||||
if debug:
|
||||
print(f"aligned offset={offset}, avail_numel={avail_numel}")
|
||||
|
||||
# Sanity check
|
||||
if offset != avail_numel:
|
||||
raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
|
||||
|
||||
print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
|
||||
|
||||
|
||||
def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
||||
exclude_frozen_parameters):
|
||||
state_dict = OrderedDict()
|
||||
|
||||
# buffers
|
||||
buffers = zero_model_states[0].buffers
|
||||
state_dict.update(buffers)
|
||||
if debug:
|
||||
print(f"added {len(buffers)} buffers")
|
||||
|
||||
if not exclude_frozen_parameters:
|
||||
_zero2_merge_frozen_params(state_dict, zero_model_states)
|
||||
|
||||
_zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
|
||||
|
||||
# recover shared parameters
|
||||
for pair in zero_model_states[0].shared_params:
|
||||
if pair[1] in state_dict:
|
||||
state_dict[pair[0]] = state_dict[pair[1]]
|
||||
|
||||
return state_dict
|
||||
|
||||
|
||||
def zero3_partitioned_param_info(unpartitioned_numel, world_size):
|
||||
remainder = unpartitioned_numel % world_size
|
||||
padding_numel = (world_size - remainder) if remainder else 0
|
||||
partitioned_numel = math.ceil(unpartitioned_numel / world_size)
|
||||
return partitioned_numel, padding_numel
|
||||
|
||||
|
||||
def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
|
||||
if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
|
||||
return
|
||||
|
||||
if debug:
|
||||
for i in range(world_size):
|
||||
num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
|
||||
print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
|
||||
|
||||
frozen_param_shapes = zero_model_states[0].frozen_param_shapes
|
||||
wanted_params = len(frozen_param_shapes)
|
||||
wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
|
||||
avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
|
||||
print(f'Frozen params: Have {avail_numel} numels to process.')
|
||||
print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
|
||||
|
||||
total_params = 0
|
||||
total_numel = 0
|
||||
for name, shape in zero_model_states[0].frozen_param_shapes.items():
|
||||
total_params += 1
|
||||
unpartitioned_numel = shape.numel()
|
||||
total_numel += unpartitioned_numel
|
||||
|
||||
param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
|
||||
state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
|
||||
|
||||
partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
|
||||
|
||||
if debug:
|
||||
print(
|
||||
f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
|
||||
)
|
||||
|
||||
print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
|
||||
|
||||
|
||||
class GatheredTensor:
|
||||
"""
|
||||
A pseudo tensor that collects partitioned weights.
|
||||
It is more memory efficient when there are multiple groups.
|
||||
"""
|
||||
|
||||
def __init__(self, flat_groups, flat_groups_offset, offset, partitioned_numel, shape):
|
||||
self.flat_groups = flat_groups
|
||||
self.flat_groups_offset = flat_groups_offset
|
||||
self.offset = offset
|
||||
self.partitioned_numel = partitioned_numel
|
||||
self.shape = shape
|
||||
self.dtype = self.flat_groups[0][0].dtype
|
||||
|
||||
def contiguous(self):
|
||||
"""
|
||||
Merge partitioned weights from flat_groups into a single tensor.
|
||||
"""
|
||||
end_idx = self.offset + self.partitioned_numel
|
||||
world_size = len(self.flat_groups)
|
||||
pad_flat_param_chunks = []
|
||||
|
||||
for rank_i in range(world_size):
|
||||
# for each rank, we need to collect weights from related group/groups
|
||||
flat_groups_at_rank_i = self.flat_groups[rank_i]
|
||||
start_group_id = None
|
||||
end_group_id = None
|
||||
for group_id in range(len(self.flat_groups_offset)):
|
||||
if self.flat_groups_offset[group_id] <= self.offset < self.flat_groups_offset[group_id + 1]:
|
||||
start_group_id = group_id
|
||||
if self.flat_groups_offset[group_id] < end_idx <= self.flat_groups_offset[group_id + 1]:
|
||||
end_group_id = group_id
|
||||
break
|
||||
# collect weights from related group/groups
|
||||
for group_id in range(start_group_id, end_group_id + 1):
|
||||
flat_tensor = flat_groups_at_rank_i[group_id]
|
||||
start_offset = self.offset - self.flat_groups_offset[group_id]
|
||||
end_offset = min(end_idx, self.flat_groups_offset[group_id + 1]) - self.flat_groups_offset[group_id]
|
||||
pad_flat_param_chunks.append(flat_tensor[start_offset:end_offset])
|
||||
|
||||
# collect weights from all ranks
|
||||
pad_flat_param = torch.cat(pad_flat_param_chunks, dim=0)
|
||||
param = pad_flat_param[:self.shape.numel()].view(self.shape).contiguous()
|
||||
return param
|
||||
|
||||
|
||||
def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
|
||||
param_shapes = zero_model_states[0].param_shapes
|
||||
avail_numel = sum([flat_group.numel() for flat_group in fp32_flat_groups[0]]) * world_size
|
||||
|
||||
# Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
|
||||
# param, re-consolidating each param, while dealing with padding if any
|
||||
|
||||
# merge list of dicts, preserving order
|
||||
param_shapes = {k: v for d in param_shapes for k, v in d.items()}
|
||||
|
||||
if debug:
|
||||
for i in range(world_size):
|
||||
print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
|
||||
|
||||
wanted_params = len(param_shapes)
|
||||
wanted_numel = sum(shape.numel() for shape in param_shapes.values())
|
||||
# not asserting if there is a mismatch due to possible padding
|
||||
avail_numel = fp32_flat_groups[0].numel() * world_size
|
||||
print(f"Trainable params: Have {avail_numel} numels to process.")
|
||||
print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
|
||||
|
||||
# params
|
||||
# XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
|
||||
# out-of-core computing solution
|
||||
offset = 0
|
||||
total_numel = 0
|
||||
total_params = 0
|
||||
flat_groups_offset = [0] + list(np.cumsum([flat_tensor.numel() for flat_tensor in fp32_flat_groups[0]]))
|
||||
for name, shape in tqdm(param_shapes.items(), desc='Gathering sharded weights'):
|
||||
unpartitioned_numel = shape.numel()
|
||||
total_numel += unpartitioned_numel
|
||||
total_params += 1
|
||||
partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
|
||||
|
||||
if debug:
|
||||
print(
|
||||
f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
|
||||
)
|
||||
|
||||
# memory efficient tensor
|
||||
tensor = GatheredTensor(fp32_flat_groups, flat_groups_offset, offset, partitioned_numel, shape)
|
||||
state_dict[name] = tensor
|
||||
offset += partitioned_numel
|
||||
|
||||
offset *= world_size
|
||||
|
||||
# Sanity check
|
||||
if offset != avail_numel:
|
||||
raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
|
||||
|
||||
print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
|
||||
|
||||
|
||||
def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
||||
exclude_frozen_parameters):
|
||||
state_dict = OrderedDict()
|
||||
|
||||
# buffers
|
||||
buffers = zero_model_states[0].buffers
|
||||
state_dict.update(buffers)
|
||||
if debug:
|
||||
print(f"added {len(buffers)} buffers")
|
||||
|
||||
if not exclude_frozen_parameters:
|
||||
_zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
|
||||
|
||||
_zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
|
||||
|
||||
# recover shared parameters
|
||||
for pair in zero_model_states[0].shared_params:
|
||||
if pair[1] in state_dict:
|
||||
state_dict[pair[0]] = state_dict[pair[1]]
|
||||
|
||||
return state_dict
|
||||
|
||||
|
||||
def to_torch_tensor(state_dict, return_empty_tensor=False):
|
||||
"""
|
||||
Convert state_dict of GatheredTensor to torch tensor
|
||||
"""
|
||||
torch_state_dict = {}
|
||||
converted_tensors = {}
|
||||
for name, tensor in state_dict.items():
|
||||
tensor_id = id(tensor)
|
||||
if tensor_id in converted_tensors: # shared tensors
|
||||
shared_tensor = torch_state_dict[converted_tensors[tensor_id]]
|
||||
torch_state_dict[name] = shared_tensor
|
||||
else:
|
||||
converted_tensors[tensor_id] = name
|
||||
if return_empty_tensor:
|
||||
torch_state_dict[name] = torch.empty(tensor.shape, dtype=tensor.dtype)
|
||||
else:
|
||||
torch_state_dict[name] = tensor.contiguous()
|
||||
return torch_state_dict
|
||||
|
||||
|
||||
def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
|
||||
tag=None,
|
||||
exclude_frozen_parameters=False,
|
||||
lazy_mode=False):
|
||||
"""
|
||||
Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
|
||||
``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
|
||||
via a model hub.
|
||||
|
||||
Args:
|
||||
- ``checkpoint_dir``: path to the desired checkpoint folder
|
||||
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
|
||||
- ``exclude_frozen_parameters``: exclude frozen parameters
|
||||
- ``lazy_mode``: get state_dict in lazy mode. It returns a dict of pesduo tensor instead of torch tensor, which is more memory efficient.
|
||||
Convert the pesduo tensor to torch tensor by ``.contiguous()``
|
||||
|
||||
Returns:
|
||||
- pytorch ``state_dict``
|
||||
|
||||
A typical usage might be ::
|
||||
|
||||
from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
|
||||
# do the training and checkpoint saving
|
||||
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
|
||||
model = model.cpu() # move to cpu
|
||||
model.load_state_dict(state_dict)
|
||||
# submit to model hub or save the model to share with others
|
||||
|
||||
In this example the ``model`` will no longer be usable in the deepspeed context of the same
|
||||
application. i.e. you will need to re-initialize the deepspeed engine, since
|
||||
``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
|
||||
|
||||
If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
|
||||
|
||||
Note: the above usage may not work if your application doesn't have sufficient free CPU memory.
|
||||
You may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
|
||||
the checkpoint. Or you can load state_dict in lazy mode ::
|
||||
|
||||
from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
|
||||
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, lazy_mode=True) # not on cpu
|
||||
for name, lazy_tensor in state_dict.item():
|
||||
tensor = lazy_tensor.contiguous() # to cpu
|
||||
print(name, tensor)
|
||||
# del tensor to release memory if it no longer in use
|
||||
"""
|
||||
if tag is None:
|
||||
latest_path = os.path.join(checkpoint_dir, 'latest')
|
||||
if os.path.isfile(latest_path):
|
||||
with open(latest_path, 'r') as fd:
|
||||
tag = fd.read().strip()
|
||||
else:
|
||||
raise ValueError(f"Unable to find 'latest' file at {latest_path}")
|
||||
|
||||
ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
|
||||
|
||||
if not os.path.isdir(ds_checkpoint_dir):
|
||||
raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
|
||||
|
||||
state_dict = _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
|
||||
if lazy_mode:
|
||||
return state_dict
|
||||
else:
|
||||
return to_torch_tensor(state_dict)
|
||||
|
||||
|
||||
def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir,
|
||||
output_dir,
|
||||
max_shard_size="5GB",
|
||||
safe_serialization=False,
|
||||
tag=None,
|
||||
exclude_frozen_parameters=False):
|
||||
"""
|
||||
Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
|
||||
loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
|
||||
|
||||
Args:
|
||||
- ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
|
||||
- ``output_dir``: directory to the pytorch fp32 state_dict output files
|
||||
- ``max_shard_size``: the maximum size for a checkpoint before being sharded, default value is 5GB
|
||||
- ``safe_serialization``: whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).
|
||||
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
|
||||
- ``exclude_frozen_parameters``: exclude frozen parameters
|
||||
"""
|
||||
|
||||
# Dependency pre-check
|
||||
if safe_serialization:
|
||||
try:
|
||||
from safetensors.torch import save_file
|
||||
except ImportError:
|
||||
print('If you want to use `safe_serialization`, please `pip install safetensors`')
|
||||
raise
|
||||
if max_shard_size is not None:
|
||||
try:
|
||||
from huggingface_hub import split_torch_state_dict_into_shards
|
||||
except ImportError:
|
||||
print('If you want to use `max_shard_size`, please `pip install huggingface_hub`')
|
||||
raise
|
||||
|
||||
# Convert zero checkpoint to state_dict
|
||||
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
|
||||
tag,
|
||||
exclude_frozen_parameters,
|
||||
lazy_mode=True)
|
||||
|
||||
# Shard the model if it is too big.
|
||||
weights_name = "model.safetensors" if safe_serialization else "pytorch_model.bin"
|
||||
if max_shard_size is not None:
|
||||
filename_pattern = weights_name.replace(".bin", "{suffix}.bin").replace(".safetensors", "{suffix}.safetensors")
|
||||
# an memory-efficient approach for sharding
|
||||
empty_state_dict = to_torch_tensor(state_dict, return_empty_tensor=True)
|
||||
state_dict_split = split_torch_state_dict_into_shards(empty_state_dict,
|
||||
filename_pattern=filename_pattern,
|
||||
max_shard_size=max_shard_size)
|
||||
else:
|
||||
from collections import namedtuple
|
||||
StateDictSplit = namedtuple("StateDictSplit", ["is_sharded", "filename_to_tensors"])
|
||||
state_dict_split = StateDictSplit(is_sharded=False,
|
||||
filename_to_tensors={weights_name: list(state_dict.keys())})
|
||||
|
||||
# Save the model by shard
|
||||
os.makedirs(output_dir, exist_ok=True)
|
||||
filename_to_tensors = state_dict_split.filename_to_tensors.items()
|
||||
for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"):
|
||||
shard_state_dict = {tensor_name: state_dict[tensor_name] for tensor_name in tensors}
|
||||
shard_state_dict = to_torch_tensor(shard_state_dict)
|
||||
output_path = os.path.join(output_dir, shard_file)
|
||||
if safe_serialization:
|
||||
save_file(shard_state_dict, output_path, metadata={"format": "pt"})
|
||||
else:
|
||||
torch.save(shard_state_dict, output_path)
|
||||
# release the memory of current shard
|
||||
for tensor_name in list(shard_state_dict.keys()):
|
||||
del state_dict[tensor_name]
|
||||
del shard_state_dict[tensor_name]
|
||||
del shard_state_dict
|
||||
gc.collect()
|
||||
|
||||
# Save index if sharded
|
||||
if state_dict_split.is_sharded:
|
||||
index = {
|
||||
"metadata": state_dict_split.metadata,
|
||||
"weight_map": state_dict_split.tensor_to_filename,
|
||||
}
|
||||
save_index_file = "model.safetensors.index.json" if safe_serialization else "pytorch_model.bin.index.json"
|
||||
save_index_file = os.path.join(output_dir, save_index_file)
|
||||
with open(save_index_file, "w", encoding="utf-8") as f:
|
||||
content = json.dumps(index, indent=2, sort_keys=True) + "\n"
|
||||
f.write(content)
|
||||
|
||||
|
||||
def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
|
||||
"""
|
||||
1. Put the provided model to cpu
|
||||
2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
|
||||
3. Load it into the provided model
|
||||
|
||||
Args:
|
||||
- ``model``: the model object to update
|
||||
- ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
|
||||
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
|
||||
|
||||
Returns:
|
||||
- ``model`: modified model
|
||||
|
||||
Make sure you have plenty of CPU memory available before you call this function. If you don't
|
||||
have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
|
||||
conveniently placed for you in the checkpoint folder.
|
||||
|
||||
A typical usage might be ::
|
||||
|
||||
from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
|
||||
model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
|
||||
# submit to model hub or save the model to share with others
|
||||
|
||||
Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
|
||||
of the same application. i.e. you will need to re-initialize the deepspeed engine, since
|
||||
``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
|
||||
|
||||
"""
|
||||
logger.info(f"Extracting fp32 weights")
|
||||
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
|
||||
|
||||
logger.info(f"Overwriting model with fp32 weights")
|
||||
model = model.cpu()
|
||||
model.load_state_dict(state_dict, strict=False)
|
||||
|
||||
return model
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
parser = argparse.ArgumentParser()
|
||||
parser.add_argument("checkpoint_dir",
|
||||
type=str,
|
||||
help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
|
||||
parser.add_argument("output_dir",
|
||||
type=str,
|
||||
help="directory to the pytorch fp32 state_dict output files"
|
||||
"(e.g. path/checkpoint-12-output/)")
|
||||
parser.add_argument(
|
||||
"--max_shard_size",
|
||||
type=str,
|
||||
default="5GB",
|
||||
help="The maximum size for a checkpoint before being sharded. Checkpoints shard will then be each of size"
|
||||
"lower than this size. If expressed as a string, needs to be digits followed by a unit (like `5MB`"
|
||||
"We default it to 5GB in order for models to be able to run easily on free-tier google colab instances"
|
||||
"without CPU OOM issues.")
|
||||
parser.add_argument(
|
||||
"--safe_serialization",
|
||||
default=False,
|
||||
action='store_true',
|
||||
help="Whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).")
|
||||
parser.add_argument("-t",
|
||||
"--tag",
|
||||
type=str,
|
||||
default=None,
|
||||
help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
|
||||
parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
|
||||
parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
|
||||
args = parser.parse_args()
|
||||
|
||||
debug = args.debug
|
||||
|
||||
convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
|
||||
args.output_dir,
|
||||
max_shard_size=args.max_shard_size,
|
||||
safe_serialization=args.safe_serialization,
|
||||
tag=args.tag,
|
||||
exclude_frozen_parameters=args.exclude_frozen_parameters)
|
||||
@@ -0,0 +1,202 @@
|
||||
---
|
||||
base_model: meta-llama/Llama-3.1-8B-Instruct
|
||||
library_name: peft
|
||||
---
|
||||
|
||||
# Model Card for Model ID
|
||||
|
||||
<!-- Provide a quick summary of what the model is/does. -->
|
||||
|
||||
|
||||
|
||||
## Model Details
|
||||
|
||||
### Model Description
|
||||
|
||||
<!-- Provide a longer summary of what this model is. -->
|
||||
|
||||
|
||||
|
||||
- **Developed by:** [More Information Needed]
|
||||
- **Funded by [optional]:** [More Information Needed]
|
||||
- **Shared by [optional]:** [More Information Needed]
|
||||
- **Model type:** [More Information Needed]
|
||||
- **Language(s) (NLP):** [More Information Needed]
|
||||
- **License:** [More Information Needed]
|
||||
- **Finetuned from model [optional]:** [More Information Needed]
|
||||
|
||||
### Model Sources [optional]
|
||||
|
||||
<!-- Provide the basic links for the model. -->
|
||||
|
||||
- **Repository:** [More Information Needed]
|
||||
- **Paper [optional]:** [More Information Needed]
|
||||
- **Demo [optional]:** [More Information Needed]
|
||||
|
||||
## Uses
|
||||
|
||||
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
||||
|
||||
### Direct Use
|
||||
|
||||
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Downstream Use [optional]
|
||||
|
||||
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Out-of-Scope Use
|
||||
|
||||
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Bias, Risks, and Limitations
|
||||
|
||||
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Recommendations
|
||||
|
||||
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
||||
|
||||
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
||||
|
||||
## How to Get Started with the Model
|
||||
|
||||
Use the code below to get started with the model.
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Training Details
|
||||
|
||||
### Training Data
|
||||
|
||||
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Training Procedure
|
||||
|
||||
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
||||
|
||||
#### Preprocessing [optional]
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
|
||||
#### Training Hyperparameters
|
||||
|
||||
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
||||
|
||||
#### Speeds, Sizes, Times [optional]
|
||||
|
||||
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Evaluation
|
||||
|
||||
<!-- This section describes the evaluation protocols and provides the results. -->
|
||||
|
||||
### Testing Data, Factors & Metrics
|
||||
|
||||
#### Testing Data
|
||||
|
||||
<!-- This should link to a Dataset Card if possible. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Factors
|
||||
|
||||
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Metrics
|
||||
|
||||
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Results
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Summary
|
||||
|
||||
|
||||
|
||||
## Model Examination [optional]
|
||||
|
||||
<!-- Relevant interpretability work for the model goes here -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Environmental Impact
|
||||
|
||||
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
||||
|
||||
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
||||
|
||||
- **Hardware Type:** [More Information Needed]
|
||||
- **Hours used:** [More Information Needed]
|
||||
- **Cloud Provider:** [More Information Needed]
|
||||
- **Compute Region:** [More Information Needed]
|
||||
- **Carbon Emitted:** [More Information Needed]
|
||||
|
||||
## Technical Specifications [optional]
|
||||
|
||||
### Model Architecture and Objective
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Compute Infrastructure
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Hardware
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Software
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Citation [optional]
|
||||
|
||||
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
||||
|
||||
**BibTeX:**
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
**APA:**
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Glossary [optional]
|
||||
|
||||
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## More Information [optional]
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Model Card Authors [optional]
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Model Card Contact
|
||||
|
||||
[More Information Needed]
|
||||
### Framework versions
|
||||
|
||||
- PEFT 0.15.2
|
||||
@@ -0,0 +1,41 @@
|
||||
{
|
||||
"alpha_pattern": {},
|
||||
"auto_mapping": null,
|
||||
"base_model_name_or_path": "meta-llama/Llama-3.1-8B-Instruct",
|
||||
"bias": "none",
|
||||
"corda_config": null,
|
||||
"eva_config": null,
|
||||
"exclude_modules": null,
|
||||
"fan_in_fan_out": false,
|
||||
"inference_mode": true,
|
||||
"init_lora_weights": true,
|
||||
"layer_replication": null,
|
||||
"layers_pattern": null,
|
||||
"layers_to_transform": null,
|
||||
"loftq_config": {},
|
||||
"lora_alpha": 256,
|
||||
"lora_bias": false,
|
||||
"lora_dropout": 0.0,
|
||||
"megatron_config": null,
|
||||
"megatron_core": "megatron.core",
|
||||
"modules_to_save": null,
|
||||
"peft_type": "LORA",
|
||||
"r": 128,
|
||||
"rank_pattern": {},
|
||||
"revision": null,
|
||||
"target_modules": [
|
||||
"o_proj",
|
||||
"up_proj",
|
||||
"k_proj",
|
||||
"down_proj",
|
||||
"lm_head",
|
||||
"gate_proj",
|
||||
"q_proj",
|
||||
"v_proj",
|
||||
"embed_tokens"
|
||||
],
|
||||
"task_type": "CAUSAL_LM",
|
||||
"trainable_token_indices": null,
|
||||
"use_dora": false,
|
||||
"use_rslora": false
|
||||
}
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:fede272bbd3ef306aec2ce96def835024e4ccc14cf25ba089b1035a098b437e4
|
||||
size 2840262376
|
||||
@@ -0,0 +1 @@
|
||||
global_step1600
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:1a8f9f34bdbb678a835d223585a0e484343976292576c76cda6742c7b929521e
|
||||
size 14960
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:4a5e5b1c29ffae78e3ceda87e7457e49cb888b5febe4260cc50e63b00a13a109
|
||||
size 14960
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:5af24eea6c41331b18581139cb0b4269f65207448657ad5d2f1ad6df5eb34f4d
|
||||
size 14960
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:844831f14bf592025fa94c318924e5902c7171e7c66c27a6f8dad455b9b18396
|
||||
size 14960
|
||||
@@ -0,0 +1,16 @@
|
||||
{
|
||||
"bos_token": {
|
||||
"content": "<|begin_of_text|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "<|eot_id|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
BIN
lora-embedding-128-llama3.1-8b-malaysian-8k/checkpoint-1600/tokenizer.json
(Stored with Git LFS)
Normal file
BIN
lora-embedding-128-llama3.1-8b-malaysian-8k/checkpoint-1600/tokenizer.json
(Stored with Git LFS)
Normal file
Binary file not shown.
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:922c4272bf2cd66460df74f5c309b6b97e5e3f4c0ba57215852b5b38fbe927c2
|
||||
size 7800
|
||||
@@ -0,0 +1,760 @@
|
||||
#!/usr/bin/env python
|
||||
|
||||
# Copyright (c) Microsoft Corporation.
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
|
||||
# DeepSpeed Team
|
||||
|
||||
# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
|
||||
# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
|
||||
# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
|
||||
# application.
|
||||
#
|
||||
# example:
|
||||
# python zero_to_fp32.py . output_dir/
|
||||
# or
|
||||
# python zero_to_fp32.py . output_dir/ --safe_serialization
|
||||
|
||||
import argparse
|
||||
import torch
|
||||
import glob
|
||||
import math
|
||||
import os
|
||||
import re
|
||||
import gc
|
||||
import json
|
||||
import numpy as np
|
||||
from tqdm import tqdm
|
||||
from collections import OrderedDict
|
||||
from dataclasses import dataclass
|
||||
|
||||
# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
|
||||
# DeepSpeed data structures it has to be available in the current python environment.
|
||||
from deepspeed.utils import logger
|
||||
from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
|
||||
FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
|
||||
FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
|
||||
|
||||
|
||||
@dataclass
|
||||
class zero_model_state:
|
||||
buffers: dict()
|
||||
param_shapes: dict()
|
||||
shared_params: list
|
||||
ds_version: int
|
||||
frozen_param_shapes: dict()
|
||||
frozen_param_fragments: dict()
|
||||
|
||||
|
||||
debug = 0
|
||||
|
||||
# load to cpu
|
||||
device = torch.device('cpu')
|
||||
|
||||
|
||||
def atoi(text):
|
||||
return int(text) if text.isdigit() else text
|
||||
|
||||
|
||||
def natural_keys(text):
|
||||
'''
|
||||
alist.sort(key=natural_keys) sorts in human order
|
||||
http://nedbatchelder.com/blog/200712/human_sorting.html
|
||||
(See Toothy's implementation in the comments)
|
||||
'''
|
||||
return [atoi(c) for c in re.split(r'(\d+)', text)]
|
||||
|
||||
|
||||
def get_model_state_file(checkpoint_dir, zero_stage):
|
||||
if not os.path.isdir(checkpoint_dir):
|
||||
raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
|
||||
|
||||
# there should be only one file
|
||||
if zero_stage <= 2:
|
||||
file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
|
||||
elif zero_stage == 3:
|
||||
file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
|
||||
|
||||
if not os.path.exists(file):
|
||||
raise FileNotFoundError(f"can't find model states file at '{file}'")
|
||||
|
||||
return file
|
||||
|
||||
|
||||
def get_checkpoint_files(checkpoint_dir, glob_pattern):
|
||||
# XXX: need to test that this simple glob rule works for multi-node setup too
|
||||
ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
|
||||
|
||||
if len(ckpt_files) == 0:
|
||||
raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
|
||||
|
||||
return ckpt_files
|
||||
|
||||
|
||||
def get_optim_files(checkpoint_dir):
|
||||
return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
|
||||
|
||||
|
||||
def get_model_state_files(checkpoint_dir):
|
||||
return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
|
||||
|
||||
|
||||
def parse_model_states(files):
|
||||
zero_model_states = []
|
||||
for file in files:
|
||||
state_dict = torch.load(file, map_location=device, weights_only=False)
|
||||
|
||||
if BUFFER_NAMES not in state_dict:
|
||||
raise ValueError(f"{file} is not a model state checkpoint")
|
||||
buffer_names = state_dict[BUFFER_NAMES]
|
||||
if debug:
|
||||
print("Found buffers:", buffer_names)
|
||||
|
||||
# recover just the buffers while restoring them to fp32 if they were saved in fp16
|
||||
buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
|
||||
param_shapes = state_dict[PARAM_SHAPES]
|
||||
|
||||
# collect parameters that are included in param_shapes
|
||||
param_names = []
|
||||
for s in param_shapes:
|
||||
for name in s.keys():
|
||||
param_names.append(name)
|
||||
|
||||
# update with frozen parameters
|
||||
frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
|
||||
if frozen_param_shapes is not None:
|
||||
if debug:
|
||||
print(f"Found frozen_param_shapes: {frozen_param_shapes}")
|
||||
param_names += list(frozen_param_shapes.keys())
|
||||
|
||||
# handle shared params
|
||||
shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
|
||||
|
||||
ds_version = state_dict.get(DS_VERSION, None)
|
||||
|
||||
frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
|
||||
|
||||
z_model_state = zero_model_state(buffers=buffers,
|
||||
param_shapes=param_shapes,
|
||||
shared_params=shared_params,
|
||||
ds_version=ds_version,
|
||||
frozen_param_shapes=frozen_param_shapes,
|
||||
frozen_param_fragments=frozen_param_fragments)
|
||||
zero_model_states.append(z_model_state)
|
||||
|
||||
return zero_model_states
|
||||
|
||||
|
||||
def parse_optim_states(files, ds_checkpoint_dir):
|
||||
total_files = len(files)
|
||||
state_dicts = []
|
||||
for f in tqdm(files, desc='Loading checkpoint shards'):
|
||||
state_dict = torch.load(f, map_location=device, mmap=True, weights_only=False)
|
||||
# immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
|
||||
# and also handle the case where it was already removed by another helper script
|
||||
state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
|
||||
state_dicts.append(state_dict)
|
||||
|
||||
if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
|
||||
raise ValueError(f"{files[0]} is not a zero checkpoint")
|
||||
zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
|
||||
world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
|
||||
|
||||
# For ZeRO-2 each param group can have different partition_count as data parallelism for expert
|
||||
# parameters can be different from data parallelism for non-expert parameters. So we can just
|
||||
# use the max of the partition_count to get the dp world_size.
|
||||
|
||||
if type(world_size) is list:
|
||||
world_size = max(world_size)
|
||||
|
||||
if world_size != total_files:
|
||||
raise ValueError(
|
||||
f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
|
||||
"Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
|
||||
)
|
||||
|
||||
# the groups are named differently in each stage
|
||||
if zero_stage <= 2:
|
||||
fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
|
||||
elif zero_stage == 3:
|
||||
fp32_groups_key = FP32_FLAT_GROUPS
|
||||
else:
|
||||
raise ValueError(f"unknown zero stage {zero_stage}")
|
||||
|
||||
fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
|
||||
return zero_stage, world_size, fp32_flat_groups
|
||||
|
||||
|
||||
def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
|
||||
"""
|
||||
Returns fp32 state_dict reconstructed from ds checkpoint
|
||||
|
||||
Args:
|
||||
- ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
|
||||
|
||||
"""
|
||||
print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
|
||||
|
||||
optim_files = get_optim_files(ds_checkpoint_dir)
|
||||
zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
|
||||
print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
|
||||
|
||||
model_files = get_model_state_files(ds_checkpoint_dir)
|
||||
|
||||
zero_model_states = parse_model_states(model_files)
|
||||
print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
|
||||
|
||||
if zero_stage <= 2:
|
||||
return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
||||
exclude_frozen_parameters)
|
||||
elif zero_stage == 3:
|
||||
return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
||||
exclude_frozen_parameters)
|
||||
|
||||
|
||||
def _zero2_merge_frozen_params(state_dict, zero_model_states):
|
||||
if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
|
||||
return
|
||||
|
||||
frozen_param_shapes = zero_model_states[0].frozen_param_shapes
|
||||
frozen_param_fragments = zero_model_states[0].frozen_param_fragments
|
||||
|
||||
if debug:
|
||||
num_elem = sum(s.numel() for s in frozen_param_shapes.values())
|
||||
print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
|
||||
|
||||
wanted_params = len(frozen_param_shapes)
|
||||
wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
|
||||
avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
|
||||
print(f'Frozen params: Have {avail_numel} numels to process.')
|
||||
print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
|
||||
|
||||
total_params = 0
|
||||
total_numel = 0
|
||||
for name, shape in frozen_param_shapes.items():
|
||||
total_params += 1
|
||||
unpartitioned_numel = shape.numel()
|
||||
total_numel += unpartitioned_numel
|
||||
|
||||
state_dict[name] = frozen_param_fragments[name]
|
||||
|
||||
if debug:
|
||||
print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
|
||||
|
||||
print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
|
||||
|
||||
|
||||
def _has_callable(obj, fn):
|
||||
attr = getattr(obj, fn, None)
|
||||
return callable(attr)
|
||||
|
||||
|
||||
def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
|
||||
param_shapes = zero_model_states[0].param_shapes
|
||||
|
||||
# Reconstruction protocol:
|
||||
#
|
||||
# XXX: document this
|
||||
|
||||
if debug:
|
||||
for i in range(world_size):
|
||||
for j in range(len(fp32_flat_groups[0])):
|
||||
print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
|
||||
|
||||
# XXX: memory usage doubles here (zero2)
|
||||
num_param_groups = len(fp32_flat_groups[0])
|
||||
merged_single_partition_of_fp32_groups = []
|
||||
for i in range(num_param_groups):
|
||||
merged_partitions = [sd[i] for sd in fp32_flat_groups]
|
||||
full_single_fp32_vector = torch.cat(merged_partitions, 0)
|
||||
merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
|
||||
avail_numel = sum(
|
||||
[full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
|
||||
|
||||
if debug:
|
||||
wanted_params = sum([len(shapes) for shapes in param_shapes])
|
||||
wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
|
||||
# not asserting if there is a mismatch due to possible padding
|
||||
print(f"Have {avail_numel} numels to process.")
|
||||
print(f"Need {wanted_numel} numels in {wanted_params} params.")
|
||||
|
||||
# params
|
||||
# XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
|
||||
# out-of-core computing solution
|
||||
total_numel = 0
|
||||
total_params = 0
|
||||
for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
|
||||
offset = 0
|
||||
avail_numel = full_single_fp32_vector.numel()
|
||||
for name, shape in shapes.items():
|
||||
|
||||
unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
|
||||
total_numel += unpartitioned_numel
|
||||
total_params += 1
|
||||
|
||||
if debug:
|
||||
print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
|
||||
state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
|
||||
offset += unpartitioned_numel
|
||||
|
||||
# Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
|
||||
# avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
|
||||
# paddings performed in the code it's almost impossible to predict the exact numbers w/o the
|
||||
# live optimizer object, so we are checking that the numbers are within the right range
|
||||
align_to = 2 * world_size
|
||||
|
||||
def zero2_align(x):
|
||||
return align_to * math.ceil(x / align_to)
|
||||
|
||||
if debug:
|
||||
print(f"original offset={offset}, avail_numel={avail_numel}")
|
||||
|
||||
offset = zero2_align(offset)
|
||||
avail_numel = zero2_align(avail_numel)
|
||||
|
||||
if debug:
|
||||
print(f"aligned offset={offset}, avail_numel={avail_numel}")
|
||||
|
||||
# Sanity check
|
||||
if offset != avail_numel:
|
||||
raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
|
||||
|
||||
print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
|
||||
|
||||
|
||||
def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
||||
exclude_frozen_parameters):
|
||||
state_dict = OrderedDict()
|
||||
|
||||
# buffers
|
||||
buffers = zero_model_states[0].buffers
|
||||
state_dict.update(buffers)
|
||||
if debug:
|
||||
print(f"added {len(buffers)} buffers")
|
||||
|
||||
if not exclude_frozen_parameters:
|
||||
_zero2_merge_frozen_params(state_dict, zero_model_states)
|
||||
|
||||
_zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
|
||||
|
||||
# recover shared parameters
|
||||
for pair in zero_model_states[0].shared_params:
|
||||
if pair[1] in state_dict:
|
||||
state_dict[pair[0]] = state_dict[pair[1]]
|
||||
|
||||
return state_dict
|
||||
|
||||
|
||||
def zero3_partitioned_param_info(unpartitioned_numel, world_size):
|
||||
remainder = unpartitioned_numel % world_size
|
||||
padding_numel = (world_size - remainder) if remainder else 0
|
||||
partitioned_numel = math.ceil(unpartitioned_numel / world_size)
|
||||
return partitioned_numel, padding_numel
|
||||
|
||||
|
||||
def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
|
||||
if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
|
||||
return
|
||||
|
||||
if debug:
|
||||
for i in range(world_size):
|
||||
num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
|
||||
print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
|
||||
|
||||
frozen_param_shapes = zero_model_states[0].frozen_param_shapes
|
||||
wanted_params = len(frozen_param_shapes)
|
||||
wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
|
||||
avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
|
||||
print(f'Frozen params: Have {avail_numel} numels to process.')
|
||||
print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
|
||||
|
||||
total_params = 0
|
||||
total_numel = 0
|
||||
for name, shape in zero_model_states[0].frozen_param_shapes.items():
|
||||
total_params += 1
|
||||
unpartitioned_numel = shape.numel()
|
||||
total_numel += unpartitioned_numel
|
||||
|
||||
param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
|
||||
state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
|
||||
|
||||
partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
|
||||
|
||||
if debug:
|
||||
print(
|
||||
f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
|
||||
)
|
||||
|
||||
print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
|
||||
|
||||
|
||||
class GatheredTensor:
|
||||
"""
|
||||
A pseudo tensor that collects partitioned weights.
|
||||
It is more memory efficient when there are multiple groups.
|
||||
"""
|
||||
|
||||
def __init__(self, flat_groups, flat_groups_offset, offset, partitioned_numel, shape):
|
||||
self.flat_groups = flat_groups
|
||||
self.flat_groups_offset = flat_groups_offset
|
||||
self.offset = offset
|
||||
self.partitioned_numel = partitioned_numel
|
||||
self.shape = shape
|
||||
self.dtype = self.flat_groups[0][0].dtype
|
||||
|
||||
def contiguous(self):
|
||||
"""
|
||||
Merge partitioned weights from flat_groups into a single tensor.
|
||||
"""
|
||||
end_idx = self.offset + self.partitioned_numel
|
||||
world_size = len(self.flat_groups)
|
||||
pad_flat_param_chunks = []
|
||||
|
||||
for rank_i in range(world_size):
|
||||
# for each rank, we need to collect weights from related group/groups
|
||||
flat_groups_at_rank_i = self.flat_groups[rank_i]
|
||||
start_group_id = None
|
||||
end_group_id = None
|
||||
for group_id in range(len(self.flat_groups_offset)):
|
||||
if self.flat_groups_offset[group_id] <= self.offset < self.flat_groups_offset[group_id + 1]:
|
||||
start_group_id = group_id
|
||||
if self.flat_groups_offset[group_id] < end_idx <= self.flat_groups_offset[group_id + 1]:
|
||||
end_group_id = group_id
|
||||
break
|
||||
# collect weights from related group/groups
|
||||
for group_id in range(start_group_id, end_group_id + 1):
|
||||
flat_tensor = flat_groups_at_rank_i[group_id]
|
||||
start_offset = self.offset - self.flat_groups_offset[group_id]
|
||||
end_offset = min(end_idx, self.flat_groups_offset[group_id + 1]) - self.flat_groups_offset[group_id]
|
||||
pad_flat_param_chunks.append(flat_tensor[start_offset:end_offset])
|
||||
|
||||
# collect weights from all ranks
|
||||
pad_flat_param = torch.cat(pad_flat_param_chunks, dim=0)
|
||||
param = pad_flat_param[:self.shape.numel()].view(self.shape).contiguous()
|
||||
return param
|
||||
|
||||
|
||||
def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
|
||||
param_shapes = zero_model_states[0].param_shapes
|
||||
avail_numel = sum([flat_group.numel() for flat_group in fp32_flat_groups[0]]) * world_size
|
||||
|
||||
# Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
|
||||
# param, re-consolidating each param, while dealing with padding if any
|
||||
|
||||
# merge list of dicts, preserving order
|
||||
param_shapes = {k: v for d in param_shapes for k, v in d.items()}
|
||||
|
||||
if debug:
|
||||
for i in range(world_size):
|
||||
print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
|
||||
|
||||
wanted_params = len(param_shapes)
|
||||
wanted_numel = sum(shape.numel() for shape in param_shapes.values())
|
||||
# not asserting if there is a mismatch due to possible padding
|
||||
avail_numel = fp32_flat_groups[0].numel() * world_size
|
||||
print(f"Trainable params: Have {avail_numel} numels to process.")
|
||||
print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
|
||||
|
||||
# params
|
||||
# XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
|
||||
# out-of-core computing solution
|
||||
offset = 0
|
||||
total_numel = 0
|
||||
total_params = 0
|
||||
flat_groups_offset = [0] + list(np.cumsum([flat_tensor.numel() for flat_tensor in fp32_flat_groups[0]]))
|
||||
for name, shape in tqdm(param_shapes.items(), desc='Gathering sharded weights'):
|
||||
unpartitioned_numel = shape.numel()
|
||||
total_numel += unpartitioned_numel
|
||||
total_params += 1
|
||||
partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
|
||||
|
||||
if debug:
|
||||
print(
|
||||
f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
|
||||
)
|
||||
|
||||
# memory efficient tensor
|
||||
tensor = GatheredTensor(fp32_flat_groups, flat_groups_offset, offset, partitioned_numel, shape)
|
||||
state_dict[name] = tensor
|
||||
offset += partitioned_numel
|
||||
|
||||
offset *= world_size
|
||||
|
||||
# Sanity check
|
||||
if offset != avail_numel:
|
||||
raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
|
||||
|
||||
print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
|
||||
|
||||
|
||||
def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
||||
exclude_frozen_parameters):
|
||||
state_dict = OrderedDict()
|
||||
|
||||
# buffers
|
||||
buffers = zero_model_states[0].buffers
|
||||
state_dict.update(buffers)
|
||||
if debug:
|
||||
print(f"added {len(buffers)} buffers")
|
||||
|
||||
if not exclude_frozen_parameters:
|
||||
_zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
|
||||
|
||||
_zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
|
||||
|
||||
# recover shared parameters
|
||||
for pair in zero_model_states[0].shared_params:
|
||||
if pair[1] in state_dict:
|
||||
state_dict[pair[0]] = state_dict[pair[1]]
|
||||
|
||||
return state_dict
|
||||
|
||||
|
||||
def to_torch_tensor(state_dict, return_empty_tensor=False):
|
||||
"""
|
||||
Convert state_dict of GatheredTensor to torch tensor
|
||||
"""
|
||||
torch_state_dict = {}
|
||||
converted_tensors = {}
|
||||
for name, tensor in state_dict.items():
|
||||
tensor_id = id(tensor)
|
||||
if tensor_id in converted_tensors: # shared tensors
|
||||
shared_tensor = torch_state_dict[converted_tensors[tensor_id]]
|
||||
torch_state_dict[name] = shared_tensor
|
||||
else:
|
||||
converted_tensors[tensor_id] = name
|
||||
if return_empty_tensor:
|
||||
torch_state_dict[name] = torch.empty(tensor.shape, dtype=tensor.dtype)
|
||||
else:
|
||||
torch_state_dict[name] = tensor.contiguous()
|
||||
return torch_state_dict
|
||||
|
||||
|
||||
def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
|
||||
tag=None,
|
||||
exclude_frozen_parameters=False,
|
||||
lazy_mode=False):
|
||||
"""
|
||||
Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
|
||||
``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
|
||||
via a model hub.
|
||||
|
||||
Args:
|
||||
- ``checkpoint_dir``: path to the desired checkpoint folder
|
||||
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
|
||||
- ``exclude_frozen_parameters``: exclude frozen parameters
|
||||
- ``lazy_mode``: get state_dict in lazy mode. It returns a dict of pesduo tensor instead of torch tensor, which is more memory efficient.
|
||||
Convert the pesduo tensor to torch tensor by ``.contiguous()``
|
||||
|
||||
Returns:
|
||||
- pytorch ``state_dict``
|
||||
|
||||
A typical usage might be ::
|
||||
|
||||
from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
|
||||
# do the training and checkpoint saving
|
||||
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
|
||||
model = model.cpu() # move to cpu
|
||||
model.load_state_dict(state_dict)
|
||||
# submit to model hub or save the model to share with others
|
||||
|
||||
In this example the ``model`` will no longer be usable in the deepspeed context of the same
|
||||
application. i.e. you will need to re-initialize the deepspeed engine, since
|
||||
``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
|
||||
|
||||
If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
|
||||
|
||||
Note: the above usage may not work if your application doesn't have sufficient free CPU memory.
|
||||
You may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
|
||||
the checkpoint. Or you can load state_dict in lazy mode ::
|
||||
|
||||
from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
|
||||
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, lazy_mode=True) # not on cpu
|
||||
for name, lazy_tensor in state_dict.item():
|
||||
tensor = lazy_tensor.contiguous() # to cpu
|
||||
print(name, tensor)
|
||||
# del tensor to release memory if it no longer in use
|
||||
"""
|
||||
if tag is None:
|
||||
latest_path = os.path.join(checkpoint_dir, 'latest')
|
||||
if os.path.isfile(latest_path):
|
||||
with open(latest_path, 'r') as fd:
|
||||
tag = fd.read().strip()
|
||||
else:
|
||||
raise ValueError(f"Unable to find 'latest' file at {latest_path}")
|
||||
|
||||
ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
|
||||
|
||||
if not os.path.isdir(ds_checkpoint_dir):
|
||||
raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
|
||||
|
||||
state_dict = _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
|
||||
if lazy_mode:
|
||||
return state_dict
|
||||
else:
|
||||
return to_torch_tensor(state_dict)
|
||||
|
||||
|
||||
def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir,
|
||||
output_dir,
|
||||
max_shard_size="5GB",
|
||||
safe_serialization=False,
|
||||
tag=None,
|
||||
exclude_frozen_parameters=False):
|
||||
"""
|
||||
Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
|
||||
loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
|
||||
|
||||
Args:
|
||||
- ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
|
||||
- ``output_dir``: directory to the pytorch fp32 state_dict output files
|
||||
- ``max_shard_size``: the maximum size for a checkpoint before being sharded, default value is 5GB
|
||||
- ``safe_serialization``: whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).
|
||||
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
|
||||
- ``exclude_frozen_parameters``: exclude frozen parameters
|
||||
"""
|
||||
|
||||
# Dependency pre-check
|
||||
if safe_serialization:
|
||||
try:
|
||||
from safetensors.torch import save_file
|
||||
except ImportError:
|
||||
print('If you want to use `safe_serialization`, please `pip install safetensors`')
|
||||
raise
|
||||
if max_shard_size is not None:
|
||||
try:
|
||||
from huggingface_hub import split_torch_state_dict_into_shards
|
||||
except ImportError:
|
||||
print('If you want to use `max_shard_size`, please `pip install huggingface_hub`')
|
||||
raise
|
||||
|
||||
# Convert zero checkpoint to state_dict
|
||||
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
|
||||
tag,
|
||||
exclude_frozen_parameters,
|
||||
lazy_mode=True)
|
||||
|
||||
# Shard the model if it is too big.
|
||||
weights_name = "model.safetensors" if safe_serialization else "pytorch_model.bin"
|
||||
if max_shard_size is not None:
|
||||
filename_pattern = weights_name.replace(".bin", "{suffix}.bin").replace(".safetensors", "{suffix}.safetensors")
|
||||
# an memory-efficient approach for sharding
|
||||
empty_state_dict = to_torch_tensor(state_dict, return_empty_tensor=True)
|
||||
state_dict_split = split_torch_state_dict_into_shards(empty_state_dict,
|
||||
filename_pattern=filename_pattern,
|
||||
max_shard_size=max_shard_size)
|
||||
else:
|
||||
from collections import namedtuple
|
||||
StateDictSplit = namedtuple("StateDictSplit", ["is_sharded", "filename_to_tensors"])
|
||||
state_dict_split = StateDictSplit(is_sharded=False,
|
||||
filename_to_tensors={weights_name: list(state_dict.keys())})
|
||||
|
||||
# Save the model by shard
|
||||
os.makedirs(output_dir, exist_ok=True)
|
||||
filename_to_tensors = state_dict_split.filename_to_tensors.items()
|
||||
for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"):
|
||||
shard_state_dict = {tensor_name: state_dict[tensor_name] for tensor_name in tensors}
|
||||
shard_state_dict = to_torch_tensor(shard_state_dict)
|
||||
output_path = os.path.join(output_dir, shard_file)
|
||||
if safe_serialization:
|
||||
save_file(shard_state_dict, output_path, metadata={"format": "pt"})
|
||||
else:
|
||||
torch.save(shard_state_dict, output_path)
|
||||
# release the memory of current shard
|
||||
for tensor_name in list(shard_state_dict.keys()):
|
||||
del state_dict[tensor_name]
|
||||
del shard_state_dict[tensor_name]
|
||||
del shard_state_dict
|
||||
gc.collect()
|
||||
|
||||
# Save index if sharded
|
||||
if state_dict_split.is_sharded:
|
||||
index = {
|
||||
"metadata": state_dict_split.metadata,
|
||||
"weight_map": state_dict_split.tensor_to_filename,
|
||||
}
|
||||
save_index_file = "model.safetensors.index.json" if safe_serialization else "pytorch_model.bin.index.json"
|
||||
save_index_file = os.path.join(output_dir, save_index_file)
|
||||
with open(save_index_file, "w", encoding="utf-8") as f:
|
||||
content = json.dumps(index, indent=2, sort_keys=True) + "\n"
|
||||
f.write(content)
|
||||
|
||||
|
||||
def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
|
||||
"""
|
||||
1. Put the provided model to cpu
|
||||
2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
|
||||
3. Load it into the provided model
|
||||
|
||||
Args:
|
||||
- ``model``: the model object to update
|
||||
- ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
|
||||
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
|
||||
|
||||
Returns:
|
||||
- ``model`: modified model
|
||||
|
||||
Make sure you have plenty of CPU memory available before you call this function. If you don't
|
||||
have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
|
||||
conveniently placed for you in the checkpoint folder.
|
||||
|
||||
A typical usage might be ::
|
||||
|
||||
from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
|
||||
model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
|
||||
# submit to model hub or save the model to share with others
|
||||
|
||||
Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
|
||||
of the same application. i.e. you will need to re-initialize the deepspeed engine, since
|
||||
``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
|
||||
|
||||
"""
|
||||
logger.info(f"Extracting fp32 weights")
|
||||
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
|
||||
|
||||
logger.info(f"Overwriting model with fp32 weights")
|
||||
model = model.cpu()
|
||||
model.load_state_dict(state_dict, strict=False)
|
||||
|
||||
return model
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
parser = argparse.ArgumentParser()
|
||||
parser.add_argument("checkpoint_dir",
|
||||
type=str,
|
||||
help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
|
||||
parser.add_argument("output_dir",
|
||||
type=str,
|
||||
help="directory to the pytorch fp32 state_dict output files"
|
||||
"(e.g. path/checkpoint-12-output/)")
|
||||
parser.add_argument(
|
||||
"--max_shard_size",
|
||||
type=str,
|
||||
default="5GB",
|
||||
help="The maximum size for a checkpoint before being sharded. Checkpoints shard will then be each of size"
|
||||
"lower than this size. If expressed as a string, needs to be digits followed by a unit (like `5MB`"
|
||||
"We default it to 5GB in order for models to be able to run easily on free-tier google colab instances"
|
||||
"without CPU OOM issues.")
|
||||
parser.add_argument(
|
||||
"--safe_serialization",
|
||||
default=False,
|
||||
action='store_true',
|
||||
help="Whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).")
|
||||
parser.add_argument("-t",
|
||||
"--tag",
|
||||
type=str,
|
||||
default=None,
|
||||
help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
|
||||
parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
|
||||
parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
|
||||
args = parser.parse_args()
|
||||
|
||||
debug = args.debug
|
||||
|
||||
convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
|
||||
args.output_dir,
|
||||
max_shard_size=args.max_shard_size,
|
||||
safe_serialization=args.safe_serialization,
|
||||
tag=args.tag,
|
||||
exclude_frozen_parameters=args.exclude_frozen_parameters)
|
||||
@@ -0,0 +1,202 @@
|
||||
---
|
||||
base_model: meta-llama/Llama-3.1-8B-Instruct
|
||||
library_name: peft
|
||||
---
|
||||
|
||||
# Model Card for Model ID
|
||||
|
||||
<!-- Provide a quick summary of what the model is/does. -->
|
||||
|
||||
|
||||
|
||||
## Model Details
|
||||
|
||||
### Model Description
|
||||
|
||||
<!-- Provide a longer summary of what this model is. -->
|
||||
|
||||
|
||||
|
||||
- **Developed by:** [More Information Needed]
|
||||
- **Funded by [optional]:** [More Information Needed]
|
||||
- **Shared by [optional]:** [More Information Needed]
|
||||
- **Model type:** [More Information Needed]
|
||||
- **Language(s) (NLP):** [More Information Needed]
|
||||
- **License:** [More Information Needed]
|
||||
- **Finetuned from model [optional]:** [More Information Needed]
|
||||
|
||||
### Model Sources [optional]
|
||||
|
||||
<!-- Provide the basic links for the model. -->
|
||||
|
||||
- **Repository:** [More Information Needed]
|
||||
- **Paper [optional]:** [More Information Needed]
|
||||
- **Demo [optional]:** [More Information Needed]
|
||||
|
||||
## Uses
|
||||
|
||||
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
||||
|
||||
### Direct Use
|
||||
|
||||
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Downstream Use [optional]
|
||||
|
||||
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Out-of-Scope Use
|
||||
|
||||
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Bias, Risks, and Limitations
|
||||
|
||||
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Recommendations
|
||||
|
||||
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
||||
|
||||
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
||||
|
||||
## How to Get Started with the Model
|
||||
|
||||
Use the code below to get started with the model.
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Training Details
|
||||
|
||||
### Training Data
|
||||
|
||||
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Training Procedure
|
||||
|
||||
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
||||
|
||||
#### Preprocessing [optional]
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
|
||||
#### Training Hyperparameters
|
||||
|
||||
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
||||
|
||||
#### Speeds, Sizes, Times [optional]
|
||||
|
||||
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Evaluation
|
||||
|
||||
<!-- This section describes the evaluation protocols and provides the results. -->
|
||||
|
||||
### Testing Data, Factors & Metrics
|
||||
|
||||
#### Testing Data
|
||||
|
||||
<!-- This should link to a Dataset Card if possible. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Factors
|
||||
|
||||
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Metrics
|
||||
|
||||
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Results
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Summary
|
||||
|
||||
|
||||
|
||||
## Model Examination [optional]
|
||||
|
||||
<!-- Relevant interpretability work for the model goes here -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Environmental Impact
|
||||
|
||||
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
||||
|
||||
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
||||
|
||||
- **Hardware Type:** [More Information Needed]
|
||||
- **Hours used:** [More Information Needed]
|
||||
- **Cloud Provider:** [More Information Needed]
|
||||
- **Compute Region:** [More Information Needed]
|
||||
- **Carbon Emitted:** [More Information Needed]
|
||||
|
||||
## Technical Specifications [optional]
|
||||
|
||||
### Model Architecture and Objective
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Compute Infrastructure
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Hardware
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Software
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Citation [optional]
|
||||
|
||||
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
||||
|
||||
**BibTeX:**
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
**APA:**
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Glossary [optional]
|
||||
|
||||
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## More Information [optional]
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Model Card Authors [optional]
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Model Card Contact
|
||||
|
||||
[More Information Needed]
|
||||
### Framework versions
|
||||
|
||||
- PEFT 0.15.2
|
||||
@@ -0,0 +1,41 @@
|
||||
{
|
||||
"alpha_pattern": {},
|
||||
"auto_mapping": null,
|
||||
"base_model_name_or_path": "meta-llama/Llama-3.1-8B-Instruct",
|
||||
"bias": "none",
|
||||
"corda_config": null,
|
||||
"eva_config": null,
|
||||
"exclude_modules": null,
|
||||
"fan_in_fan_out": false,
|
||||
"inference_mode": true,
|
||||
"init_lora_weights": true,
|
||||
"layer_replication": null,
|
||||
"layers_pattern": null,
|
||||
"layers_to_transform": null,
|
||||
"loftq_config": {},
|
||||
"lora_alpha": 256,
|
||||
"lora_bias": false,
|
||||
"lora_dropout": 0.0,
|
||||
"megatron_config": null,
|
||||
"megatron_core": "megatron.core",
|
||||
"modules_to_save": null,
|
||||
"peft_type": "LORA",
|
||||
"r": 128,
|
||||
"rank_pattern": {},
|
||||
"revision": null,
|
||||
"target_modules": [
|
||||
"o_proj",
|
||||
"up_proj",
|
||||
"k_proj",
|
||||
"down_proj",
|
||||
"lm_head",
|
||||
"gate_proj",
|
||||
"q_proj",
|
||||
"v_proj",
|
||||
"embed_tokens"
|
||||
],
|
||||
"task_type": "CAUSAL_LM",
|
||||
"trainable_token_indices": null,
|
||||
"use_dora": false,
|
||||
"use_rslora": false
|
||||
}
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d20a5472de70c9823e9ace31961953b9066abc28c0f0c32be53b244a612239dd
|
||||
size 2840262376
|
||||
@@ -0,0 +1 @@
|
||||
global_step1800
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:0b193a0ed547272d6c3634c166139c873d55a928c7ac8f1b5d6e92f114810c0c
|
||||
size 14960
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:7551ff85d4867677b7e1b7d4d94080a13904a1e477f2a4de5ff9b9f64147550c
|
||||
size 14960
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:f209e7edb72af2c188f5e5202e6acf28acaead4403a99ca926dbbb1d8725209c
|
||||
size 14960
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:1be869c74202ff09955aff2e14086d2276e40f58e7face0f723bb8dc623f7a65
|
||||
size 14960
|
||||
@@ -0,0 +1,16 @@
|
||||
{
|
||||
"bos_token": {
|
||||
"content": "<|begin_of_text|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "<|eot_id|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
BIN
lora-embedding-128-llama3.1-8b-malaysian-8k/checkpoint-1800/tokenizer.json
(Stored with Git LFS)
Normal file
BIN
lora-embedding-128-llama3.1-8b-malaysian-8k/checkpoint-1800/tokenizer.json
(Stored with Git LFS)
Normal file
Binary file not shown.
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:922c4272bf2cd66460df74f5c309b6b97e5e3f4c0ba57215852b5b38fbe927c2
|
||||
size 7800
|
||||
@@ -0,0 +1,760 @@
|
||||
#!/usr/bin/env python
|
||||
|
||||
# Copyright (c) Microsoft Corporation.
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
|
||||
# DeepSpeed Team
|
||||
|
||||
# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
|
||||
# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
|
||||
# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
|
||||
# application.
|
||||
#
|
||||
# example:
|
||||
# python zero_to_fp32.py . output_dir/
|
||||
# or
|
||||
# python zero_to_fp32.py . output_dir/ --safe_serialization
|
||||
|
||||
import argparse
|
||||
import torch
|
||||
import glob
|
||||
import math
|
||||
import os
|
||||
import re
|
||||
import gc
|
||||
import json
|
||||
import numpy as np
|
||||
from tqdm import tqdm
|
||||
from collections import OrderedDict
|
||||
from dataclasses import dataclass
|
||||
|
||||
# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
|
||||
# DeepSpeed data structures it has to be available in the current python environment.
|
||||
from deepspeed.utils import logger
|
||||
from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
|
||||
FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
|
||||
FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
|
||||
|
||||
|
||||
@dataclass
|
||||
class zero_model_state:
|
||||
buffers: dict()
|
||||
param_shapes: dict()
|
||||
shared_params: list
|
||||
ds_version: int
|
||||
frozen_param_shapes: dict()
|
||||
frozen_param_fragments: dict()
|
||||
|
||||
|
||||
debug = 0
|
||||
|
||||
# load to cpu
|
||||
device = torch.device('cpu')
|
||||
|
||||
|
||||
def atoi(text):
|
||||
return int(text) if text.isdigit() else text
|
||||
|
||||
|
||||
def natural_keys(text):
|
||||
'''
|
||||
alist.sort(key=natural_keys) sorts in human order
|
||||
http://nedbatchelder.com/blog/200712/human_sorting.html
|
||||
(See Toothy's implementation in the comments)
|
||||
'''
|
||||
return [atoi(c) for c in re.split(r'(\d+)', text)]
|
||||
|
||||
|
||||
def get_model_state_file(checkpoint_dir, zero_stage):
|
||||
if not os.path.isdir(checkpoint_dir):
|
||||
raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
|
||||
|
||||
# there should be only one file
|
||||
if zero_stage <= 2:
|
||||
file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
|
||||
elif zero_stage == 3:
|
||||
file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
|
||||
|
||||
if not os.path.exists(file):
|
||||
raise FileNotFoundError(f"can't find model states file at '{file}'")
|
||||
|
||||
return file
|
||||
|
||||
|
||||
def get_checkpoint_files(checkpoint_dir, glob_pattern):
|
||||
# XXX: need to test that this simple glob rule works for multi-node setup too
|
||||
ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
|
||||
|
||||
if len(ckpt_files) == 0:
|
||||
raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
|
||||
|
||||
return ckpt_files
|
||||
|
||||
|
||||
def get_optim_files(checkpoint_dir):
|
||||
return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
|
||||
|
||||
|
||||
def get_model_state_files(checkpoint_dir):
|
||||
return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
|
||||
|
||||
|
||||
def parse_model_states(files):
|
||||
zero_model_states = []
|
||||
for file in files:
|
||||
state_dict = torch.load(file, map_location=device, weights_only=False)
|
||||
|
||||
if BUFFER_NAMES not in state_dict:
|
||||
raise ValueError(f"{file} is not a model state checkpoint")
|
||||
buffer_names = state_dict[BUFFER_NAMES]
|
||||
if debug:
|
||||
print("Found buffers:", buffer_names)
|
||||
|
||||
# recover just the buffers while restoring them to fp32 if they were saved in fp16
|
||||
buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
|
||||
param_shapes = state_dict[PARAM_SHAPES]
|
||||
|
||||
# collect parameters that are included in param_shapes
|
||||
param_names = []
|
||||
for s in param_shapes:
|
||||
for name in s.keys():
|
||||
param_names.append(name)
|
||||
|
||||
# update with frozen parameters
|
||||
frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
|
||||
if frozen_param_shapes is not None:
|
||||
if debug:
|
||||
print(f"Found frozen_param_shapes: {frozen_param_shapes}")
|
||||
param_names += list(frozen_param_shapes.keys())
|
||||
|
||||
# handle shared params
|
||||
shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
|
||||
|
||||
ds_version = state_dict.get(DS_VERSION, None)
|
||||
|
||||
frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
|
||||
|
||||
z_model_state = zero_model_state(buffers=buffers,
|
||||
param_shapes=param_shapes,
|
||||
shared_params=shared_params,
|
||||
ds_version=ds_version,
|
||||
frozen_param_shapes=frozen_param_shapes,
|
||||
frozen_param_fragments=frozen_param_fragments)
|
||||
zero_model_states.append(z_model_state)
|
||||
|
||||
return zero_model_states
|
||||
|
||||
|
||||
def parse_optim_states(files, ds_checkpoint_dir):
|
||||
total_files = len(files)
|
||||
state_dicts = []
|
||||
for f in tqdm(files, desc='Loading checkpoint shards'):
|
||||
state_dict = torch.load(f, map_location=device, mmap=True, weights_only=False)
|
||||
# immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
|
||||
# and also handle the case where it was already removed by another helper script
|
||||
state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
|
||||
state_dicts.append(state_dict)
|
||||
|
||||
if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
|
||||
raise ValueError(f"{files[0]} is not a zero checkpoint")
|
||||
zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
|
||||
world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
|
||||
|
||||
# For ZeRO-2 each param group can have different partition_count as data parallelism for expert
|
||||
# parameters can be different from data parallelism for non-expert parameters. So we can just
|
||||
# use the max of the partition_count to get the dp world_size.
|
||||
|
||||
if type(world_size) is list:
|
||||
world_size = max(world_size)
|
||||
|
||||
if world_size != total_files:
|
||||
raise ValueError(
|
||||
f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
|
||||
"Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
|
||||
)
|
||||
|
||||
# the groups are named differently in each stage
|
||||
if zero_stage <= 2:
|
||||
fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
|
||||
elif zero_stage == 3:
|
||||
fp32_groups_key = FP32_FLAT_GROUPS
|
||||
else:
|
||||
raise ValueError(f"unknown zero stage {zero_stage}")
|
||||
|
||||
fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
|
||||
return zero_stage, world_size, fp32_flat_groups
|
||||
|
||||
|
||||
def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
|
||||
"""
|
||||
Returns fp32 state_dict reconstructed from ds checkpoint
|
||||
|
||||
Args:
|
||||
- ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
|
||||
|
||||
"""
|
||||
print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
|
||||
|
||||
optim_files = get_optim_files(ds_checkpoint_dir)
|
||||
zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
|
||||
print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
|
||||
|
||||
model_files = get_model_state_files(ds_checkpoint_dir)
|
||||
|
||||
zero_model_states = parse_model_states(model_files)
|
||||
print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
|
||||
|
||||
if zero_stage <= 2:
|
||||
return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
||||
exclude_frozen_parameters)
|
||||
elif zero_stage == 3:
|
||||
return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
||||
exclude_frozen_parameters)
|
||||
|
||||
|
||||
def _zero2_merge_frozen_params(state_dict, zero_model_states):
|
||||
if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
|
||||
return
|
||||
|
||||
frozen_param_shapes = zero_model_states[0].frozen_param_shapes
|
||||
frozen_param_fragments = zero_model_states[0].frozen_param_fragments
|
||||
|
||||
if debug:
|
||||
num_elem = sum(s.numel() for s in frozen_param_shapes.values())
|
||||
print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
|
||||
|
||||
wanted_params = len(frozen_param_shapes)
|
||||
wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
|
||||
avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
|
||||
print(f'Frozen params: Have {avail_numel} numels to process.')
|
||||
print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
|
||||
|
||||
total_params = 0
|
||||
total_numel = 0
|
||||
for name, shape in frozen_param_shapes.items():
|
||||
total_params += 1
|
||||
unpartitioned_numel = shape.numel()
|
||||
total_numel += unpartitioned_numel
|
||||
|
||||
state_dict[name] = frozen_param_fragments[name]
|
||||
|
||||
if debug:
|
||||
print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
|
||||
|
||||
print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
|
||||
|
||||
|
||||
def _has_callable(obj, fn):
|
||||
attr = getattr(obj, fn, None)
|
||||
return callable(attr)
|
||||
|
||||
|
||||
def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
|
||||
param_shapes = zero_model_states[0].param_shapes
|
||||
|
||||
# Reconstruction protocol:
|
||||
#
|
||||
# XXX: document this
|
||||
|
||||
if debug:
|
||||
for i in range(world_size):
|
||||
for j in range(len(fp32_flat_groups[0])):
|
||||
print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
|
||||
|
||||
# XXX: memory usage doubles here (zero2)
|
||||
num_param_groups = len(fp32_flat_groups[0])
|
||||
merged_single_partition_of_fp32_groups = []
|
||||
for i in range(num_param_groups):
|
||||
merged_partitions = [sd[i] for sd in fp32_flat_groups]
|
||||
full_single_fp32_vector = torch.cat(merged_partitions, 0)
|
||||
merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
|
||||
avail_numel = sum(
|
||||
[full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
|
||||
|
||||
if debug:
|
||||
wanted_params = sum([len(shapes) for shapes in param_shapes])
|
||||
wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
|
||||
# not asserting if there is a mismatch due to possible padding
|
||||
print(f"Have {avail_numel} numels to process.")
|
||||
print(f"Need {wanted_numel} numels in {wanted_params} params.")
|
||||
|
||||
# params
|
||||
# XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
|
||||
# out-of-core computing solution
|
||||
total_numel = 0
|
||||
total_params = 0
|
||||
for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
|
||||
offset = 0
|
||||
avail_numel = full_single_fp32_vector.numel()
|
||||
for name, shape in shapes.items():
|
||||
|
||||
unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
|
||||
total_numel += unpartitioned_numel
|
||||
total_params += 1
|
||||
|
||||
if debug:
|
||||
print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
|
||||
state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
|
||||
offset += unpartitioned_numel
|
||||
|
||||
# Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
|
||||
# avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
|
||||
# paddings performed in the code it's almost impossible to predict the exact numbers w/o the
|
||||
# live optimizer object, so we are checking that the numbers are within the right range
|
||||
align_to = 2 * world_size
|
||||
|
||||
def zero2_align(x):
|
||||
return align_to * math.ceil(x / align_to)
|
||||
|
||||
if debug:
|
||||
print(f"original offset={offset}, avail_numel={avail_numel}")
|
||||
|
||||
offset = zero2_align(offset)
|
||||
avail_numel = zero2_align(avail_numel)
|
||||
|
||||
if debug:
|
||||
print(f"aligned offset={offset}, avail_numel={avail_numel}")
|
||||
|
||||
# Sanity check
|
||||
if offset != avail_numel:
|
||||
raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
|
||||
|
||||
print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
|
||||
|
||||
|
||||
def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
||||
exclude_frozen_parameters):
|
||||
state_dict = OrderedDict()
|
||||
|
||||
# buffers
|
||||
buffers = zero_model_states[0].buffers
|
||||
state_dict.update(buffers)
|
||||
if debug:
|
||||
print(f"added {len(buffers)} buffers")
|
||||
|
||||
if not exclude_frozen_parameters:
|
||||
_zero2_merge_frozen_params(state_dict, zero_model_states)
|
||||
|
||||
_zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
|
||||
|
||||
# recover shared parameters
|
||||
for pair in zero_model_states[0].shared_params:
|
||||
if pair[1] in state_dict:
|
||||
state_dict[pair[0]] = state_dict[pair[1]]
|
||||
|
||||
return state_dict
|
||||
|
||||
|
||||
def zero3_partitioned_param_info(unpartitioned_numel, world_size):
|
||||
remainder = unpartitioned_numel % world_size
|
||||
padding_numel = (world_size - remainder) if remainder else 0
|
||||
partitioned_numel = math.ceil(unpartitioned_numel / world_size)
|
||||
return partitioned_numel, padding_numel
|
||||
|
||||
|
||||
def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
|
||||
if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
|
||||
return
|
||||
|
||||
if debug:
|
||||
for i in range(world_size):
|
||||
num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
|
||||
print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
|
||||
|
||||
frozen_param_shapes = zero_model_states[0].frozen_param_shapes
|
||||
wanted_params = len(frozen_param_shapes)
|
||||
wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
|
||||
avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
|
||||
print(f'Frozen params: Have {avail_numel} numels to process.')
|
||||
print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
|
||||
|
||||
total_params = 0
|
||||
total_numel = 0
|
||||
for name, shape in zero_model_states[0].frozen_param_shapes.items():
|
||||
total_params += 1
|
||||
unpartitioned_numel = shape.numel()
|
||||
total_numel += unpartitioned_numel
|
||||
|
||||
param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
|
||||
state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
|
||||
|
||||
partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
|
||||
|
||||
if debug:
|
||||
print(
|
||||
f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
|
||||
)
|
||||
|
||||
print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
|
||||
|
||||
|
||||
class GatheredTensor:
|
||||
"""
|
||||
A pseudo tensor that collects partitioned weights.
|
||||
It is more memory efficient when there are multiple groups.
|
||||
"""
|
||||
|
||||
def __init__(self, flat_groups, flat_groups_offset, offset, partitioned_numel, shape):
|
||||
self.flat_groups = flat_groups
|
||||
self.flat_groups_offset = flat_groups_offset
|
||||
self.offset = offset
|
||||
self.partitioned_numel = partitioned_numel
|
||||
self.shape = shape
|
||||
self.dtype = self.flat_groups[0][0].dtype
|
||||
|
||||
def contiguous(self):
|
||||
"""
|
||||
Merge partitioned weights from flat_groups into a single tensor.
|
||||
"""
|
||||
end_idx = self.offset + self.partitioned_numel
|
||||
world_size = len(self.flat_groups)
|
||||
pad_flat_param_chunks = []
|
||||
|
||||
for rank_i in range(world_size):
|
||||
# for each rank, we need to collect weights from related group/groups
|
||||
flat_groups_at_rank_i = self.flat_groups[rank_i]
|
||||
start_group_id = None
|
||||
end_group_id = None
|
||||
for group_id in range(len(self.flat_groups_offset)):
|
||||
if self.flat_groups_offset[group_id] <= self.offset < self.flat_groups_offset[group_id + 1]:
|
||||
start_group_id = group_id
|
||||
if self.flat_groups_offset[group_id] < end_idx <= self.flat_groups_offset[group_id + 1]:
|
||||
end_group_id = group_id
|
||||
break
|
||||
# collect weights from related group/groups
|
||||
for group_id in range(start_group_id, end_group_id + 1):
|
||||
flat_tensor = flat_groups_at_rank_i[group_id]
|
||||
start_offset = self.offset - self.flat_groups_offset[group_id]
|
||||
end_offset = min(end_idx, self.flat_groups_offset[group_id + 1]) - self.flat_groups_offset[group_id]
|
||||
pad_flat_param_chunks.append(flat_tensor[start_offset:end_offset])
|
||||
|
||||
# collect weights from all ranks
|
||||
pad_flat_param = torch.cat(pad_flat_param_chunks, dim=0)
|
||||
param = pad_flat_param[:self.shape.numel()].view(self.shape).contiguous()
|
||||
return param
|
||||
|
||||
|
||||
def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
|
||||
param_shapes = zero_model_states[0].param_shapes
|
||||
avail_numel = sum([flat_group.numel() for flat_group in fp32_flat_groups[0]]) * world_size
|
||||
|
||||
# Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
|
||||
# param, re-consolidating each param, while dealing with padding if any
|
||||
|
||||
# merge list of dicts, preserving order
|
||||
param_shapes = {k: v for d in param_shapes for k, v in d.items()}
|
||||
|
||||
if debug:
|
||||
for i in range(world_size):
|
||||
print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
|
||||
|
||||
wanted_params = len(param_shapes)
|
||||
wanted_numel = sum(shape.numel() for shape in param_shapes.values())
|
||||
# not asserting if there is a mismatch due to possible padding
|
||||
avail_numel = fp32_flat_groups[0].numel() * world_size
|
||||
print(f"Trainable params: Have {avail_numel} numels to process.")
|
||||
print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
|
||||
|
||||
# params
|
||||
# XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
|
||||
# out-of-core computing solution
|
||||
offset = 0
|
||||
total_numel = 0
|
||||
total_params = 0
|
||||
flat_groups_offset = [0] + list(np.cumsum([flat_tensor.numel() for flat_tensor in fp32_flat_groups[0]]))
|
||||
for name, shape in tqdm(param_shapes.items(), desc='Gathering sharded weights'):
|
||||
unpartitioned_numel = shape.numel()
|
||||
total_numel += unpartitioned_numel
|
||||
total_params += 1
|
||||
partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
|
||||
|
||||
if debug:
|
||||
print(
|
||||
f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
|
||||
)
|
||||
|
||||
# memory efficient tensor
|
||||
tensor = GatheredTensor(fp32_flat_groups, flat_groups_offset, offset, partitioned_numel, shape)
|
||||
state_dict[name] = tensor
|
||||
offset += partitioned_numel
|
||||
|
||||
offset *= world_size
|
||||
|
||||
# Sanity check
|
||||
if offset != avail_numel:
|
||||
raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
|
||||
|
||||
print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
|
||||
|
||||
|
||||
def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
||||
exclude_frozen_parameters):
|
||||
state_dict = OrderedDict()
|
||||
|
||||
# buffers
|
||||
buffers = zero_model_states[0].buffers
|
||||
state_dict.update(buffers)
|
||||
if debug:
|
||||
print(f"added {len(buffers)} buffers")
|
||||
|
||||
if not exclude_frozen_parameters:
|
||||
_zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
|
||||
|
||||
_zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
|
||||
|
||||
# recover shared parameters
|
||||
for pair in zero_model_states[0].shared_params:
|
||||
if pair[1] in state_dict:
|
||||
state_dict[pair[0]] = state_dict[pair[1]]
|
||||
|
||||
return state_dict
|
||||
|
||||
|
||||
def to_torch_tensor(state_dict, return_empty_tensor=False):
|
||||
"""
|
||||
Convert state_dict of GatheredTensor to torch tensor
|
||||
"""
|
||||
torch_state_dict = {}
|
||||
converted_tensors = {}
|
||||
for name, tensor in state_dict.items():
|
||||
tensor_id = id(tensor)
|
||||
if tensor_id in converted_tensors: # shared tensors
|
||||
shared_tensor = torch_state_dict[converted_tensors[tensor_id]]
|
||||
torch_state_dict[name] = shared_tensor
|
||||
else:
|
||||
converted_tensors[tensor_id] = name
|
||||
if return_empty_tensor:
|
||||
torch_state_dict[name] = torch.empty(tensor.shape, dtype=tensor.dtype)
|
||||
else:
|
||||
torch_state_dict[name] = tensor.contiguous()
|
||||
return torch_state_dict
|
||||
|
||||
|
||||
def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
|
||||
tag=None,
|
||||
exclude_frozen_parameters=False,
|
||||
lazy_mode=False):
|
||||
"""
|
||||
Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
|
||||
``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
|
||||
via a model hub.
|
||||
|
||||
Args:
|
||||
- ``checkpoint_dir``: path to the desired checkpoint folder
|
||||
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
|
||||
- ``exclude_frozen_parameters``: exclude frozen parameters
|
||||
- ``lazy_mode``: get state_dict in lazy mode. It returns a dict of pesduo tensor instead of torch tensor, which is more memory efficient.
|
||||
Convert the pesduo tensor to torch tensor by ``.contiguous()``
|
||||
|
||||
Returns:
|
||||
- pytorch ``state_dict``
|
||||
|
||||
A typical usage might be ::
|
||||
|
||||
from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
|
||||
# do the training and checkpoint saving
|
||||
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
|
||||
model = model.cpu() # move to cpu
|
||||
model.load_state_dict(state_dict)
|
||||
# submit to model hub or save the model to share with others
|
||||
|
||||
In this example the ``model`` will no longer be usable in the deepspeed context of the same
|
||||
application. i.e. you will need to re-initialize the deepspeed engine, since
|
||||
``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
|
||||
|
||||
If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
|
||||
|
||||
Note: the above usage may not work if your application doesn't have sufficient free CPU memory.
|
||||
You may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
|
||||
the checkpoint. Or you can load state_dict in lazy mode ::
|
||||
|
||||
from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
|
||||
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, lazy_mode=True) # not on cpu
|
||||
for name, lazy_tensor in state_dict.item():
|
||||
tensor = lazy_tensor.contiguous() # to cpu
|
||||
print(name, tensor)
|
||||
# del tensor to release memory if it no longer in use
|
||||
"""
|
||||
if tag is None:
|
||||
latest_path = os.path.join(checkpoint_dir, 'latest')
|
||||
if os.path.isfile(latest_path):
|
||||
with open(latest_path, 'r') as fd:
|
||||
tag = fd.read().strip()
|
||||
else:
|
||||
raise ValueError(f"Unable to find 'latest' file at {latest_path}")
|
||||
|
||||
ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
|
||||
|
||||
if not os.path.isdir(ds_checkpoint_dir):
|
||||
raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
|
||||
|
||||
state_dict = _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
|
||||
if lazy_mode:
|
||||
return state_dict
|
||||
else:
|
||||
return to_torch_tensor(state_dict)
|
||||
|
||||
|
||||
def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir,
|
||||
output_dir,
|
||||
max_shard_size="5GB",
|
||||
safe_serialization=False,
|
||||
tag=None,
|
||||
exclude_frozen_parameters=False):
|
||||
"""
|
||||
Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
|
||||
loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
|
||||
|
||||
Args:
|
||||
- ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
|
||||
- ``output_dir``: directory to the pytorch fp32 state_dict output files
|
||||
- ``max_shard_size``: the maximum size for a checkpoint before being sharded, default value is 5GB
|
||||
- ``safe_serialization``: whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).
|
||||
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
|
||||
- ``exclude_frozen_parameters``: exclude frozen parameters
|
||||
"""
|
||||
|
||||
# Dependency pre-check
|
||||
if safe_serialization:
|
||||
try:
|
||||
from safetensors.torch import save_file
|
||||
except ImportError:
|
||||
print('If you want to use `safe_serialization`, please `pip install safetensors`')
|
||||
raise
|
||||
if max_shard_size is not None:
|
||||
try:
|
||||
from huggingface_hub import split_torch_state_dict_into_shards
|
||||
except ImportError:
|
||||
print('If you want to use `max_shard_size`, please `pip install huggingface_hub`')
|
||||
raise
|
||||
|
||||
# Convert zero checkpoint to state_dict
|
||||
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
|
||||
tag,
|
||||
exclude_frozen_parameters,
|
||||
lazy_mode=True)
|
||||
|
||||
# Shard the model if it is too big.
|
||||
weights_name = "model.safetensors" if safe_serialization else "pytorch_model.bin"
|
||||
if max_shard_size is not None:
|
||||
filename_pattern = weights_name.replace(".bin", "{suffix}.bin").replace(".safetensors", "{suffix}.safetensors")
|
||||
# an memory-efficient approach for sharding
|
||||
empty_state_dict = to_torch_tensor(state_dict, return_empty_tensor=True)
|
||||
state_dict_split = split_torch_state_dict_into_shards(empty_state_dict,
|
||||
filename_pattern=filename_pattern,
|
||||
max_shard_size=max_shard_size)
|
||||
else:
|
||||
from collections import namedtuple
|
||||
StateDictSplit = namedtuple("StateDictSplit", ["is_sharded", "filename_to_tensors"])
|
||||
state_dict_split = StateDictSplit(is_sharded=False,
|
||||
filename_to_tensors={weights_name: list(state_dict.keys())})
|
||||
|
||||
# Save the model by shard
|
||||
os.makedirs(output_dir, exist_ok=True)
|
||||
filename_to_tensors = state_dict_split.filename_to_tensors.items()
|
||||
for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"):
|
||||
shard_state_dict = {tensor_name: state_dict[tensor_name] for tensor_name in tensors}
|
||||
shard_state_dict = to_torch_tensor(shard_state_dict)
|
||||
output_path = os.path.join(output_dir, shard_file)
|
||||
if safe_serialization:
|
||||
save_file(shard_state_dict, output_path, metadata={"format": "pt"})
|
||||
else:
|
||||
torch.save(shard_state_dict, output_path)
|
||||
# release the memory of current shard
|
||||
for tensor_name in list(shard_state_dict.keys()):
|
||||
del state_dict[tensor_name]
|
||||
del shard_state_dict[tensor_name]
|
||||
del shard_state_dict
|
||||
gc.collect()
|
||||
|
||||
# Save index if sharded
|
||||
if state_dict_split.is_sharded:
|
||||
index = {
|
||||
"metadata": state_dict_split.metadata,
|
||||
"weight_map": state_dict_split.tensor_to_filename,
|
||||
}
|
||||
save_index_file = "model.safetensors.index.json" if safe_serialization else "pytorch_model.bin.index.json"
|
||||
save_index_file = os.path.join(output_dir, save_index_file)
|
||||
with open(save_index_file, "w", encoding="utf-8") as f:
|
||||
content = json.dumps(index, indent=2, sort_keys=True) + "\n"
|
||||
f.write(content)
|
||||
|
||||
|
||||
def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
|
||||
"""
|
||||
1. Put the provided model to cpu
|
||||
2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
|
||||
3. Load it into the provided model
|
||||
|
||||
Args:
|
||||
- ``model``: the model object to update
|
||||
- ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
|
||||
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
|
||||
|
||||
Returns:
|
||||
- ``model`: modified model
|
||||
|
||||
Make sure you have plenty of CPU memory available before you call this function. If you don't
|
||||
have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
|
||||
conveniently placed for you in the checkpoint folder.
|
||||
|
||||
A typical usage might be ::
|
||||
|
||||
from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
|
||||
model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
|
||||
# submit to model hub or save the model to share with others
|
||||
|
||||
Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
|
||||
of the same application. i.e. you will need to re-initialize the deepspeed engine, since
|
||||
``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
|
||||
|
||||
"""
|
||||
logger.info(f"Extracting fp32 weights")
|
||||
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
|
||||
|
||||
logger.info(f"Overwriting model with fp32 weights")
|
||||
model = model.cpu()
|
||||
model.load_state_dict(state_dict, strict=False)
|
||||
|
||||
return model
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
parser = argparse.ArgumentParser()
|
||||
parser.add_argument("checkpoint_dir",
|
||||
type=str,
|
||||
help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
|
||||
parser.add_argument("output_dir",
|
||||
type=str,
|
||||
help="directory to the pytorch fp32 state_dict output files"
|
||||
"(e.g. path/checkpoint-12-output/)")
|
||||
parser.add_argument(
|
||||
"--max_shard_size",
|
||||
type=str,
|
||||
default="5GB",
|
||||
help="The maximum size for a checkpoint before being sharded. Checkpoints shard will then be each of size"
|
||||
"lower than this size. If expressed as a string, needs to be digits followed by a unit (like `5MB`"
|
||||
"We default it to 5GB in order for models to be able to run easily on free-tier google colab instances"
|
||||
"without CPU OOM issues.")
|
||||
parser.add_argument(
|
||||
"--safe_serialization",
|
||||
default=False,
|
||||
action='store_true',
|
||||
help="Whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).")
|
||||
parser.add_argument("-t",
|
||||
"--tag",
|
||||
type=str,
|
||||
default=None,
|
||||
help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
|
||||
parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
|
||||
parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
|
||||
args = parser.parse_args()
|
||||
|
||||
debug = args.debug
|
||||
|
||||
convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
|
||||
args.output_dir,
|
||||
max_shard_size=args.max_shard_size,
|
||||
safe_serialization=args.safe_serialization,
|
||||
tag=args.tag,
|
||||
exclude_frozen_parameters=args.exclude_frozen_parameters)
|
||||
@@ -0,0 +1,202 @@
|
||||
---
|
||||
base_model: meta-llama/Llama-3.1-8B-Instruct
|
||||
library_name: peft
|
||||
---
|
||||
|
||||
# Model Card for Model ID
|
||||
|
||||
<!-- Provide a quick summary of what the model is/does. -->
|
||||
|
||||
|
||||
|
||||
## Model Details
|
||||
|
||||
### Model Description
|
||||
|
||||
<!-- Provide a longer summary of what this model is. -->
|
||||
|
||||
|
||||
|
||||
- **Developed by:** [More Information Needed]
|
||||
- **Funded by [optional]:** [More Information Needed]
|
||||
- **Shared by [optional]:** [More Information Needed]
|
||||
- **Model type:** [More Information Needed]
|
||||
- **Language(s) (NLP):** [More Information Needed]
|
||||
- **License:** [More Information Needed]
|
||||
- **Finetuned from model [optional]:** [More Information Needed]
|
||||
|
||||
### Model Sources [optional]
|
||||
|
||||
<!-- Provide the basic links for the model. -->
|
||||
|
||||
- **Repository:** [More Information Needed]
|
||||
- **Paper [optional]:** [More Information Needed]
|
||||
- **Demo [optional]:** [More Information Needed]
|
||||
|
||||
## Uses
|
||||
|
||||
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
||||
|
||||
### Direct Use
|
||||
|
||||
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Downstream Use [optional]
|
||||
|
||||
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Out-of-Scope Use
|
||||
|
||||
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Bias, Risks, and Limitations
|
||||
|
||||
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Recommendations
|
||||
|
||||
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
||||
|
||||
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
||||
|
||||
## How to Get Started with the Model
|
||||
|
||||
Use the code below to get started with the model.
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Training Details
|
||||
|
||||
### Training Data
|
||||
|
||||
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Training Procedure
|
||||
|
||||
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
||||
|
||||
#### Preprocessing [optional]
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
|
||||
#### Training Hyperparameters
|
||||
|
||||
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
||||
|
||||
#### Speeds, Sizes, Times [optional]
|
||||
|
||||
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Evaluation
|
||||
|
||||
<!-- This section describes the evaluation protocols and provides the results. -->
|
||||
|
||||
### Testing Data, Factors & Metrics
|
||||
|
||||
#### Testing Data
|
||||
|
||||
<!-- This should link to a Dataset Card if possible. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Factors
|
||||
|
||||
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Metrics
|
||||
|
||||
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Results
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Summary
|
||||
|
||||
|
||||
|
||||
## Model Examination [optional]
|
||||
|
||||
<!-- Relevant interpretability work for the model goes here -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Environmental Impact
|
||||
|
||||
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
||||
|
||||
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
||||
|
||||
- **Hardware Type:** [More Information Needed]
|
||||
- **Hours used:** [More Information Needed]
|
||||
- **Cloud Provider:** [More Information Needed]
|
||||
- **Compute Region:** [More Information Needed]
|
||||
- **Carbon Emitted:** [More Information Needed]
|
||||
|
||||
## Technical Specifications [optional]
|
||||
|
||||
### Model Architecture and Objective
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Compute Infrastructure
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Hardware
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Software
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Citation [optional]
|
||||
|
||||
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
||||
|
||||
**BibTeX:**
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
**APA:**
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Glossary [optional]
|
||||
|
||||
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## More Information [optional]
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Model Card Authors [optional]
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Model Card Contact
|
||||
|
||||
[More Information Needed]
|
||||
### Framework versions
|
||||
|
||||
- PEFT 0.15.2
|
||||
@@ -0,0 +1,41 @@
|
||||
{
|
||||
"alpha_pattern": {},
|
||||
"auto_mapping": null,
|
||||
"base_model_name_or_path": "meta-llama/Llama-3.1-8B-Instruct",
|
||||
"bias": "none",
|
||||
"corda_config": null,
|
||||
"eva_config": null,
|
||||
"exclude_modules": null,
|
||||
"fan_in_fan_out": false,
|
||||
"inference_mode": true,
|
||||
"init_lora_weights": true,
|
||||
"layer_replication": null,
|
||||
"layers_pattern": null,
|
||||
"layers_to_transform": null,
|
||||
"loftq_config": {},
|
||||
"lora_alpha": 256,
|
||||
"lora_bias": false,
|
||||
"lora_dropout": 0.0,
|
||||
"megatron_config": null,
|
||||
"megatron_core": "megatron.core",
|
||||
"modules_to_save": null,
|
||||
"peft_type": "LORA",
|
||||
"r": 128,
|
||||
"rank_pattern": {},
|
||||
"revision": null,
|
||||
"target_modules": [
|
||||
"o_proj",
|
||||
"up_proj",
|
||||
"k_proj",
|
||||
"down_proj",
|
||||
"lm_head",
|
||||
"gate_proj",
|
||||
"q_proj",
|
||||
"v_proj",
|
||||
"embed_tokens"
|
||||
],
|
||||
"task_type": "CAUSAL_LM",
|
||||
"trainable_token_indices": null,
|
||||
"use_dora": false,
|
||||
"use_rslora": false
|
||||
}
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:edebb8dbe11f0549cbd69a9e60bac91eb7aa4f1ea4ebb0da95d570247a693407
|
||||
size 2840262376
|
||||
@@ -0,0 +1 @@
|
||||
global_step200
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:1a0d477f40dfde214f6089e1817f4376b15f321f02e31d8b4afb55329d9162d7
|
||||
size 14960
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:00ed91261a32431ac6504c6c0135b9ed16689ab0432c4440d1fc5bb455b4f846
|
||||
size 14960
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:bfbc200ac95494637db7600f19125b61c66c248876994caf4e0e349b5dfa41fd
|
||||
size 14960
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:09a0ffb15b42980f9208ee1d9af0b4ea112ceaad3ab07668725a6ad97f2c911d
|
||||
size 14960
|
||||
@@ -0,0 +1,16 @@
|
||||
{
|
||||
"bos_token": {
|
||||
"content": "<|begin_of_text|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "<|eot_id|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
BIN
lora-embedding-128-llama3.1-8b-malaysian-8k/checkpoint-200/tokenizer.json
(Stored with Git LFS)
Normal file
BIN
lora-embedding-128-llama3.1-8b-malaysian-8k/checkpoint-200/tokenizer.json
(Stored with Git LFS)
Normal file
Binary file not shown.
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:922c4272bf2cd66460df74f5c309b6b97e5e3f4c0ba57215852b5b38fbe927c2
|
||||
size 7800
|
||||
@@ -0,0 +1,760 @@
|
||||
#!/usr/bin/env python
|
||||
|
||||
# Copyright (c) Microsoft Corporation.
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
|
||||
# DeepSpeed Team
|
||||
|
||||
# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
|
||||
# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
|
||||
# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
|
||||
# application.
|
||||
#
|
||||
# example:
|
||||
# python zero_to_fp32.py . output_dir/
|
||||
# or
|
||||
# python zero_to_fp32.py . output_dir/ --safe_serialization
|
||||
|
||||
import argparse
|
||||
import torch
|
||||
import glob
|
||||
import math
|
||||
import os
|
||||
import re
|
||||
import gc
|
||||
import json
|
||||
import numpy as np
|
||||
from tqdm import tqdm
|
||||
from collections import OrderedDict
|
||||
from dataclasses import dataclass
|
||||
|
||||
# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
|
||||
# DeepSpeed data structures it has to be available in the current python environment.
|
||||
from deepspeed.utils import logger
|
||||
from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
|
||||
FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
|
||||
FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
|
||||
|
||||
|
||||
@dataclass
|
||||
class zero_model_state:
|
||||
buffers: dict()
|
||||
param_shapes: dict()
|
||||
shared_params: list
|
||||
ds_version: int
|
||||
frozen_param_shapes: dict()
|
||||
frozen_param_fragments: dict()
|
||||
|
||||
|
||||
debug = 0
|
||||
|
||||
# load to cpu
|
||||
device = torch.device('cpu')
|
||||
|
||||
|
||||
def atoi(text):
|
||||
return int(text) if text.isdigit() else text
|
||||
|
||||
|
||||
def natural_keys(text):
|
||||
'''
|
||||
alist.sort(key=natural_keys) sorts in human order
|
||||
http://nedbatchelder.com/blog/200712/human_sorting.html
|
||||
(See Toothy's implementation in the comments)
|
||||
'''
|
||||
return [atoi(c) for c in re.split(r'(\d+)', text)]
|
||||
|
||||
|
||||
def get_model_state_file(checkpoint_dir, zero_stage):
|
||||
if not os.path.isdir(checkpoint_dir):
|
||||
raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
|
||||
|
||||
# there should be only one file
|
||||
if zero_stage <= 2:
|
||||
file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
|
||||
elif zero_stage == 3:
|
||||
file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
|
||||
|
||||
if not os.path.exists(file):
|
||||
raise FileNotFoundError(f"can't find model states file at '{file}'")
|
||||
|
||||
return file
|
||||
|
||||
|
||||
def get_checkpoint_files(checkpoint_dir, glob_pattern):
|
||||
# XXX: need to test that this simple glob rule works for multi-node setup too
|
||||
ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
|
||||
|
||||
if len(ckpt_files) == 0:
|
||||
raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
|
||||
|
||||
return ckpt_files
|
||||
|
||||
|
||||
def get_optim_files(checkpoint_dir):
|
||||
return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
|
||||
|
||||
|
||||
def get_model_state_files(checkpoint_dir):
|
||||
return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
|
||||
|
||||
|
||||
def parse_model_states(files):
|
||||
zero_model_states = []
|
||||
for file in files:
|
||||
state_dict = torch.load(file, map_location=device, weights_only=False)
|
||||
|
||||
if BUFFER_NAMES not in state_dict:
|
||||
raise ValueError(f"{file} is not a model state checkpoint")
|
||||
buffer_names = state_dict[BUFFER_NAMES]
|
||||
if debug:
|
||||
print("Found buffers:", buffer_names)
|
||||
|
||||
# recover just the buffers while restoring them to fp32 if they were saved in fp16
|
||||
buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
|
||||
param_shapes = state_dict[PARAM_SHAPES]
|
||||
|
||||
# collect parameters that are included in param_shapes
|
||||
param_names = []
|
||||
for s in param_shapes:
|
||||
for name in s.keys():
|
||||
param_names.append(name)
|
||||
|
||||
# update with frozen parameters
|
||||
frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
|
||||
if frozen_param_shapes is not None:
|
||||
if debug:
|
||||
print(f"Found frozen_param_shapes: {frozen_param_shapes}")
|
||||
param_names += list(frozen_param_shapes.keys())
|
||||
|
||||
# handle shared params
|
||||
shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
|
||||
|
||||
ds_version = state_dict.get(DS_VERSION, None)
|
||||
|
||||
frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
|
||||
|
||||
z_model_state = zero_model_state(buffers=buffers,
|
||||
param_shapes=param_shapes,
|
||||
shared_params=shared_params,
|
||||
ds_version=ds_version,
|
||||
frozen_param_shapes=frozen_param_shapes,
|
||||
frozen_param_fragments=frozen_param_fragments)
|
||||
zero_model_states.append(z_model_state)
|
||||
|
||||
return zero_model_states
|
||||
|
||||
|
||||
def parse_optim_states(files, ds_checkpoint_dir):
|
||||
total_files = len(files)
|
||||
state_dicts = []
|
||||
for f in tqdm(files, desc='Loading checkpoint shards'):
|
||||
state_dict = torch.load(f, map_location=device, mmap=True, weights_only=False)
|
||||
# immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
|
||||
# and also handle the case where it was already removed by another helper script
|
||||
state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
|
||||
state_dicts.append(state_dict)
|
||||
|
||||
if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
|
||||
raise ValueError(f"{files[0]} is not a zero checkpoint")
|
||||
zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
|
||||
world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
|
||||
|
||||
# For ZeRO-2 each param group can have different partition_count as data parallelism for expert
|
||||
# parameters can be different from data parallelism for non-expert parameters. So we can just
|
||||
# use the max of the partition_count to get the dp world_size.
|
||||
|
||||
if type(world_size) is list:
|
||||
world_size = max(world_size)
|
||||
|
||||
if world_size != total_files:
|
||||
raise ValueError(
|
||||
f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
|
||||
"Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
|
||||
)
|
||||
|
||||
# the groups are named differently in each stage
|
||||
if zero_stage <= 2:
|
||||
fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
|
||||
elif zero_stage == 3:
|
||||
fp32_groups_key = FP32_FLAT_GROUPS
|
||||
else:
|
||||
raise ValueError(f"unknown zero stage {zero_stage}")
|
||||
|
||||
fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
|
||||
return zero_stage, world_size, fp32_flat_groups
|
||||
|
||||
|
||||
def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
|
||||
"""
|
||||
Returns fp32 state_dict reconstructed from ds checkpoint
|
||||
|
||||
Args:
|
||||
- ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
|
||||
|
||||
"""
|
||||
print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
|
||||
|
||||
optim_files = get_optim_files(ds_checkpoint_dir)
|
||||
zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
|
||||
print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
|
||||
|
||||
model_files = get_model_state_files(ds_checkpoint_dir)
|
||||
|
||||
zero_model_states = parse_model_states(model_files)
|
||||
print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
|
||||
|
||||
if zero_stage <= 2:
|
||||
return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
||||
exclude_frozen_parameters)
|
||||
elif zero_stage == 3:
|
||||
return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
||||
exclude_frozen_parameters)
|
||||
|
||||
|
||||
def _zero2_merge_frozen_params(state_dict, zero_model_states):
|
||||
if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
|
||||
return
|
||||
|
||||
frozen_param_shapes = zero_model_states[0].frozen_param_shapes
|
||||
frozen_param_fragments = zero_model_states[0].frozen_param_fragments
|
||||
|
||||
if debug:
|
||||
num_elem = sum(s.numel() for s in frozen_param_shapes.values())
|
||||
print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
|
||||
|
||||
wanted_params = len(frozen_param_shapes)
|
||||
wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
|
||||
avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
|
||||
print(f'Frozen params: Have {avail_numel} numels to process.')
|
||||
print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
|
||||
|
||||
total_params = 0
|
||||
total_numel = 0
|
||||
for name, shape in frozen_param_shapes.items():
|
||||
total_params += 1
|
||||
unpartitioned_numel = shape.numel()
|
||||
total_numel += unpartitioned_numel
|
||||
|
||||
state_dict[name] = frozen_param_fragments[name]
|
||||
|
||||
if debug:
|
||||
print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
|
||||
|
||||
print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
|
||||
|
||||
|
||||
def _has_callable(obj, fn):
|
||||
attr = getattr(obj, fn, None)
|
||||
return callable(attr)
|
||||
|
||||
|
||||
def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
|
||||
param_shapes = zero_model_states[0].param_shapes
|
||||
|
||||
# Reconstruction protocol:
|
||||
#
|
||||
# XXX: document this
|
||||
|
||||
if debug:
|
||||
for i in range(world_size):
|
||||
for j in range(len(fp32_flat_groups[0])):
|
||||
print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
|
||||
|
||||
# XXX: memory usage doubles here (zero2)
|
||||
num_param_groups = len(fp32_flat_groups[0])
|
||||
merged_single_partition_of_fp32_groups = []
|
||||
for i in range(num_param_groups):
|
||||
merged_partitions = [sd[i] for sd in fp32_flat_groups]
|
||||
full_single_fp32_vector = torch.cat(merged_partitions, 0)
|
||||
merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
|
||||
avail_numel = sum(
|
||||
[full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
|
||||
|
||||
if debug:
|
||||
wanted_params = sum([len(shapes) for shapes in param_shapes])
|
||||
wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
|
||||
# not asserting if there is a mismatch due to possible padding
|
||||
print(f"Have {avail_numel} numels to process.")
|
||||
print(f"Need {wanted_numel} numels in {wanted_params} params.")
|
||||
|
||||
# params
|
||||
# XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
|
||||
# out-of-core computing solution
|
||||
total_numel = 0
|
||||
total_params = 0
|
||||
for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
|
||||
offset = 0
|
||||
avail_numel = full_single_fp32_vector.numel()
|
||||
for name, shape in shapes.items():
|
||||
|
||||
unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
|
||||
total_numel += unpartitioned_numel
|
||||
total_params += 1
|
||||
|
||||
if debug:
|
||||
print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
|
||||
state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
|
||||
offset += unpartitioned_numel
|
||||
|
||||
# Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
|
||||
# avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
|
||||
# paddings performed in the code it's almost impossible to predict the exact numbers w/o the
|
||||
# live optimizer object, so we are checking that the numbers are within the right range
|
||||
align_to = 2 * world_size
|
||||
|
||||
def zero2_align(x):
|
||||
return align_to * math.ceil(x / align_to)
|
||||
|
||||
if debug:
|
||||
print(f"original offset={offset}, avail_numel={avail_numel}")
|
||||
|
||||
offset = zero2_align(offset)
|
||||
avail_numel = zero2_align(avail_numel)
|
||||
|
||||
if debug:
|
||||
print(f"aligned offset={offset}, avail_numel={avail_numel}")
|
||||
|
||||
# Sanity check
|
||||
if offset != avail_numel:
|
||||
raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
|
||||
|
||||
print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
|
||||
|
||||
|
||||
def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
||||
exclude_frozen_parameters):
|
||||
state_dict = OrderedDict()
|
||||
|
||||
# buffers
|
||||
buffers = zero_model_states[0].buffers
|
||||
state_dict.update(buffers)
|
||||
if debug:
|
||||
print(f"added {len(buffers)} buffers")
|
||||
|
||||
if not exclude_frozen_parameters:
|
||||
_zero2_merge_frozen_params(state_dict, zero_model_states)
|
||||
|
||||
_zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
|
||||
|
||||
# recover shared parameters
|
||||
for pair in zero_model_states[0].shared_params:
|
||||
if pair[1] in state_dict:
|
||||
state_dict[pair[0]] = state_dict[pair[1]]
|
||||
|
||||
return state_dict
|
||||
|
||||
|
||||
def zero3_partitioned_param_info(unpartitioned_numel, world_size):
|
||||
remainder = unpartitioned_numel % world_size
|
||||
padding_numel = (world_size - remainder) if remainder else 0
|
||||
partitioned_numel = math.ceil(unpartitioned_numel / world_size)
|
||||
return partitioned_numel, padding_numel
|
||||
|
||||
|
||||
def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
|
||||
if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
|
||||
return
|
||||
|
||||
if debug:
|
||||
for i in range(world_size):
|
||||
num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
|
||||
print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
|
||||
|
||||
frozen_param_shapes = zero_model_states[0].frozen_param_shapes
|
||||
wanted_params = len(frozen_param_shapes)
|
||||
wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
|
||||
avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
|
||||
print(f'Frozen params: Have {avail_numel} numels to process.')
|
||||
print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
|
||||
|
||||
total_params = 0
|
||||
total_numel = 0
|
||||
for name, shape in zero_model_states[0].frozen_param_shapes.items():
|
||||
total_params += 1
|
||||
unpartitioned_numel = shape.numel()
|
||||
total_numel += unpartitioned_numel
|
||||
|
||||
param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
|
||||
state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
|
||||
|
||||
partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
|
||||
|
||||
if debug:
|
||||
print(
|
||||
f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
|
||||
)
|
||||
|
||||
print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
|
||||
|
||||
|
||||
class GatheredTensor:
|
||||
"""
|
||||
A pseudo tensor that collects partitioned weights.
|
||||
It is more memory efficient when there are multiple groups.
|
||||
"""
|
||||
|
||||
def __init__(self, flat_groups, flat_groups_offset, offset, partitioned_numel, shape):
|
||||
self.flat_groups = flat_groups
|
||||
self.flat_groups_offset = flat_groups_offset
|
||||
self.offset = offset
|
||||
self.partitioned_numel = partitioned_numel
|
||||
self.shape = shape
|
||||
self.dtype = self.flat_groups[0][0].dtype
|
||||
|
||||
def contiguous(self):
|
||||
"""
|
||||
Merge partitioned weights from flat_groups into a single tensor.
|
||||
"""
|
||||
end_idx = self.offset + self.partitioned_numel
|
||||
world_size = len(self.flat_groups)
|
||||
pad_flat_param_chunks = []
|
||||
|
||||
for rank_i in range(world_size):
|
||||
# for each rank, we need to collect weights from related group/groups
|
||||
flat_groups_at_rank_i = self.flat_groups[rank_i]
|
||||
start_group_id = None
|
||||
end_group_id = None
|
||||
for group_id in range(len(self.flat_groups_offset)):
|
||||
if self.flat_groups_offset[group_id] <= self.offset < self.flat_groups_offset[group_id + 1]:
|
||||
start_group_id = group_id
|
||||
if self.flat_groups_offset[group_id] < end_idx <= self.flat_groups_offset[group_id + 1]:
|
||||
end_group_id = group_id
|
||||
break
|
||||
# collect weights from related group/groups
|
||||
for group_id in range(start_group_id, end_group_id + 1):
|
||||
flat_tensor = flat_groups_at_rank_i[group_id]
|
||||
start_offset = self.offset - self.flat_groups_offset[group_id]
|
||||
end_offset = min(end_idx, self.flat_groups_offset[group_id + 1]) - self.flat_groups_offset[group_id]
|
||||
pad_flat_param_chunks.append(flat_tensor[start_offset:end_offset])
|
||||
|
||||
# collect weights from all ranks
|
||||
pad_flat_param = torch.cat(pad_flat_param_chunks, dim=0)
|
||||
param = pad_flat_param[:self.shape.numel()].view(self.shape).contiguous()
|
||||
return param
|
||||
|
||||
|
||||
def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
|
||||
param_shapes = zero_model_states[0].param_shapes
|
||||
avail_numel = sum([flat_group.numel() for flat_group in fp32_flat_groups[0]]) * world_size
|
||||
|
||||
# Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
|
||||
# param, re-consolidating each param, while dealing with padding if any
|
||||
|
||||
# merge list of dicts, preserving order
|
||||
param_shapes = {k: v for d in param_shapes for k, v in d.items()}
|
||||
|
||||
if debug:
|
||||
for i in range(world_size):
|
||||
print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
|
||||
|
||||
wanted_params = len(param_shapes)
|
||||
wanted_numel = sum(shape.numel() for shape in param_shapes.values())
|
||||
# not asserting if there is a mismatch due to possible padding
|
||||
avail_numel = fp32_flat_groups[0].numel() * world_size
|
||||
print(f"Trainable params: Have {avail_numel} numels to process.")
|
||||
print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
|
||||
|
||||
# params
|
||||
# XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
|
||||
# out-of-core computing solution
|
||||
offset = 0
|
||||
total_numel = 0
|
||||
total_params = 0
|
||||
flat_groups_offset = [0] + list(np.cumsum([flat_tensor.numel() for flat_tensor in fp32_flat_groups[0]]))
|
||||
for name, shape in tqdm(param_shapes.items(), desc='Gathering sharded weights'):
|
||||
unpartitioned_numel = shape.numel()
|
||||
total_numel += unpartitioned_numel
|
||||
total_params += 1
|
||||
partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
|
||||
|
||||
if debug:
|
||||
print(
|
||||
f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
|
||||
)
|
||||
|
||||
# memory efficient tensor
|
||||
tensor = GatheredTensor(fp32_flat_groups, flat_groups_offset, offset, partitioned_numel, shape)
|
||||
state_dict[name] = tensor
|
||||
offset += partitioned_numel
|
||||
|
||||
offset *= world_size
|
||||
|
||||
# Sanity check
|
||||
if offset != avail_numel:
|
||||
raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
|
||||
|
||||
print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
|
||||
|
||||
|
||||
def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
||||
exclude_frozen_parameters):
|
||||
state_dict = OrderedDict()
|
||||
|
||||
# buffers
|
||||
buffers = zero_model_states[0].buffers
|
||||
state_dict.update(buffers)
|
||||
if debug:
|
||||
print(f"added {len(buffers)} buffers")
|
||||
|
||||
if not exclude_frozen_parameters:
|
||||
_zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
|
||||
|
||||
_zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
|
||||
|
||||
# recover shared parameters
|
||||
for pair in zero_model_states[0].shared_params:
|
||||
if pair[1] in state_dict:
|
||||
state_dict[pair[0]] = state_dict[pair[1]]
|
||||
|
||||
return state_dict
|
||||
|
||||
|
||||
def to_torch_tensor(state_dict, return_empty_tensor=False):
|
||||
"""
|
||||
Convert state_dict of GatheredTensor to torch tensor
|
||||
"""
|
||||
torch_state_dict = {}
|
||||
converted_tensors = {}
|
||||
for name, tensor in state_dict.items():
|
||||
tensor_id = id(tensor)
|
||||
if tensor_id in converted_tensors: # shared tensors
|
||||
shared_tensor = torch_state_dict[converted_tensors[tensor_id]]
|
||||
torch_state_dict[name] = shared_tensor
|
||||
else:
|
||||
converted_tensors[tensor_id] = name
|
||||
if return_empty_tensor:
|
||||
torch_state_dict[name] = torch.empty(tensor.shape, dtype=tensor.dtype)
|
||||
else:
|
||||
torch_state_dict[name] = tensor.contiguous()
|
||||
return torch_state_dict
|
||||
|
||||
|
||||
def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
|
||||
tag=None,
|
||||
exclude_frozen_parameters=False,
|
||||
lazy_mode=False):
|
||||
"""
|
||||
Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
|
||||
``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
|
||||
via a model hub.
|
||||
|
||||
Args:
|
||||
- ``checkpoint_dir``: path to the desired checkpoint folder
|
||||
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
|
||||
- ``exclude_frozen_parameters``: exclude frozen parameters
|
||||
- ``lazy_mode``: get state_dict in lazy mode. It returns a dict of pesduo tensor instead of torch tensor, which is more memory efficient.
|
||||
Convert the pesduo tensor to torch tensor by ``.contiguous()``
|
||||
|
||||
Returns:
|
||||
- pytorch ``state_dict``
|
||||
|
||||
A typical usage might be ::
|
||||
|
||||
from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
|
||||
# do the training and checkpoint saving
|
||||
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
|
||||
model = model.cpu() # move to cpu
|
||||
model.load_state_dict(state_dict)
|
||||
# submit to model hub or save the model to share with others
|
||||
|
||||
In this example the ``model`` will no longer be usable in the deepspeed context of the same
|
||||
application. i.e. you will need to re-initialize the deepspeed engine, since
|
||||
``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
|
||||
|
||||
If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
|
||||
|
||||
Note: the above usage may not work if your application doesn't have sufficient free CPU memory.
|
||||
You may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
|
||||
the checkpoint. Or you can load state_dict in lazy mode ::
|
||||
|
||||
from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
|
||||
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, lazy_mode=True) # not on cpu
|
||||
for name, lazy_tensor in state_dict.item():
|
||||
tensor = lazy_tensor.contiguous() # to cpu
|
||||
print(name, tensor)
|
||||
# del tensor to release memory if it no longer in use
|
||||
"""
|
||||
if tag is None:
|
||||
latest_path = os.path.join(checkpoint_dir, 'latest')
|
||||
if os.path.isfile(latest_path):
|
||||
with open(latest_path, 'r') as fd:
|
||||
tag = fd.read().strip()
|
||||
else:
|
||||
raise ValueError(f"Unable to find 'latest' file at {latest_path}")
|
||||
|
||||
ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
|
||||
|
||||
if not os.path.isdir(ds_checkpoint_dir):
|
||||
raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
|
||||
|
||||
state_dict = _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
|
||||
if lazy_mode:
|
||||
return state_dict
|
||||
else:
|
||||
return to_torch_tensor(state_dict)
|
||||
|
||||
|
||||
def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir,
|
||||
output_dir,
|
||||
max_shard_size="5GB",
|
||||
safe_serialization=False,
|
||||
tag=None,
|
||||
exclude_frozen_parameters=False):
|
||||
"""
|
||||
Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
|
||||
loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
|
||||
|
||||
Args:
|
||||
- ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
|
||||
- ``output_dir``: directory to the pytorch fp32 state_dict output files
|
||||
- ``max_shard_size``: the maximum size for a checkpoint before being sharded, default value is 5GB
|
||||
- ``safe_serialization``: whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).
|
||||
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
|
||||
- ``exclude_frozen_parameters``: exclude frozen parameters
|
||||
"""
|
||||
|
||||
# Dependency pre-check
|
||||
if safe_serialization:
|
||||
try:
|
||||
from safetensors.torch import save_file
|
||||
except ImportError:
|
||||
print('If you want to use `safe_serialization`, please `pip install safetensors`')
|
||||
raise
|
||||
if max_shard_size is not None:
|
||||
try:
|
||||
from huggingface_hub import split_torch_state_dict_into_shards
|
||||
except ImportError:
|
||||
print('If you want to use `max_shard_size`, please `pip install huggingface_hub`')
|
||||
raise
|
||||
|
||||
# Convert zero checkpoint to state_dict
|
||||
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
|
||||
tag,
|
||||
exclude_frozen_parameters,
|
||||
lazy_mode=True)
|
||||
|
||||
# Shard the model if it is too big.
|
||||
weights_name = "model.safetensors" if safe_serialization else "pytorch_model.bin"
|
||||
if max_shard_size is not None:
|
||||
filename_pattern = weights_name.replace(".bin", "{suffix}.bin").replace(".safetensors", "{suffix}.safetensors")
|
||||
# an memory-efficient approach for sharding
|
||||
empty_state_dict = to_torch_tensor(state_dict, return_empty_tensor=True)
|
||||
state_dict_split = split_torch_state_dict_into_shards(empty_state_dict,
|
||||
filename_pattern=filename_pattern,
|
||||
max_shard_size=max_shard_size)
|
||||
else:
|
||||
from collections import namedtuple
|
||||
StateDictSplit = namedtuple("StateDictSplit", ["is_sharded", "filename_to_tensors"])
|
||||
state_dict_split = StateDictSplit(is_sharded=False,
|
||||
filename_to_tensors={weights_name: list(state_dict.keys())})
|
||||
|
||||
# Save the model by shard
|
||||
os.makedirs(output_dir, exist_ok=True)
|
||||
filename_to_tensors = state_dict_split.filename_to_tensors.items()
|
||||
for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"):
|
||||
shard_state_dict = {tensor_name: state_dict[tensor_name] for tensor_name in tensors}
|
||||
shard_state_dict = to_torch_tensor(shard_state_dict)
|
||||
output_path = os.path.join(output_dir, shard_file)
|
||||
if safe_serialization:
|
||||
save_file(shard_state_dict, output_path, metadata={"format": "pt"})
|
||||
else:
|
||||
torch.save(shard_state_dict, output_path)
|
||||
# release the memory of current shard
|
||||
for tensor_name in list(shard_state_dict.keys()):
|
||||
del state_dict[tensor_name]
|
||||
del shard_state_dict[tensor_name]
|
||||
del shard_state_dict
|
||||
gc.collect()
|
||||
|
||||
# Save index if sharded
|
||||
if state_dict_split.is_sharded:
|
||||
index = {
|
||||
"metadata": state_dict_split.metadata,
|
||||
"weight_map": state_dict_split.tensor_to_filename,
|
||||
}
|
||||
save_index_file = "model.safetensors.index.json" if safe_serialization else "pytorch_model.bin.index.json"
|
||||
save_index_file = os.path.join(output_dir, save_index_file)
|
||||
with open(save_index_file, "w", encoding="utf-8") as f:
|
||||
content = json.dumps(index, indent=2, sort_keys=True) + "\n"
|
||||
f.write(content)
|
||||
|
||||
|
||||
def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
|
||||
"""
|
||||
1. Put the provided model to cpu
|
||||
2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
|
||||
3. Load it into the provided model
|
||||
|
||||
Args:
|
||||
- ``model``: the model object to update
|
||||
- ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
|
||||
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
|
||||
|
||||
Returns:
|
||||
- ``model`: modified model
|
||||
|
||||
Make sure you have plenty of CPU memory available before you call this function. If you don't
|
||||
have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
|
||||
conveniently placed for you in the checkpoint folder.
|
||||
|
||||
A typical usage might be ::
|
||||
|
||||
from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
|
||||
model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
|
||||
# submit to model hub or save the model to share with others
|
||||
|
||||
Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
|
||||
of the same application. i.e. you will need to re-initialize the deepspeed engine, since
|
||||
``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
|
||||
|
||||
"""
|
||||
logger.info(f"Extracting fp32 weights")
|
||||
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
|
||||
|
||||
logger.info(f"Overwriting model with fp32 weights")
|
||||
model = model.cpu()
|
||||
model.load_state_dict(state_dict, strict=False)
|
||||
|
||||
return model
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
parser = argparse.ArgumentParser()
|
||||
parser.add_argument("checkpoint_dir",
|
||||
type=str,
|
||||
help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
|
||||
parser.add_argument("output_dir",
|
||||
type=str,
|
||||
help="directory to the pytorch fp32 state_dict output files"
|
||||
"(e.g. path/checkpoint-12-output/)")
|
||||
parser.add_argument(
|
||||
"--max_shard_size",
|
||||
type=str,
|
||||
default="5GB",
|
||||
help="The maximum size for a checkpoint before being sharded. Checkpoints shard will then be each of size"
|
||||
"lower than this size. If expressed as a string, needs to be digits followed by a unit (like `5MB`"
|
||||
"We default it to 5GB in order for models to be able to run easily on free-tier google colab instances"
|
||||
"without CPU OOM issues.")
|
||||
parser.add_argument(
|
||||
"--safe_serialization",
|
||||
default=False,
|
||||
action='store_true',
|
||||
help="Whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).")
|
||||
parser.add_argument("-t",
|
||||
"--tag",
|
||||
type=str,
|
||||
default=None,
|
||||
help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
|
||||
parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
|
||||
parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
|
||||
args = parser.parse_args()
|
||||
|
||||
debug = args.debug
|
||||
|
||||
convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
|
||||
args.output_dir,
|
||||
max_shard_size=args.max_shard_size,
|
||||
safe_serialization=args.safe_serialization,
|
||||
tag=args.tag,
|
||||
exclude_frozen_parameters=args.exclude_frozen_parameters)
|
||||
@@ -0,0 +1,202 @@
|
||||
---
|
||||
base_model: meta-llama/Llama-3.1-8B-Instruct
|
||||
library_name: peft
|
||||
---
|
||||
|
||||
# Model Card for Model ID
|
||||
|
||||
<!-- Provide a quick summary of what the model is/does. -->
|
||||
|
||||
|
||||
|
||||
## Model Details
|
||||
|
||||
### Model Description
|
||||
|
||||
<!-- Provide a longer summary of what this model is. -->
|
||||
|
||||
|
||||
|
||||
- **Developed by:** [More Information Needed]
|
||||
- **Funded by [optional]:** [More Information Needed]
|
||||
- **Shared by [optional]:** [More Information Needed]
|
||||
- **Model type:** [More Information Needed]
|
||||
- **Language(s) (NLP):** [More Information Needed]
|
||||
- **License:** [More Information Needed]
|
||||
- **Finetuned from model [optional]:** [More Information Needed]
|
||||
|
||||
### Model Sources [optional]
|
||||
|
||||
<!-- Provide the basic links for the model. -->
|
||||
|
||||
- **Repository:** [More Information Needed]
|
||||
- **Paper [optional]:** [More Information Needed]
|
||||
- **Demo [optional]:** [More Information Needed]
|
||||
|
||||
## Uses
|
||||
|
||||
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
||||
|
||||
### Direct Use
|
||||
|
||||
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Downstream Use [optional]
|
||||
|
||||
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Out-of-Scope Use
|
||||
|
||||
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Bias, Risks, and Limitations
|
||||
|
||||
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Recommendations
|
||||
|
||||
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
||||
|
||||
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
||||
|
||||
## How to Get Started with the Model
|
||||
|
||||
Use the code below to get started with the model.
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Training Details
|
||||
|
||||
### Training Data
|
||||
|
||||
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Training Procedure
|
||||
|
||||
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
||||
|
||||
#### Preprocessing [optional]
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
|
||||
#### Training Hyperparameters
|
||||
|
||||
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
||||
|
||||
#### Speeds, Sizes, Times [optional]
|
||||
|
||||
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Evaluation
|
||||
|
||||
<!-- This section describes the evaluation protocols and provides the results. -->
|
||||
|
||||
### Testing Data, Factors & Metrics
|
||||
|
||||
#### Testing Data
|
||||
|
||||
<!-- This should link to a Dataset Card if possible. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Factors
|
||||
|
||||
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Metrics
|
||||
|
||||
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Results
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Summary
|
||||
|
||||
|
||||
|
||||
## Model Examination [optional]
|
||||
|
||||
<!-- Relevant interpretability work for the model goes here -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Environmental Impact
|
||||
|
||||
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
||||
|
||||
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
||||
|
||||
- **Hardware Type:** [More Information Needed]
|
||||
- **Hours used:** [More Information Needed]
|
||||
- **Cloud Provider:** [More Information Needed]
|
||||
- **Compute Region:** [More Information Needed]
|
||||
- **Carbon Emitted:** [More Information Needed]
|
||||
|
||||
## Technical Specifications [optional]
|
||||
|
||||
### Model Architecture and Objective
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Compute Infrastructure
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Hardware
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Software
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Citation [optional]
|
||||
|
||||
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
||||
|
||||
**BibTeX:**
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
**APA:**
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Glossary [optional]
|
||||
|
||||
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## More Information [optional]
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Model Card Authors [optional]
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Model Card Contact
|
||||
|
||||
[More Information Needed]
|
||||
### Framework versions
|
||||
|
||||
- PEFT 0.15.2
|
||||
@@ -0,0 +1,41 @@
|
||||
{
|
||||
"alpha_pattern": {},
|
||||
"auto_mapping": null,
|
||||
"base_model_name_or_path": "meta-llama/Llama-3.1-8B-Instruct",
|
||||
"bias": "none",
|
||||
"corda_config": null,
|
||||
"eva_config": null,
|
||||
"exclude_modules": null,
|
||||
"fan_in_fan_out": false,
|
||||
"inference_mode": true,
|
||||
"init_lora_weights": true,
|
||||
"layer_replication": null,
|
||||
"layers_pattern": null,
|
||||
"layers_to_transform": null,
|
||||
"loftq_config": {},
|
||||
"lora_alpha": 256,
|
||||
"lora_bias": false,
|
||||
"lora_dropout": 0.0,
|
||||
"megatron_config": null,
|
||||
"megatron_core": "megatron.core",
|
||||
"modules_to_save": null,
|
||||
"peft_type": "LORA",
|
||||
"r": 128,
|
||||
"rank_pattern": {},
|
||||
"revision": null,
|
||||
"target_modules": [
|
||||
"o_proj",
|
||||
"up_proj",
|
||||
"k_proj",
|
||||
"down_proj",
|
||||
"lm_head",
|
||||
"gate_proj",
|
||||
"q_proj",
|
||||
"v_proj",
|
||||
"embed_tokens"
|
||||
],
|
||||
"task_type": "CAUSAL_LM",
|
||||
"trainable_token_indices": null,
|
||||
"use_dora": false,
|
||||
"use_rslora": false
|
||||
}
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:4bd29fb1491cd9b49c1777d5988599c3924f25c6c7e8d5c317b0ed6c601ec3cd
|
||||
size 2840262376
|
||||
@@ -0,0 +1 @@
|
||||
global_step2000
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:f0c14f1707bc469889a7b9cd36b1e660bcca25c2b8e8250d963da334e69124b2
|
||||
size 14960
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:7049414d5e03ef7ee044d313686cf89839b376c348f3aa943a90ba79cdcb2446
|
||||
size 14960
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:e2a77d4e4f6fb20e6cb4eac478df18765a195a5be58f610b86c760bf2759ecb4
|
||||
size 14960
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:4479886ea2ad9eb835c1e7ebe109dad86bf462b6dca37ed2df470ed52feceb57
|
||||
size 14960
|
||||
@@ -0,0 +1,16 @@
|
||||
{
|
||||
"bos_token": {
|
||||
"content": "<|begin_of_text|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "<|eot_id|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
BIN
lora-embedding-128-llama3.1-8b-malaysian-8k/checkpoint-2000/tokenizer.json
(Stored with Git LFS)
Normal file
BIN
lora-embedding-128-llama3.1-8b-malaysian-8k/checkpoint-2000/tokenizer.json
(Stored with Git LFS)
Normal file
Binary file not shown.
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user