初始化项目，由ModelHub XC社区提供模型
Model: mlabonne/NeuralHermes-2.5-Mistral-7B-laser Source: Original Platform
This commit is contained in:
ModelHub XC
47
.gitattributes
vendored
Normal file
47
.gitattributes
vendored
Normal file
@@ -0,0 +1,47 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 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
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack 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
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* 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
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
||||
*.tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
*.db* filter=lfs diff=lfs merge=lfs -text
|
||||
*.ark* filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.gguf* filter=lfs diff=lfs merge=lfs -text
|
||||
*.ggml filter=lfs diff=lfs merge=lfs -text
|
||||
*.llamafile* filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
268
README.md
Normal file
268
README.md
Normal file
@@ -0,0 +1,268 @@
|
||||
---
|
||||
language:
|
||||
- en
|
||||
license: apache-2.0
|
||||
tags:
|
||||
- mistral
|
||||
- instruct
|
||||
- finetune
|
||||
- chatml
|
||||
- gpt4
|
||||
- synthetic data
|
||||
- distillation
|
||||
- dpo
|
||||
- rlhf
|
||||
- laser
|
||||
datasets:
|
||||
- mlabonne/chatml_dpo_pairs
|
||||
base_model: teknium/OpenHermes-2.5-Mistral-7B
|
||||
model-index:
|
||||
- name: NeuralHermes-2.5-Mistral-7B-laser
|
||||
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: 66.38
|
||||
name: normalized accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/NeuralHermes-2.5-Mistral-7B-laser
|
||||
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: 85.09
|
||||
name: normalized accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/NeuralHermes-2.5-Mistral-7B-laser
|
||||
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: 63.43
|
||||
name: accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/NeuralHermes-2.5-Mistral-7B-laser
|
||||
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: 54.95
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/NeuralHermes-2.5-Mistral-7B-laser
|
||||
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: 78.14
|
||||
name: accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/NeuralHermes-2.5-Mistral-7B-laser
|
||||
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: 55.72
|
||||
name: accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/NeuralHermes-2.5-Mistral-7B-laser
|
||||
name: Open LLM Leaderboard
|
||||
---
|
||||
|
||||
<center><img src="https://i.imgur.com/gUlEJuU.jpeg"></center>
|
||||
|
||||
# NeuralHermes 2.5 - Mistral 7B - LASER
|
||||
|
||||
This is an experimental LASER version of NeuralHermes using [laserRMT](https://github.com/cognitivecomputations/laserRMT), based on [this paper](https://arxiv.org/pdf/2312.13558.pdf).
|
||||
|
||||
| Model |AGIEval|GPT4All|TruthfulQA|Bigbench|Average|
|
||||
|------------------------------------------------------------------------------------------------------|------:|------:|---------:|-------:|------:|
|
||||
|[NeuralHermes-2.5-Mistral-7B-laser](https://huggingface.co/mlabonne/NeuralHermes-2.5-Mistral-7B-laser)| 43.54| 73.44| 55.26| 42.24| 53.62|
|
||||
|[NeuralHermes-2.5-Mistral-7B](https://huggingface.co/mlabonne/NeuralHermes-2.5-Mistral-7B) | 43.67| 73.24| 55.37| 41.76| 53.51|
|
||||
|
||||
Fernando Fernandes Neto and Eric Hartford. "Optimizing Large Language Models Using Layer-Selective Rank Reduction and Random Matrix Theory." 2024.
|
||||
|
||||
NeuralHermes is an [teknium/OpenHermes-2.5-Mistral-7B](https://huggingface.co/teknium/OpenHermes-2.5-Mistral-7B) model that has been further fine-tuned with Direct Preference Optimization (DPO) using the [mlabonne/chatml_dpo_pairs](https://huggingface.co/datasets/mlabonne/chatml_dpo_pairs) dataset. It surpasses the original model on several benchmarks (see results).
|
||||
|
||||
It is directly inspired by the RLHF process described by [Intel/neural-chat-7b-v3-1](https://huggingface.co/Intel/neural-chat-7b-v3-1)'s authors to improve performance. I used the same dataset and reformatted it to apply the ChatML template.
|
||||
|
||||
The code to train this model is available on [Google Colab](https://colab.research.google.com/drive/15iFBr1xWgztXvhrj5I9fBv20c7CFOPBE?usp=sharing) and [GitHub](https://github.com/mlabonne/llm-course/tree/main). It required an A100 GPU for about an hour.
|
||||
|
||||
## Results
|
||||
|
||||
### AGIEval
|
||||
| Task |Version| Metric |Value| |Stderr|
|
||||
|------------------------------|------:|--------|----:|---|-----:|
|
||||
|agieval_aqua_rat | 0|acc |21.26|± | 2.57|
|
||||
| | |acc_norm|22.83|± | 2.64|
|
||||
|agieval_logiqa_en | 0|acc |39.32|± | 1.92|
|
||||
| | |acc_norm|40.71|± | 1.93|
|
||||
|agieval_lsat_ar | 0|acc |25.65|± | 2.89|
|
||||
| | |acc_norm|25.65|± | 2.89|
|
||||
|agieval_lsat_lr | 0|acc |48.82|± | 2.22|
|
||||
| | |acc_norm|50.00|± | 2.22|
|
||||
|agieval_lsat_rc | 0|acc |58.36|± | 3.01|
|
||||
| | |acc_norm|57.25|± | 3.02|
|
||||
|agieval_sat_en | 0|acc |74.27|± | 3.05|
|
||||
| | |acc_norm|73.30|± | 3.09|
|
||||
|agieval_sat_en_without_passage| 0|acc |43.69|± | 3.46|
|
||||
| | |acc_norm|42.23|± | 3.45|
|
||||
|agieval_sat_math | 0|acc |37.27|± | 3.27|
|
||||
| | |acc_norm|36.36|± | 3.25|
|
||||
|
||||
Average: 43.54%
|
||||
|
||||
### GPT4All
|
||||
| Task |Version| Metric |Value| |Stderr|
|
||||
|-------------|------:|--------|----:|---|-----:|
|
||||
|arc_challenge| 0|acc |57.76|± | 1.44|
|
||||
| | |acc_norm|60.32|± | 1.43|
|
||||
|arc_easy | 0|acc |83.84|± | 0.76|
|
||||
| | |acc_norm|81.10|± | 0.80|
|
||||
|boolq | 1|acc |86.70|± | 0.59|
|
||||
|hellaswag | 0|acc |63.15|± | 0.48|
|
||||
| | |acc_norm|82.55|± | 0.38|
|
||||
|openbookqa | 0|acc |34.40|± | 2.13|
|
||||
| | |acc_norm|45.20|± | 2.23|
|
||||
|piqa | 0|acc |81.94|± | 0.90|
|
||||
| | |acc_norm|82.97|± | 0.88|
|
||||
|winogrande | 0|acc |75.22|± | 1.21|
|
||||
|
||||
Average: 73.44%
|
||||
|
||||
### TruthfulQA
|
||||
| Task |Version|Metric|Value| |Stderr|
|
||||
|-------------|------:|------|----:|---|-----:|
|
||||
|truthfulqa_mc| 1|mc1 |37.70|± | 1.70|
|
||||
| | |mc2 |55.26|± | 1.52|
|
||||
|
||||
Average: 55.26%
|
||||
|
||||
### Bigbench
|
||||
| Task |Version| Metric |Value| |Stderr|
|
||||
|------------------------------------------------|------:|---------------------|----:|---|-----:|
|
||||
|bigbench_causal_judgement | 0|multiple_choice_grade|53.16|± | 3.63|
|
||||
|bigbench_date_understanding | 0|multiple_choice_grade|65.31|± | 2.48|
|
||||
|bigbench_disambiguation_qa | 0|multiple_choice_grade|34.11|± | 2.96|
|
||||
|bigbench_geometric_shapes | 0|multiple_choice_grade|27.02|± | 2.35|
|
||||
| | |exact_str_match | 0.28|± | 0.28|
|
||||
|bigbench_logical_deduction_five_objects | 0|multiple_choice_grade|27.80|± | 2.01|
|
||||
|bigbench_logical_deduction_seven_objects | 0|multiple_choice_grade|19.86|± | 1.51|
|
||||
|bigbench_logical_deduction_three_objects | 0|multiple_choice_grade|48.33|± | 2.89|
|
||||
|bigbench_movie_recommendation | 0|multiple_choice_grade|41.40|± | 2.20|
|
||||
|bigbench_navigate | 0|multiple_choice_grade|50.00|± | 1.58|
|
||||
|bigbench_reasoning_about_colored_objects | 0|multiple_choice_grade|65.00|± | 1.07|
|
||||
|bigbench_ruin_names | 0|multiple_choice_grade|46.21|± | 2.36|
|
||||
|bigbench_salient_translation_error_detection | 0|multiple_choice_grade|27.25|± | 1.41|
|
||||
|bigbench_snarks | 0|multiple_choice_grade|70.72|± | 3.39|
|
||||
|bigbench_sports_understanding | 0|multiple_choice_grade|65.72|± | 1.51|
|
||||
|bigbench_temporal_sequences | 0|multiple_choice_grade|30.40|± | 1.46|
|
||||
|bigbench_tracking_shuffled_objects_five_objects | 0|multiple_choice_grade|22.56|± | 1.18|
|
||||
|bigbench_tracking_shuffled_objects_seven_objects| 0|multiple_choice_grade|17.09|± | 0.90|
|
||||
|bigbench_tracking_shuffled_objects_three_objects| 0|multiple_choice_grade|48.33|± | 2.89|
|
||||
|
||||
Average: 42.24%
|
||||
|
||||
Average score: 53.62%
|
||||
|
||||
## Usage
|
||||
|
||||
You can run this model using [LM Studio](https://lmstudio.ai/) or any other frontend.
|
||||
|
||||
You can also run this model using the following code:
|
||||
|
||||
```python
|
||||
import transformers
|
||||
from transformers import AutoTokenizer
|
||||
|
||||
# Format prompt
|
||||
message = [
|
||||
{"role": "system", "content": "You are a helpful assistant chatbot."},
|
||||
{"role": "user", "content": "What is a Large Language Model?"}
|
||||
]
|
||||
tokenizer = AutoTokenizer.from_pretrained(new_model)
|
||||
prompt = tokenizer.apply_chat_template(message, add_generation_prompt=True, tokenize=False)
|
||||
|
||||
# Create pipeline
|
||||
pipeline = transformers.pipeline(
|
||||
"text-generation",
|
||||
model="mlabonne/NeuralHermes-2.5-Mistral-7B-laser",
|
||||
tokenizer=tokenizer
|
||||
)
|
||||
|
||||
# Generate text
|
||||
sequences = pipeline(
|
||||
prompt,
|
||||
do_sample=True,
|
||||
temperature=0.7,
|
||||
top_p=0.9,
|
||||
num_return_sequences=1,
|
||||
max_length=200,
|
||||
)
|
||||
print(sequences[0]['generated_text'])
|
||||
```
|
||||
# [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_mlabonne__NeuralHermes-2.5-Mistral-7B-laser)
|
||||
|
||||
| Metric |Value|
|
||||
|---------------------------------|----:|
|
||||
|Avg. |67.29|
|
||||
|AI2 Reasoning Challenge (25-Shot)|66.38|
|
||||
|HellaSwag (10-Shot) |85.09|
|
||||
|MMLU (5-Shot) |63.43|
|
||||
|TruthfulQA (0-shot) |54.95|
|
||||
|Winogrande (5-shot) |78.14|
|
||||
|GSM8k (5-shot) |55.72|
|
||||
|
||||
4
added_tokens.json
Normal file
4
added_tokens.json
Normal file
@@ -0,0 +1,4 @@
|
||||
{
|
||||
"<|im_end|>": 32000,
|
||||
"<|im_start|>": 32001
|
||||
}
|
||||
25
config.json
Normal file
25
config.json
Normal file
@@ -0,0 +1,25 @@
|
||||
{
|
||||
"_name_or_path": "mlabonne/NeuralHermes-2.5-Mistral-7B",
|
||||
"architectures": [
|
||||
"MistralForCausalLM"
|
||||
],
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 32000,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 4096,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 14336,
|
||||
"max_position_embeddings": 32768,
|
||||
"model_type": "mistral",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 32,
|
||||
"num_key_value_heads": 8,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_theta": 10000.0,
|
||||
"sliding_window": 4096,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.35.2",
|
||||
"use_cache": false,
|
||||
"vocab_size": 32002
|
||||
}
|
||||
1
configuration.json
Normal file
1
configuration.json
Normal file
@@ -0,0 +1 @@
|
||||
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}
|
||||
6
generation_config.json
Normal file
6
generation_config.json
Normal file
@@ -0,0 +1,6 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 32000,
|
||||
"transformers_version": "4.35.2"
|
||||
}
|
||||
128
laserRMT.log
Normal file
128
laserRMT.log
Normal file
@@ -0,0 +1,128 @@
|
||||
Downloading shards: 100% 3/3 [00:41<00:00, 13.87s/it]
|
||||
Loading checkpoint shards: 100% 3/3 [00:07<00:00, 2.53s/it]
|
||||
generation_config.json: 100% 115/115 [00:00<00:00, 575kB/s]
|
||||
tokenizer_config.json: 100% 1.60k/1.60k [00:00<00:00, 8.48MB/s]
|
||||
tokenizer.model: 100% 493k/493k [00:00<00:00, 22.9MB/s]
|
||||
tokenizer.json: 100% 1.80M/1.80M [00:00<00:00, 7.43MB/s]
|
||||
added_tokens.json: 100% 51.0/51.0 [00:00<00:00, 283kB/s]
|
||||
special_tokens_map.json: 100% 420/420 [00:00<00:00, 1.74MB/s]
|
||||
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
|
||||
Reconstructing layer: model.layers.25.mlp.down_proj
|
||||
Reduced from torch.Size([4096]) to 3607
|
||||
Layer mlp.down_proj_25 has already been modified. Skipping.
|
||||
Restored original weights for layer: model.layers.25.mlp.down_proj
|
||||
Reconstructing layer: model.layers.25.mlp.down_proj
|
||||
Reduced from torch.Size([4096]) to 3607
|
||||
Restored original weights for layer: model.layers.25.mlp.down_proj
|
||||
['.31.', '.30.', '.29.', '.28.', '.27.', '.26.', '.25.', '.24.', '.23.', '.22.', '.21.', '.20.', '.19.', '.18.', '.17.', '.16.', '.15.', '.14.', '.13.', '.12.', '.11.', '.10.', '.9.', '.8.', '.7.', '.6.', '.5.', '.4.', '.3.', '.2.', '.1.', '.0.']
|
||||
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
|
||||
avg_loss = 2.1474520114478235: 100% 871/871 [00:46<00:00, 18.55it/s]
|
||||
/usr/local/lib/python3.10/dist-packages/huggingface_hub/repocard.py:105: UserWarning: Repo card metadata block was not found. Setting CardData to empty.
|
||||
warnings.warn("Repo card metadata block was not found. Setting CardData to empty.")
|
||||
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
|
||||
avg_loss = 9.703152929898351: 100% 256/256 [00:13<00:00, 18.83it/s]
|
||||
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
|
||||
avg_loss = 13.355979550516967: 100% 264/264 [00:14<00:00, 18.66it/s]
|
||||
==================================================
|
||||
The initial perplexity of the model is 12.614558219909668
|
||||
==================================================
|
||||
Reconstructing layer: model.layers.31.mlp.down_proj
|
||||
Reduced from torch.Size([4096]) to 3753
|
||||
avg_loss = 2.150142833641832: 100% 871/871 [00:46<00:00, 18.75it/s]
|
||||
avg_loss = 9.714343913365155: 100% 256/256 [00:13<00:00, 18.74it/s]
|
||||
avg_loss = 13.374103391260812: 100% 264/264 [00:14<00:00, 18.43it/s]
|
||||
Restored original weights for layer: model.layers.31.mlp.down_proj
|
||||
Reconstructing layer: model.layers.31.mlp.up_proj
|
||||
Reduced from torch.Size([4096]) to 3717
|
||||
avg_loss = 2.1734046262660063: 100% 871/871 [00:46<00:00, 18.57it/s]
|
||||
avg_loss = 9.82143080001697: 100% 256/256 [00:13<00:00, 18.57it/s]
|
||||
avg_loss = 13.477815985228077: 100% 264/264 [00:14<00:00, 18.20it/s]
|
||||
Restored original weights for layer: model.layers.31.mlp.up_proj
|
||||
Reconstructing layer: model.layers.31.self_attn.q_proj
|
||||
Reduced from torch.Size([4096]) to 818
|
||||
avg_loss = 2.148138916040808: 100% 871/871 [00:46<00:00, 18.53it/s]
|
||||
avg_loss = 9.705221582669765: 100% 256/256 [00:13<00:00, 18.62it/s]
|
||||
avg_loss = 13.35540055280382: 100% 264/264 [00:14<00:00, 18.71it/s]
|
||||
**************************************************
|
||||
Improved perplexity found: 12.613171577453613 for layer self_attn.q_proj .31.. Total modifications is 1
|
||||
**************************************************
|
||||
Reconstructing layer: model.layers.31.self_attn.k_proj
|
||||
Reduced from torch.Size([1024]) to 524
|
||||
avg_loss = 2.1553964071514686: 100% 871/871 [00:46<00:00, 18.71it/s]
|
||||
avg_loss = 9.734999645967036: 100% 256/256 [00:13<00:00, 18.84it/s]
|
||||
avg_loss = 13.383289175954731: 100% 264/264 [00:14<00:00, 18.51it/s]
|
||||
Restored original weights for layer: model.layers.31.self_attn.k_proj
|
||||
Reconstructing layer: model.layers.31.self_attn.v_proj
|
||||
Reduced from torch.Size([1024]) to 846
|
||||
avg_loss = 2.1430855287339465: 100% 871/871 [00:46<00:00, 18.78it/s]
|
||||
avg_loss = 9.666598222218454: 100% 256/256 [00:13<00:00, 18.74it/s]
|
||||
avg_loss = 13.313674368641593: 100% 264/264 [00:14<00:00, 18.69it/s]
|
||||
**************************************************
|
||||
Improved perplexity found: 12.513681411743164 for layer self_attn.v_proj .31.. Total modifications is 2
|
||||
**************************************************
|
||||
Reconstructing layer: model.layers.31.self_attn.o_proj
|
||||
Reduced from torch.Size([4096]) to 834
|
||||
avg_loss = 2.1483869746960402: 100% 871/871 [00:47<00:00, 18.46it/s]
|
||||
avg_loss = 9.686229056213051: 100% 256/256 [00:13<00:00, 18.78it/s]
|
||||
avg_loss = 13.344844787861362: 100% 264/264 [00:14<00:00, 18.56it/s]
|
||||
Restored original weights for layer: model.layers.31.self_attn.o_proj
|
||||
Reconstructing layer: model.layers.30.mlp.down_proj
|
||||
Reduced from torch.Size([4096]) to 3770
|
||||
avg_loss = 2.1505854418576105: 100% 871/871 [00:47<00:00, 18.34it/s]
|
||||
avg_loss = 9.6962159560062: 100% 256/256 [00:13<00:00, 18.63it/s]
|
||||
avg_loss = 13.353956826256983: 100% 264/264 [00:14<00:00, 18.49it/s]
|
||||
Restored original weights for layer: model.layers.30.mlp.down_proj
|
||||
Reconstructing layer: model.layers.30.mlp.up_proj
|
||||
Reduced from torch.Size([4096]) to 3787
|
||||
avg_loss = 2.148582770547965: 100% 871/871 [00:47<00:00, 18.34it/s]
|
||||
avg_loss = 9.686316559556872: 100% 256/256 [00:13<00:00, 18.59it/s]
|
||||
avg_loss = 13.34067751738158: 100% 264/264 [00:14<00:00, 18.81it/s]
|
||||
Restored original weights for layer: model.layers.30.mlp.up_proj
|
||||
Reconstructing layer: model.layers.30.self_attn.q_proj
|
||||
Reduced from torch.Size([4096]) to 819
|
||||
avg_loss = 2.1425534111760927: 100% 871/871 [00:47<00:00, 18.40it/s]
|
||||
avg_loss = 9.664284548722208: 100% 256/256 [00:13<00:00, 18.49it/s]
|
||||
avg_loss = 13.309857179721197: 100% 264/264 [00:14<00:00, 18.63it/s]
|
||||
**************************************************
|
||||
Improved perplexity found: 12.504617691040039 for layer self_attn.q_proj .30.. Total modifications is 3
|
||||
**************************************************
|
||||
Reconstructing layer: model.layers.30.self_attn.k_proj
|
||||
Reduced from torch.Size([1024]) to 524
|
||||
avg_loss = 2.1449567824088884: 100% 871/871 [00:47<00:00, 18.51it/s]
|
||||
avg_loss = 9.675114367622882: 100% 256/256 [00:13<00:00, 18.56it/s]
|
||||
avg_loss = 13.32237600783507: 100% 264/264 [00:14<00:00, 18.72it/s]
|
||||
Restored original weights for layer: model.layers.30.self_attn.k_proj
|
||||
Reconstructing layer: model.layers.30.self_attn.v_proj
|
||||
Reduced from torch.Size([1024]) to 812
|
||||
avg_loss = 2.155356107294628: 100% 871/871 [00:47<00:00, 18.48it/s]
|
||||
avg_loss = 9.7138080005534: 100% 256/256 [00:13<00:00, 18.37it/s]
|
||||
avg_loss = 13.366635067444859: 100% 264/264 [00:14<00:00, 18.33it/s]
|
||||
Restored original weights for layer: model.layers.30.self_attn.v_proj
|
||||
Reconstructing layer: model.layers.30.self_attn.o_proj
|
||||
Reduced from torch.Size([4096]) to 859
|
||||
avg_loss = 2.146158002821641: 100% 871/871 [00:47<00:00, 18.33it/s]
|
||||
avg_loss = 9.676836102735251: 100% 256/256 [00:13<00:00, 18.43it/s]
|
||||
avg_loss = 13.318221795287998: 100% 264/264 [00:14<00:00, 18.33it/s]
|
||||
Restored original weights for layer: model.layers.30.self_attn.o_proj
|
||||
Reconstructing layer: model.layers.29.mlp.down_proj
|
||||
Reduced from torch.Size([4096]) to 3763
|
||||
avg_loss = 2.1450509054652587: 100% 871/871 [00:47<00:00, 18.35it/s]
|
||||
avg_loss = 9.6743658403866: 100% 256/256 [00:14<00:00, 18.21it/s]
|
||||
avg_loss = 13.321742536895202: 100% 264/264 [00:14<00:00, 18.19it/s]
|
||||
Restored original weights for layer: model.layers.29.mlp.down_proj
|
||||
Reconstructing layer: model.layers.29.mlp.up_proj
|
||||
Reduced from torch.Size([4096]) to 3828
|
||||
avg_loss = 2.1408350525165125: 100% 871/871 [00:47<00:00, 18.21it/s]
|
||||
avg_loss = 9.65894997306168: 100% 256/256 [00:14<00:00, 18.26it/s]
|
||||
avg_loss = 13.306687997146087: 100% 264/264 [00:14<00:00, 18.31it/s]
|
||||
**************************************************
|
||||
Improved perplexity found: 12.497097969055176 for layer mlp.up_proj .29.. Total modifications is 4
|
||||
**************************************************
|
||||
Reconstructing layer: model.layers.29.self_attn.q_proj
|
||||
Reduced from torch.Size([4096]) to 803
|
||||
avg_loss = 2.1367383972238043: 100% 871/871 [00:47<00:00, 18.18it/s]
|
||||
avg_loss = 9.641230288892984: 100% 256/256 [00:13<00:00, 18.36it/s]
|
||||
avg_loss = 13.289274643767964: 100% 264/264 [00:14<00:00, 18.47it/s]
|
||||
**************************************************
|
||||
Improved perplexity found: 12.455863952636719 for layer self_attn.q_proj .29.. Total modifications is 5
|
||||
**************************************************
|
||||
3
model-00001-of-00003.safetensors
Normal file
3
model-00001-of-00003.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:135ef5f4a8def72031c6aa2213e7fe6f4cae48b68c537c6ca70b5678722c18f9
|
||||
size 4943178720
|
||||
3
model-00002-of-00003.safetensors
Normal file
3
model-00002-of-00003.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b4910158a27886558254fecad898ddeb9e569e1d53eb3d27c05c7371eade0e4b
|
||||
size 4999819336
|
||||
3
model-00003-of-00003.safetensors
Normal file
3
model-00003-of-00003.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:e9d6b4ff69cd826be5f64ea6b190232e7076d84e4b35cc95fe2dc2bfbb0e4a36
|
||||
size 4540532728
|
||||
298
model.safetensors.index.json
Normal file
298
model.safetensors.index.json
Normal file
@@ -0,0 +1,298 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 14483496960
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00003-of-00003.safetensors",
|
||||
"model.embed_tokens.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.norm.weight": "model-00003-of-00003.safetensors"
|
||||
}
|
||||
}
|
||||
23
special_tokens_map.json
Normal file
23
special_tokens_map.json
Normal file
@@ -0,0 +1,23 @@
|
||||
{
|
||||
"bos_token": {
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"unk_token": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
91140
tokenizer.json
Normal file
91140
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.
59
tokenizer_config.json
Normal file
59
tokenizer_config.json
Normal file
@@ -0,0 +1,59 @@
|
||||
{
|
||||
"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_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32001": {
|
||||
"content": "<|im_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
}
|
||||
},
|
||||
"additional_special_tokens": [],
|
||||
"bos_token": "<s>",
|
||||
"chat_template": "{% for message in messages %}{{'<|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": "<|im_end|>",
|
||||
"legacy": true,
|
||||
"model_max_length": 1000000000000000019884624838656,
|
||||
"pad_token": null,
|
||||
"sp_model_kwargs": {},
|
||||
"spaces_between_special_tokens": false,
|
||||
"tokenizer_class": "LlamaTokenizer",
|
||||
"trust_remote_code": false,
|
||||
"unk_token": "<unk>",
|
||||
"use_default_system_prompt": true,
|
||||
"use_fast": true
|
||||
}
|
||||
Reference in New Issue
Block a user