初始化项目，由ModelHub XC社区提供模型
Model: HuggingFaceH4/mistral-7b-sft-beta Source: Original Platform
This commit is contained in:
ModelHub XC
39
.gitattributes
vendored
Normal file
39
.gitattributes
vendored
Normal file
@@ -0,0 +1,39 @@
|
||||
*.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
|
||||
model-00001-of-00002.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
model-00002-of-00002.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
pytorch_model-00001-of-00002.bin filter=lfs diff=lfs merge=lfs -text
|
||||
pytorch_model-00002-of-00002.bin filter=lfs diff=lfs merge=lfs -text
|
||||
104
README.md
Normal file
104
README.md
Normal file
@@ -0,0 +1,104 @@
|
||||
---
|
||||
license: mit
|
||||
base_model: mistralai/Mistral-7B-v0.1
|
||||
tags:
|
||||
- generated_from_trainer
|
||||
model-index:
|
||||
- name: mistral-7b-sft-beta
|
||||
results: []
|
||||
datasets:
|
||||
- HuggingFaceH4/ultrachat_200k
|
||||
language:
|
||||
- en
|
||||
---
|
||||
|
||||
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
||||
should probably proofread and complete it, then remove this comment. -->
|
||||
|
||||
# Model Card for Mistral 7B SFT β
|
||||
|
||||
This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the HuggingFaceH4/ultrachat_200k dataset. It is the SFT model that was used to train Zephyr-7B-β with Direct Preference Optimization.
|
||||
|
||||
It achieves the following results on the evaluation set:
|
||||
- Loss: 0.9399
|
||||
|
||||
## Model description
|
||||
|
||||
- **Model type:** A 7B parameter GPT-like model fine-tuned on a mix of publicly available, synthetic datasets.
|
||||
- **Language(s) (NLP):** Primarily English
|
||||
- **License:** MIT
|
||||
- **Finetuned from model:** [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1)
|
||||
|
||||
### Model Sources
|
||||
|
||||
<!-- Provide the basic links for the model. -->
|
||||
|
||||
- **Repository:** https://github.com/huggingface/alignment-handbook
|
||||
|
||||
## Intended uses & limitations
|
||||
|
||||
The model was fine-tuned with [🤗 TRL's](https://github.com/huggingface/trl) `SFTTrainer` on a filtered and preprocessed of the [`UltraChat`](https://huggingface.co/datasets/stingning/ultrachat) dataset, which contains a diverse range of synthetic dialogues generated by ChatGPT.
|
||||
|
||||
Here's how you can run the model using the `pipeline()` function from 🤗 Transformers:
|
||||
|
||||
```python
|
||||
# Install transformers from source - only needed for versions <= v4.34
|
||||
# pip install git+https://github.com/huggingface/transformers.git
|
||||
# pip install accelerate
|
||||
|
||||
import torch
|
||||
from transformers import pipeline
|
||||
|
||||
pipe = pipeline("text-generation", model="HuggingFaceH4/mistral-7b-sft-beta", torch_dtype=torch.bfloat16, device_map="auto")
|
||||
|
||||
# We use the tokenizer's chat template to format each message - see https://huggingface.co/docs/transformers/main/en/chat_templating
|
||||
messages = [
|
||||
{
|
||||
"role": "system",
|
||||
"content": "You are a friendly chatbot who always responds in the style of a pirate",
|
||||
},
|
||||
{"role": "user", "content": "How many helicopters can a human eat in one sitting?"},
|
||||
]
|
||||
prompt = pipe.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
|
||||
outputs = pipe(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
|
||||
print(outputs[0]["generated_text"])
|
||||
# <|system|>
|
||||
# You are a friendly chatbot who always responds in the style of a pirate.</s>
|
||||
# <|user|>
|
||||
# How many helicopters can a human eat in one sitting?</s>
|
||||
# <|assistant|>
|
||||
# Ah, me hearty matey! But yer question be a puzzler! A human cannot eat a helicopter in one sitting, as helicopters are not edible. They be made of metal, plastic, and other materials, not food!
|
||||
```
|
||||
|
||||
## Training procedure
|
||||
|
||||
### Training hyperparameters
|
||||
|
||||
The following hyperparameters were used during training:
|
||||
- learning_rate: 2e-05
|
||||
- train_batch_size: 8
|
||||
- eval_batch_size: 16
|
||||
- seed: 42
|
||||
- distributed_type: multi-GPU
|
||||
- num_devices: 16
|
||||
- gradient_accumulation_steps: 4
|
||||
- total_train_batch_size: 512
|
||||
- total_eval_batch_size: 256
|
||||
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
||||
- lr_scheduler_type: cosine
|
||||
- lr_scheduler_warmup_ratio: 0.1
|
||||
- num_epochs: 1
|
||||
|
||||
### Training results
|
||||
|
||||
| Training Loss | Epoch | Step | Validation Loss |
|
||||
|:-------------:|:-----:|:----:|:---------------:|
|
||||
| 0.9367 | 0.67 | 272 | 0.9397 |
|
||||
|
||||
|
||||
### Framework versions
|
||||
|
||||
- Transformers 4.35.0.dev0
|
||||
- Pytorch 2.0.1+cu118
|
||||
- Datasets 2.12.0
|
||||
- Tokenizers 0.14.0
|
||||
5
added_tokens.json
Normal file
5
added_tokens.json
Normal file
@@ -0,0 +1,5 @@
|
||||
{
|
||||
"</s>": 2,
|
||||
"<s>": 1,
|
||||
"<unk>": 0
|
||||
}
|
||||
14
all_results.json
Normal file
14
all_results.json
Normal file
@@ -0,0 +1,14 @@
|
||||
{
|
||||
"epoch": 0.67,
|
||||
"eval_loss": 0.9398621916770935,
|
||||
"eval_runtime": 183.2326,
|
||||
"eval_samples": 23110,
|
||||
"eval_samples_per_second": 126.124,
|
||||
"eval_steps_per_second": 0.497,
|
||||
"perplexity": 2.559628655890698,
|
||||
"train_loss": 0.9917194036876454,
|
||||
"train_runtime": 6192.0322,
|
||||
"train_samples": 207865,
|
||||
"train_samples_per_second": 33.57,
|
||||
"train_steps_per_second": 0.066
|
||||
}
|
||||
25
config.json
Normal file
25
config.json
Normal file
@@ -0,0 +1,25 @@
|
||||
{
|
||||
"_name_or_path": "mistralai/Mistral-7B-v0.1",
|
||||
"architectures": [
|
||||
"MistralForCausalLM"
|
||||
],
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"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": "4.35.0.dev0",
|
||||
"use_cache": true,
|
||||
"vocab_size": 32000
|
||||
}
|
||||
1
configuration.json
Normal file
1
configuration.json
Normal file
@@ -0,0 +1 @@
|
||||
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}
|
||||
30
dialogue_template.json
Normal file
30
dialogue_template.json
Normal file
@@ -0,0 +1,30 @@
|
||||
{
|
||||
"system": "",
|
||||
"name": "default_v3",
|
||||
"messages": [
|
||||
{
|
||||
"content": "When Texans think about defensive driving, they think DefensiveDriving.com. We have been a market leader providing quality defensive driving course online products since 2000. Texans rely on us to provide an online defensive driving course. Whether in the big cities of Houston, Dallas, San Antonio, the triangle of East Texas or the West Texas canyons, Texans across the state have come to trust us to provide high quality service for defensive driving.\nWith its 24 hour, 365 days a year service and its professional staff, our defensive driving course is educational, convenient and contemporary with DefensiveDriving.com. It is really the only way to take defensive driving course online for ticket dismissal or insurance reduction. Here, it is literally Texans serving Texans. Our staff is in Texas, not a foreign country. They are from Texas and all of our servers providing defensive driving course online are in Texas. Texas was one of the first states to approve defensive driving for ticket dismissal and we were one of the first to offer a defensive driving course online in a non-classroom setting.\nDefensiveDriving.com thinks the convenience, the service and the quality of our online defensive driving course should make the decision to choose us for your defensive driving course. It is easy, so sign up today, Got a Ticket, Just Click It!\nCan you provide information about DefensiveDriving.com's online defensive driving course and why Texans prefer it?",
|
||||
"role": "user"
|
||||
},
|
||||
{
|
||||
"content": "DefensiveDriving.com has been a market leader in providing quality online defensive driving course products to Texans since the year 2000. The company offers a convenient and contemporary course that can be accessed 24 hours a day, 365 days a year. The course is recognized by the state of Texas and can be taken for ticket dismissal or insurance reduction purposes. Texans prefer DefensiveDriving.com because of its professional staff, high-quality service, and educational content. The company is dedicated to serving Texans and all of its servers are located within the state. DefensiveDriving.com was one of the first companies to offer a defensive driving course online in a non-classroom setting, making it highly accessible and convenient. Overall, DefensiveDriving.com's online defensive driving course is the ideal option for anyone seeking a hassle-free, efficient, and effective way to complete a defensive driving course.",
|
||||
"role": "assistant"
|
||||
},
|
||||
{
|
||||
"content": "Can you tell me more about the benefits of taking DefensiveDriving.com's online defensive driving course compared to taking it in a classroom setting?",
|
||||
"role": "user"
|
||||
},
|
||||
{
|
||||
"content": "I do not have any personal experience with taking driving courses; however, I can provide information on the benefits of taking defensivedriving.com's online defensive driving course compared to taking it in a classroom.\n\none of the primary benefits of taking the course online with defensivedriving.com is convenience. The course is entirely online and can be completed at any time and from any location, enabling you to work around a busy schedule or fulfill court-mandated requirements from the comfort of your own home.\n\nanother benefit is the flexibility offered by an online course. Students can learn at their own pace rather than being tied to a set schedule in a classroom setting.\n\nonline courses also offer a more engaging and interactive learning experience. The course content is delivered through a variety of mediums, including videos, animations, and interactive exercises, which can make for a more engaging and enjoyable learning experience.\n\nfinally, defensivedriving.com's online course is cost-effective. Students can avoid the costs associated with travel, parking and time off from work by completing the course from home. \n\noverall, taking defensivedriving.com's online defensive driving course has many benefits for those seeking a convenient, flexible, and affordable way to complete the course.",
|
||||
"role": "assistant"
|
||||
}
|
||||
],
|
||||
"system_token": "<|system|>",
|
||||
"system_format": "standard",
|
||||
"user_token": "<|user|>",
|
||||
"assistant_token": "<|assistant|>",
|
||||
"end_token": "</s>",
|
||||
"mid_str": "\n",
|
||||
"end_str": "\n",
|
||||
"extra_end_text": "\n"
|
||||
}
|
||||
9
eval_results.json
Normal file
9
eval_results.json
Normal file
@@ -0,0 +1,9 @@
|
||||
{
|
||||
"epoch": 0.67,
|
||||
"eval_loss": 0.9398621916770935,
|
||||
"eval_runtime": 183.2326,
|
||||
"eval_samples": 23110,
|
||||
"eval_samples_per_second": 126.124,
|
||||
"eval_steps_per_second": 0.497,
|
||||
"perplexity": 2.559628655890698
|
||||
}
|
||||
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": 2,
|
||||
"transformers_version": "4.35.0.dev0"
|
||||
}
|
||||
3
model-00001-of-00002.safetensors
Normal file
3
model-00001-of-00002.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:3dac4fcf38c3bb7cf70ce95365c95044f46a3051330776ff1c7a9085e84f7cf5
|
||||
size 9942981696
|
||||
3
model-00002-of-00002.safetensors
Normal file
3
model-00002-of-00002.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:2fe824bc51c088b671e855db56949868d9390af6d8859044d5359268cdaa8b9d
|
||||
size 4540516344
|
||||
3
pytorch_model-00001-of-00002.bin
Normal file
3
pytorch_model-00001-of-00002.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:5b98b2b8458d591606e0dcf05013cf71e55b888e719b5506d1a5a286d256c652
|
||||
size 9943028044
|
||||
3
pytorch_model-00002-of-00002.bin
Normal file
3
pytorch_model-00002-of-00002.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:1fd43973d3cc02a4de208e593b8c81ac137367a012c471b21fbfb1a3981dc7ba
|
||||
size 4540535647
|
||||
298
pytorch_model.bin.index.json
Normal file
298
pytorch_model.bin.index.json
Normal file
@@ -0,0 +1,298 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 14483464192
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.15.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.15.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.16.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.16.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.17.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.17.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.18.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.18.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.19.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.19.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.20.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.20.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.21.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.21.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.22.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.23.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.27.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.27.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.28.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.28.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.29.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.29.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.30.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.30.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.30.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.30.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.30.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.30.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.31.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.31.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.31.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.31.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.31.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.31.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.31.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.31.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.31.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.norm.weight": "pytorch_model-00002-of-00002.bin"
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a14d0220ddc8b157ce07c37127485d98d2965dcd6adb90e929fe6b70f626c483
|
||||
size 13648
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:1ea755c95c45f01011178573107e7f1efd1226ed4a629f57cd63272f1b9e9c58
|
||||
size 359
|
||||
11
special_tokens_map.json
Normal file
11
special_tokens_map.json
Normal file
@@ -0,0 +1,11 @@
|
||||
{
|
||||
"additional_special_tokens": [
|
||||
"<unk>",
|
||||
"<s>",
|
||||
"</s>"
|
||||
],
|
||||
"bos_token": "<s>",
|
||||
"eos_token": "</s>",
|
||||
"pad_token": "</s>",
|
||||
"unk_token": "<unk>"
|
||||
}
|
||||
91122
tokenizer.json
Normal file
91122
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.
46
tokenizer_config.json
Normal file
46
tokenizer_config.json
Normal file
@@ -0,0 +1,46 @@
|
||||
{
|
||||
"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
|
||||
}
|
||||
},
|
||||
"additional_special_tokens": [
|
||||
"<unk>",
|
||||
"<s>",
|
||||
"</s>"
|
||||
],
|
||||
"bos_token": "<s>",
|
||||
"chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "</s>",
|
||||
"legacy": true,
|
||||
"model_max_length": 1000000000000000019884624838656,
|
||||
"pad_token": "</s>",
|
||||
"sp_model_kwargs": {},
|
||||
"spaces_between_special_tokens": false,
|
||||
"tokenizer_class": "LlamaTokenizer",
|
||||
"truncation_side": "left",
|
||||
"unk_token": "<unk>",
|
||||
"use_default_system_prompt": true
|
||||
}
|
||||
8
train_results.json
Normal file
8
train_results.json
Normal file
@@ -0,0 +1,8 @@
|
||||
{
|
||||
"epoch": 0.67,
|
||||
"train_loss": 0.9917194036876454,
|
||||
"train_runtime": 6192.0322,
|
||||
"train_samples": 207865,
|
||||
"train_samples_per_second": 33.57,
|
||||
"train_steps_per_second": 0.066
|
||||
}
|
||||
366
trainer_state.json
Normal file
366
trainer_state.json
Normal file
@@ -0,0 +1,366 @@
|
||||
{
|
||||
"best_metric": null,
|
||||
"best_model_checkpoint": null,
|
||||
"epoch": 0.6699507389162561,
|
||||
"eval_steps": 500,
|
||||
"global_step": 272,
|
||||
"is_hyper_param_search": false,
|
||||
"is_local_process_zero": true,
|
||||
"is_world_process_zero": true,
|
||||
"log_history": [
|
||||
{
|
||||
"epoch": 0.0,
|
||||
"learning_rate": 4.878048780487805e-07,
|
||||
"loss": 1.6931,
|
||||
"step": 1
|
||||
},
|
||||
{
|
||||
"epoch": 0.01,
|
||||
"learning_rate": 2.4390243902439027e-06,
|
||||
"loss": 1.5849,
|
||||
"step": 5
|
||||
},
|
||||
{
|
||||
"epoch": 0.02,
|
||||
"learning_rate": 4.8780487804878055e-06,
|
||||
"loss": 1.2774,
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"epoch": 0.04,
|
||||
"learning_rate": 7.317073170731707e-06,
|
||||
"loss": 1.1546,
|
||||
"step": 15
|
||||
},
|
||||
{
|
||||
"epoch": 0.05,
|
||||
"learning_rate": 9.756097560975611e-06,
|
||||
"loss": 1.1132,
|
||||
"step": 20
|
||||
},
|
||||
{
|
||||
"epoch": 0.06,
|
||||
"learning_rate": 1.2195121951219513e-05,
|
||||
"loss": 1.0589,
|
||||
"step": 25
|
||||
},
|
||||
{
|
||||
"epoch": 0.07,
|
||||
"learning_rate": 1.4634146341463415e-05,
|
||||
"loss": 1.0348,
|
||||
"step": 30
|
||||
},
|
||||
{
|
||||
"epoch": 0.09,
|
||||
"learning_rate": 1.7073170731707317e-05,
|
||||
"loss": 1.0263,
|
||||
"step": 35
|
||||
},
|
||||
{
|
||||
"epoch": 0.1,
|
||||
"learning_rate": 1.9512195121951222e-05,
|
||||
"loss": 1.0087,
|
||||
"step": 40
|
||||
},
|
||||
{
|
||||
"epoch": 0.11,
|
||||
"learning_rate": 1.999407400739705e-05,
|
||||
"loss": 1.005,
|
||||
"step": 45
|
||||
},
|
||||
{
|
||||
"epoch": 0.12,
|
||||
"learning_rate": 1.997001169925015e-05,
|
||||
"loss": 1.0048,
|
||||
"step": 50
|
||||
},
|
||||
{
|
||||
"epoch": 0.14,
|
||||
"learning_rate": 1.9927487224577402e-05,
|
||||
"loss": 0.995,
|
||||
"step": 55
|
||||
},
|
||||
{
|
||||
"epoch": 0.15,
|
||||
"learning_rate": 1.986657932891657e-05,
|
||||
"loss": 0.9845,
|
||||
"step": 60
|
||||
},
|
||||
{
|
||||
"epoch": 0.16,
|
||||
"learning_rate": 1.9787400799669155e-05,
|
||||
"loss": 0.9785,
|
||||
"step": 65
|
||||
},
|
||||
{
|
||||
"epoch": 0.17,
|
||||
"learning_rate": 1.9690098257244063e-05,
|
||||
"loss": 0.971,
|
||||
"step": 70
|
||||
},
|
||||
{
|
||||
"epoch": 0.18,
|
||||
"learning_rate": 1.9574851883550395e-05,
|
||||
"loss": 0.977,
|
||||
"step": 75
|
||||
},
|
||||
{
|
||||
"epoch": 0.2,
|
||||
"learning_rate": 1.9441875088342e-05,
|
||||
"loss": 0.9847,
|
||||
"step": 80
|
||||
},
|
||||
{
|
||||
"epoch": 0.21,
|
||||
"learning_rate": 1.9291414114031744e-05,
|
||||
"loss": 0.9813,
|
||||
"step": 85
|
||||
},
|
||||
{
|
||||
"epoch": 0.22,
|
||||
"learning_rate": 1.9123747579707275e-05,
|
||||
"loss": 0.9713,
|
||||
"step": 90
|
||||
},
|
||||
{
|
||||
"epoch": 0.23,
|
||||
"learning_rate": 1.8939185965192572e-05,
|
||||
"loss": 0.9603,
|
||||
"step": 95
|
||||
},
|
||||
{
|
||||
"epoch": 0.25,
|
||||
"learning_rate": 1.873807103611081e-05,
|
||||
"loss": 0.9732,
|
||||
"step": 100
|
||||
},
|
||||
{
|
||||
"epoch": 0.26,
|
||||
"learning_rate": 1.8520775211013094e-05,
|
||||
"loss": 0.9869,
|
||||
"step": 105
|
||||
},
|
||||
{
|
||||
"epoch": 0.27,
|
||||
"learning_rate": 1.8287700871745036e-05,
|
||||
"loss": 0.9652,
|
||||
"step": 110
|
||||
},
|
||||
{
|
||||
"epoch": 0.28,
|
||||
"learning_rate": 1.8039279618328215e-05,
|
||||
"loss": 0.9613,
|
||||
"step": 115
|
||||
},
|
||||
{
|
||||
"epoch": 0.3,
|
||||
"learning_rate": 1.777597146973627e-05,
|
||||
"loss": 0.9669,
|
||||
"step": 120
|
||||
},
|
||||
{
|
||||
"epoch": 0.31,
|
||||
"learning_rate": 1.7498264012045686e-05,
|
||||
"loss": 0.9639,
|
||||
"step": 125
|
||||
},
|
||||
{
|
||||
"epoch": 0.32,
|
||||
"learning_rate": 1.720667149553861e-05,
|
||||
"loss": 0.9713,
|
||||
"step": 130
|
||||
},
|
||||
{
|
||||
"epoch": 0.33,
|
||||
"learning_rate": 1.690173388242972e-05,
|
||||
"loss": 0.9718,
|
||||
"step": 135
|
||||
},
|
||||
{
|
||||
"epoch": 0.34,
|
||||
"learning_rate": 1.658401584698049e-05,
|
||||
"loss": 0.9569,
|
||||
"step": 140
|
||||
},
|
||||
{
|
||||
"epoch": 0.36,
|
||||
"learning_rate": 1.6254105729852466e-05,
|
||||
"loss": 0.9617,
|
||||
"step": 145
|
||||
},
|
||||
{
|
||||
"epoch": 0.37,
|
||||
"learning_rate": 1.5912614448635784e-05,
|
||||
"loss": 0.9583,
|
||||
"step": 150
|
||||
},
|
||||
{
|
||||
"epoch": 0.38,
|
||||
"learning_rate": 1.5560174366570448e-05,
|
||||
"loss": 0.9541,
|
||||
"step": 155
|
||||
},
|
||||
{
|
||||
"epoch": 0.39,
|
||||
"learning_rate": 1.5197438121555159e-05,
|
||||
"loss": 0.9433,
|
||||
"step": 160
|
||||
},
|
||||
{
|
||||
"epoch": 0.41,
|
||||
"learning_rate": 1.4825077417612187e-05,
|
||||
"loss": 0.9591,
|
||||
"step": 165
|
||||
},
|
||||
{
|
||||
"epoch": 0.42,
|
||||
"learning_rate": 1.4443781781046135e-05,
|
||||
"loss": 0.9594,
|
||||
"step": 170
|
||||
},
|
||||
{
|
||||
"epoch": 0.43,
|
||||
"learning_rate": 1.4054257283599974e-05,
|
||||
"loss": 0.9451,
|
||||
"step": 175
|
||||
},
|
||||
{
|
||||
"epoch": 0.44,
|
||||
"learning_rate": 1.3657225234972695e-05,
|
||||
"loss": 0.9511,
|
||||
"step": 180
|
||||
},
|
||||
{
|
||||
"epoch": 0.46,
|
||||
"learning_rate": 1.3253420847119804e-05,
|
||||
"loss": 0.9606,
|
||||
"step": 185
|
||||
},
|
||||
{
|
||||
"epoch": 0.47,
|
||||
"learning_rate": 1.2843591872810039e-05,
|
||||
"loss": 0.9541,
|
||||
"step": 190
|
||||
},
|
||||
{
|
||||
"epoch": 0.48,
|
||||
"learning_rate": 1.2428497220959359e-05,
|
||||
"loss": 0.9541,
|
||||
"step": 195
|
||||
},
|
||||
{
|
||||
"epoch": 0.49,
|
||||
"learning_rate": 1.2008905551306356e-05,
|
||||
"loss": 0.9446,
|
||||
"step": 200
|
||||
},
|
||||
{
|
||||
"epoch": 0.5,
|
||||
"learning_rate": 1.1585593851031346e-05,
|
||||
"loss": 0.9484,
|
||||
"step": 205
|
||||
},
|
||||
{
|
||||
"epoch": 0.52,
|
||||
"learning_rate": 1.1159345995955007e-05,
|
||||
"loss": 0.9464,
|
||||
"step": 210
|
||||
},
|
||||
{
|
||||
"epoch": 0.53,
|
||||
"learning_rate": 1.0730951298980776e-05,
|
||||
"loss": 0.9569,
|
||||
"step": 215
|
||||
},
|
||||
{
|
||||
"epoch": 0.54,
|
||||
"learning_rate": 1.0301203048469084e-05,
|
||||
"loss": 0.9458,
|
||||
"step": 220
|
||||
},
|
||||
{
|
||||
"epoch": 0.55,
|
||||
"learning_rate": 9.87089703924991e-06,
|
||||
"loss": 0.9481,
|
||||
"step": 225
|
||||
},
|
||||
{
|
||||
"epoch": 0.57,
|
||||
"learning_rate": 9.440830098993969e-06,
|
||||
"loss": 0.946,
|
||||
"step": 230
|
||||
},
|
||||
{
|
||||
"epoch": 0.58,
|
||||
"learning_rate": 9.011798612671286e-06,
|
||||
"loss": 0.9427,
|
||||
"step": 235
|
||||
},
|
||||
{
|
||||
"epoch": 0.59,
|
||||
"learning_rate": 8.58459704782957e-06,
|
||||
"loss": 0.9489,
|
||||
"step": 240
|
||||
},
|
||||
{
|
||||
"epoch": 0.6,
|
||||
"learning_rate": 8.1600164834232e-06,
|
||||
"loss": 0.9512,
|
||||
"step": 245
|
||||
},
|
||||
{
|
||||
"epoch": 0.62,
|
||||
"learning_rate": 7.738843144917119e-06,
|
||||
"loss": 0.9372,
|
||||
"step": 250
|
||||
},
|
||||
{
|
||||
"epoch": 0.63,
|
||||
"learning_rate": 7.321856948378259e-06,
|
||||
"loss": 0.9308,
|
||||
"step": 255
|
||||
},
|
||||
{
|
||||
"epoch": 0.64,
|
||||
"learning_rate": 6.909830056250527e-06,
|
||||
"loss": 0.9455,
|
||||
"step": 260
|
||||
},
|
||||
{
|
||||
"epoch": 0.65,
|
||||
"learning_rate": 6.503525447487717e-06,
|
||||
"loss": 0.934,
|
||||
"step": 265
|
||||
},
|
||||
{
|
||||
"epoch": 0.67,
|
||||
"learning_rate": 6.103695504692122e-06,
|
||||
"loss": 0.9367,
|
||||
"step": 270
|
||||
},
|
||||
{
|
||||
"epoch": 0.67,
|
||||
"eval_loss": 0.939697802066803,
|
||||
"eval_runtime": 188.9428,
|
||||
"eval_samples_per_second": 122.312,
|
||||
"eval_steps_per_second": 0.482,
|
||||
"step": 272
|
||||
},
|
||||
{
|
||||
"epoch": 0.67,
|
||||
"step": 272,
|
||||
"total_flos": 455767165501440.0,
|
||||
"train_loss": 0.9917194036876454,
|
||||
"train_runtime": 6192.0322,
|
||||
"train_samples_per_second": 33.57,
|
||||
"train_steps_per_second": 0.066
|
||||
}
|
||||
],
|
||||
"logging_steps": 5,
|
||||
"max_steps": 406,
|
||||
"num_train_epochs": 1,
|
||||
"save_steps": 500,
|
||||
"total_flos": 455767165501440.0,
|
||||
"trial_name": null,
|
||||
"trial_params": null
|
||||
}
|
||||
Reference in New Issue
Block a user