初始化项目，由ModelHub XC社区提供模型
Model: abhinand/TinyLlama-1.1B-OpenHermes-2.5-Chat-v0.1-sft Source: Original Platform
This commit is contained in:
ModelHub XC
35
.gitattributes
vendored
Normal file
35
.gitattributes
vendored
Normal file
@@ -0,0 +1,35 @@
|
||||
*.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
|
||||
263
README.md
Normal file
263
README.md
Normal file
@@ -0,0 +1,263 @@
|
||||
---
|
||||
language:
|
||||
- en
|
||||
license: apache-2.0
|
||||
datasets:
|
||||
- teknium/OpenHermes-2.5
|
||||
- abhinand/ultrachat_200k_sharegpt
|
||||
model-index:
|
||||
- name: TinyLlama-1.1B-OpenHermes-2.5-Chat-v0.1-sft
|
||||
results:
|
||||
- task:
|
||||
type: text-generation
|
||||
name: Text Generation
|
||||
dataset:
|
||||
name: AI2 Reasoning Challenge (25-Shot)
|
||||
type: ai2_arc
|
||||
config: ARC-Challenge
|
||||
split: test
|
||||
args:
|
||||
num_few_shot: 25
|
||||
metrics:
|
||||
- type: acc_norm
|
||||
value: 33.79
|
||||
name: normalized accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=abhinand/TinyLlama-1.1B-OpenHermes-2.5-Chat-v0.1-sft
|
||||
name: Open LLM Leaderboard
|
||||
- task:
|
||||
type: text-generation
|
||||
name: Text Generation
|
||||
dataset:
|
||||
name: HellaSwag (10-Shot)
|
||||
type: hellaswag
|
||||
split: validation
|
||||
args:
|
||||
num_few_shot: 10
|
||||
metrics:
|
||||
- type: acc_norm
|
||||
value: 58.72
|
||||
name: normalized accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=abhinand/TinyLlama-1.1B-OpenHermes-2.5-Chat-v0.1-sft
|
||||
name: Open LLM Leaderboard
|
||||
- task:
|
||||
type: text-generation
|
||||
name: Text Generation
|
||||
dataset:
|
||||
name: MMLU (5-Shot)
|
||||
type: cais/mmlu
|
||||
config: all
|
||||
split: test
|
||||
args:
|
||||
num_few_shot: 5
|
||||
metrics:
|
||||
- type: acc
|
||||
value: 24.52
|
||||
name: accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=abhinand/TinyLlama-1.1B-OpenHermes-2.5-Chat-v0.1-sft
|
||||
name: Open LLM Leaderboard
|
||||
- task:
|
||||
type: text-generation
|
||||
name: Text Generation
|
||||
dataset:
|
||||
name: TruthfulQA (0-shot)
|
||||
type: truthful_qa
|
||||
config: multiple_choice
|
||||
split: validation
|
||||
args:
|
||||
num_few_shot: 0
|
||||
metrics:
|
||||
- type: mc2
|
||||
value: 36.22
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=abhinand/TinyLlama-1.1B-OpenHermes-2.5-Chat-v0.1-sft
|
||||
name: Open LLM Leaderboard
|
||||
- task:
|
||||
type: text-generation
|
||||
name: Text Generation
|
||||
dataset:
|
||||
name: Winogrande (5-shot)
|
||||
type: winogrande
|
||||
config: winogrande_xl
|
||||
split: validation
|
||||
args:
|
||||
num_few_shot: 5
|
||||
metrics:
|
||||
- type: acc
|
||||
value: 60.93
|
||||
name: accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=abhinand/TinyLlama-1.1B-OpenHermes-2.5-Chat-v0.1-sft
|
||||
name: Open LLM Leaderboard
|
||||
- task:
|
||||
type: text-generation
|
||||
name: Text Generation
|
||||
dataset:
|
||||
name: GSM8k (5-shot)
|
||||
type: gsm8k
|
||||
config: main
|
||||
split: test
|
||||
args:
|
||||
num_few_shot: 5
|
||||
metrics:
|
||||
- type: acc
|
||||
value: 5.38
|
||||
name: accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=abhinand/TinyLlama-1.1B-OpenHermes-2.5-Chat-v0.1-sft
|
||||
name: Open LLM Leaderboard
|
||||
---
|
||||
|
||||
# TinyLLaMA OpenHermes2.5 [Work in Progress]
|
||||
|
||||
This a finetune of TinyLLaMA base model finetuned on [OpenHermes 2.5](https://huggingface.co/datasets/teknium/OpenHermes-2.5) and [UltraChat 200k](https://huggingface.co/datasets/abhinand/ultrachat_200k_sharegpt) for a single epoch.
|
||||
|
||||
Training was generously supported by [Jarvislabs.ai](https://jarvislabs.ai/).
|
||||
|
||||
If you appreciate this work and would like to support its continued development, consider [buying me a coffee](https://www.buymeacoffee.com/abhinand.b). Your support is invaluable and greatly appreciated.
|
||||
|
||||
[](https://www.buymeacoffee.com/abhinand.b)
|
||||
|
||||
<details><summary>See axolotl config</summary>
|
||||
|
||||
axolotl version: `0.4.0`
|
||||
```yaml
|
||||
base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
|
||||
model_type: AutoModelForCausalLM
|
||||
tokenizer_type: AutoTokenizer
|
||||
trust_remote_code: true
|
||||
is_llama_derived_model: true
|
||||
|
||||
# huggingface repo
|
||||
datasets:
|
||||
- path: teknium/OpenHermes-2.5
|
||||
type: sharegpt
|
||||
conversation: chatml
|
||||
train_on_split: train
|
||||
|
||||
- path: abhinand/ultrachat_200k_sharegpt
|
||||
type: sharegpt
|
||||
conversation: chatml
|
||||
train_on_split: train
|
||||
|
||||
load_in_4bit: false
|
||||
load_in_8bit: false
|
||||
bf16: true # require >=ampere
|
||||
chat_template: chatml
|
||||
|
||||
dataset_prepared_path: last_run_prepared_path
|
||||
hub_model_id: abhinand/TinyLlama-1.1B-OpenHermes-2.5-Chat-v1.0
|
||||
group_by_length: false
|
||||
|
||||
val_set_size: 0.0
|
||||
sequence_len: 2048
|
||||
sample_packing: true
|
||||
pad_to_sequence_len: true
|
||||
|
||||
adapter: lora
|
||||
lora_model_dir:
|
||||
lora_r: 32
|
||||
lora_alpha: 16
|
||||
lora_target_modules:
|
||||
- q_proj
|
||||
- v_proj
|
||||
- k_proj
|
||||
- o_proj
|
||||
- gate_proj
|
||||
- down_proj
|
||||
- up_proj
|
||||
lora_modules_to_save:
|
||||
- embed_tokens
|
||||
- lm_head
|
||||
lora_dropout: 0.05
|
||||
lora_target_linear: true
|
||||
lora_fan_in_fan_out:
|
||||
|
||||
output_dir: /home/tiny-llama/trained_models
|
||||
|
||||
gradient_accumulation_steps: 2
|
||||
micro_batch_size: 32
|
||||
eval_batch_size: 32
|
||||
num_epochs: 1
|
||||
logging_steps: 1
|
||||
save_steps: 50
|
||||
save_total_limit: 3
|
||||
|
||||
save_safetensors: true
|
||||
gradient_checkpointing: true
|
||||
|
||||
lr_scheduler: cosine
|
||||
optimizer: "adamw_bnb_8bit"
|
||||
adam_beta2: 0.95
|
||||
adam_epsilon: 0.00001
|
||||
weight_decay: 0.1
|
||||
learning_rate: 0.0005
|
||||
max_grad_norm: 1.0
|
||||
warmup_ratio: 0.05
|
||||
# warmup_steps: 100
|
||||
|
||||
flash_attention: true
|
||||
|
||||
# Resume from a specific checkpoint dir
|
||||
resume_from_checkpoint:
|
||||
# If resume_from_checkpoint isn't set and you simply want it to start where it left off.
|
||||
# Be careful with this being turned on between different models.
|
||||
# auto_resume_from_checkpoints: true
|
||||
|
||||
# wandb configuration if you're using it
|
||||
# Make sure your `WANDB_API_KEY` environment variable is set (recommended) or you login to wandb with `wandb login`.
|
||||
wandb_mode: # "offline" to save run metadata locally and not sync to the server, "disabled" to turn off wandb
|
||||
wandb_project: "tiny-llama-sft"
|
||||
wandb_name:
|
||||
wandb_run_id:
|
||||
|
||||
special_tokens:
|
||||
bos_token: "<s>"
|
||||
eos_token: "</s>"
|
||||
unk_token: "<unk>"
|
||||
tokens: # these are delimiters
|
||||
- "<|im_start|>"
|
||||
- "<|im_end|>"
|
||||
|
||||
```
|
||||
|
||||
</details>
|
||||
|
||||
## Training procedure
|
||||
|
||||
### Training hyperparameters
|
||||
|
||||
The following hyperparameters were used during training:
|
||||
- learning_rate: 0.0005
|
||||
- train_batch_size: 32
|
||||
- eval_batch_size: 32
|
||||
- seed: 42
|
||||
- gradient_accumulation_steps: 2
|
||||
- total_train_batch_size: 64
|
||||
- optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-05
|
||||
- lr_scheduler_type: cosine
|
||||
- lr_scheduler_warmup_steps: 476
|
||||
- num_epochs: 1
|
||||
|
||||
### Framework versions
|
||||
|
||||
- PEFT 0.8.2
|
||||
- Transformers 4.38.0.dev0
|
||||
- Pytorch 2.0.1
|
||||
- Datasets 2.16.1
|
||||
- Tokenizers 0.15.0
|
||||
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
||||
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_abhinand__TinyLlama-1.1B-OpenHermes-2.5-Chat-v0.1-sft)
|
||||
|
||||
| Metric |Value|
|
||||
|---------------------------------|----:|
|
||||
|Avg. |36.59|
|
||||
|AI2 Reasoning Challenge (25-Shot)|33.79|
|
||||
|HellaSwag (10-Shot) |58.72|
|
||||
|MMLU (5-Shot) |24.52|
|
||||
|TruthfulQA (0-shot) |36.22|
|
||||
|Winogrande (5-shot) |60.93|
|
||||
|GSM8k (5-shot) | 5.38|
|
||||
|
||||
4
added_tokens.json
Normal file
4
added_tokens.json
Normal file
@@ -0,0 +1,4 @@
|
||||
{
|
||||
"<|im_end|>": 32001,
|
||||
"<|im_start|>": 32000
|
||||
}
|
||||
28
config.json
Normal file
28
config.json
Normal file
@@ -0,0 +1,28 @@
|
||||
{
|
||||
"_name_or_path": "TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T",
|
||||
"architectures": [
|
||||
"LlamaForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 2048,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 5632,
|
||||
"max_position_embeddings": 2048,
|
||||
"model_type": "llama",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 22,
|
||||
"num_key_value_heads": 4,
|
||||
"pretraining_tp": 1,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 10000.0,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.38.0.dev0",
|
||||
"use_cache": false,
|
||||
"vocab_size": 32002
|
||||
}
|
||||
8
generation_config.json
Normal file
8
generation_config.json
Normal file
@@ -0,0 +1,8 @@
|
||||
{
|
||||
"bos_token_id": 1,
|
||||
"do_sample": true,
|
||||
"eos_token_id": 2,
|
||||
"max_length": 2048,
|
||||
"pad_token_id": 0,
|
||||
"transformers_version": "4.38.0.dev0"
|
||||
}
|
||||
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:924714002709b79aa64897275f99e6f8c59396c8ec0fc28002fef254c6fc3ea9
|
||||
size 2200136248
|
||||
24
special_tokens_map.json
Normal file
24
special_tokens_map.json
Normal file
@@ -0,0 +1,24 @@
|
||||
{
|
||||
"bos_token": {
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": "</s>",
|
||||
"unk_token": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
93409
tokenizer.json
Normal file
93409
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
BIN
tokenizer.model
(Stored with Git LFS)
Normal file
BIN
tokenizer.model
(Stored with Git LFS)
Normal file
Binary file not shown.
58
tokenizer_config.json
Normal file
58
tokenizer_config.json
Normal file
@@ -0,0 +1,58 @@
|
||||
{
|
||||
"add_bos_token": true,
|
||||
"add_eos_token": false,
|
||||
"added_tokens_decoder": {
|
||||
"0": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"1": {
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"2": {
|
||||
"content": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32000": {
|
||||
"content": "<|im_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"32001": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
}
|
||||
},
|
||||
"bos_token": "<s>",
|
||||
"chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = 'You are a helpful assistant.' %}{% endif %}{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in loop_messages %}{% if loop.index0 == 0 %}{{'<|im_start|>system\n' + system_message + '<|im_end|>\n'}}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "</s>",
|
||||
"legacy": false,
|
||||
"model_max_length": 1000000000000000019884624838656,
|
||||
"pad_token": "</s>",
|
||||
"padding_side": "right",
|
||||
"sp_model_kwargs": {},
|
||||
"tokenizer_class": "LlamaTokenizer",
|
||||
"unk_token": "<unk>",
|
||||
"use_default_system_prompt": false
|
||||
}
|
||||
Reference in New Issue
Block a user