初始化项目，由ModelHub XC社区提供模型
Model: netease-youdao/Confucius3-Math Source: Original Platform
This commit is contained in:
ModelHub XC
36
.gitattributes
vendored
Normal file
36
.gitattributes
vendored
Normal file
@@ -0,0 +1,36 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
46
LICENSE
Normal file
46
LICENSE
Normal file
@@ -0,0 +1,46 @@
|
||||
MIT License
|
||||
|
||||
Copyright (c) 2025 NetEase Youdao
|
||||
|
||||
Permission is hereby granted, free of charge, to any person obtaining a copy
|
||||
of this software and associated documentation files (the "Software"), to deal
|
||||
in the Software without restriction, including without limitation the rights
|
||||
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
||||
copies of the Software, and to permit persons to whom the Software is
|
||||
furnished to do so, subject to the following conditions:
|
||||
|
||||
The above copyright notice and this permission notice shall be included in all
|
||||
copies or substantial portions of the Software.
|
||||
|
||||
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
||||
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
||||
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
||||
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
||||
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
||||
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
|
||||
SOFTWARE.
|
||||
|
||||
This model was modified from DeepSeek-R1-Distill-Qwen-14B. We thank DeepSeek
|
||||
for their contributions. The following is the original copyright notice of
|
||||
DeepSeek.
|
||||
|
||||
|
||||
Copyright (c) 2023 DeepSeek
|
||||
|
||||
Permission is hereby granted, free of charge, to any person obtaining a copy
|
||||
of this software and associated documentation files (the "Software"), to deal
|
||||
in the Software without restriction, including without limitation the rights
|
||||
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
||||
copies of the Software, and to permit persons to whom the Software is
|
||||
furnished to do so, subject to the following conditions:
|
||||
|
||||
The above copyright notice and this permission notice shall be included in all
|
||||
copies or substantial portions of the Software.
|
||||
|
||||
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
||||
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
||||
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
||||
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
||||
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
||||
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
|
||||
SOFTWARE.
|
||||
142
README.md
Normal file
142
README.md
Normal file
@@ -0,0 +1,142 @@
|
||||
---
|
||||
license: mit
|
||||
language:
|
||||
- en
|
||||
base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
|
||||
tags:
|
||||
- chat
|
||||
library_name: transformers
|
||||
---
|
||||
|
||||
# Confucius3-Math
|
||||
<p align="center">
|
||||
<img width="25%" src="figures/confucius_logo.png">
|
||||
</p>
|
||||
|
||||
## Introduction
|
||||
<div style="display: flex; justify-content: center; gap: 20px;">
|
||||
|
||||
<a href="https://confucius.youdao.com">💬DEMO</a>
|
||||
|
||||
<a href="https://github.com/netease-youdao/Confucius3-Math">🌟Github</a>
|
||||
|
||||
<a href="https://github.com/netease-youdao/Confucius3-Math/blob/main/Confucius3-Math.pdf">🎓Paper</a>
|
||||
|
||||
</div>
|
||||
|
||||
**Confucius3-Math** is a 14B parameter open-source resoning LLM developed by the NetEase Youdao AI Team, specifically optimized for K-12 mathematics education. Unlike general-purpose models, Confucius3-Math:
|
||||
- ✅ SOTA Performance on Math Tasks
|
||||
Outperforms larger models on Chinese K-12 math problems through specialized RL training
|
||||
- ✅ Cost-Effective Deployment
|
||||
Runs efficiently on a single consumer-grade GPU (e.g., RTX 4090D)
|
||||
- ✅ Cultural & Curriculum Alignment
|
||||
Optimized for China's national mathematics standards and problem-solving methodologies
|
||||
|
||||
Confucius3-Math was developed through an RL-only post-training process with novel data scheduling policy and improved group-relative advantage estimator. Please refer to our technical report for details.
|
||||
<p></p>
|
||||
<p align="center">
|
||||
<img width="85%" src="figures/benchmark.png">
|
||||
</p>
|
||||
|
||||
## Evaluation Results
|
||||
|
||||
<div align="center">
|
||||
|
||||
|
||||
| Benchmark | DeepSeek-R1 | Qwen3-14B | QwQ-32B | DeepSeek-R1-Distill-Qwen-14B | Confucius3-Math |
|
||||
|-------------------|----------------------|------------|--------------|----------------|------------|
|
||||
| CK12-MATH | 92.74 | 94.04 | 93.60 | 82.86 | **96.24** |
|
||||
| GAOKAO-Bench (math) | 93.27 | 94.44 | 94.93 | 86.75 | **98.46** |
|
||||
| MathBench (K12) | 89.99 | 96.51 | **96.57** | 88.40 | 95.10 |
|
||||
| CMATH | 95.81 | 95.90 | 95.95 | 77.41 | **96.13** |
|
||||
| MATH-500 | 97.30 | 96.80 | 98.00 | 93.90 | **98.80** |
|
||||
| AIME 2024 | 79.80 | 79.30 | 79.50 | 69.70 | **81.15** |
|
||||
| AIME 2025 | 70.00 | **70.40** | 69.50 | 42.97 | 69.95 |
|
||||
|
||||
</div>
|
||||
|
||||
|
||||
|
||||
## Limitations
|
||||
|
||||
However, there are some limitations that must be stated in advance:
|
||||
1. **Scenario Limitations**: Our optimization is only carried out on data from the K12 mathematics scenario, and the effectiveness has only been verified in math-related benchmark tests. The performance of the model in non-mathematical scenarios has not been tested, so we cannot guarantee its quality and effectiveness in other fields.
|
||||
2. **Invalid Results**: The model may sometimes fall into circular reasoning. Since we use explicit identifiers to divide the thinking and summary parts, when the model enters this mode, it may generate invalid results that cannot be parsed.
|
||||
3. **Safety and Ethics**: This model has not undergone optimization and testing for alignment at the safety and ethical levels. Any output generated by the model does not represent the official positions, views, or attitudes of our company. When using this model, users should independently judge and evaluate the rationality and applicability of the output content and comply with relevant laws, regulations, and social ethics.
|
||||
|
||||
## Quickstart
|
||||
The environmental requirements for running it are exactly the same as those of the [Qwen2.5-14B-Instruct](https://huggingface.co/Qwen/Qwen2.5-14B-Instruct) model. Therefore, you can easily use Transformers or vLLM to load and run the model for inference, and deploy your services.
|
||||
|
||||
The only thing you need to pay attention to is to use the predefined system message and user message templates provided below to request the model. Other templates may also be usable, but we haven't tested them yet.
|
||||
```python
|
||||
SYSTEM_PROMPT_TEMPLATE = """A conversation between User and Assistant. The user asks a question, and the Assistant solves it. The assistant first thinks about the reasoning process in the mind and then provides the user with the answer. The reasoning process and answer are enclosed within <think> </think> and <answer> </answer> tags, respectively, i.e., <think> reasoning process here </think> <answer> answer here </answer>."""
|
||||
|
||||
USER_PROMPT_TEMPLATE = """{question}"""
|
||||
```
|
||||
|
||||
Then you can create your `messages` as follows and use them to request model results. You just need to fill in your instructions in the "question" field.
|
||||
```python
|
||||
from transformers import AutoModelForCausalLM, AutoTokenizer
|
||||
|
||||
model_name = "netease-youdao/Confucius3-Math"
|
||||
|
||||
model = AutoModelForCausalLM.from_pretrained(
|
||||
model_name,
|
||||
torch_dtype="auto",
|
||||
device_map="auto"
|
||||
)
|
||||
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
||||
|
||||
messages = [
|
||||
{'role': 'system', 'content': SYSTEM_PROMPT_TEMPLATE},
|
||||
{'role': 'user', 'content': USER_PROMPT_TEMPLATE.format(question=question)},
|
||||
]
|
||||
|
||||
text = tokenizer.apply_chat_template(
|
||||
messages,
|
||||
tokenize=False,
|
||||
add_generation_prompt=True
|
||||
)
|
||||
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
|
||||
|
||||
generated_ids = model.generate(
|
||||
**model_inputs,
|
||||
max_new_tokens=32768
|
||||
)
|
||||
generated_ids = [
|
||||
output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
|
||||
]
|
||||
|
||||
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
|
||||
```
|
||||
> [!NOTE]
|
||||
> **Generate Parameters**: We suggest using Temperature=1.0, TopP=0.7 to sample.
|
||||
|
||||
After obtaining the model results, you can parse out the "thinking" and "summary" parts as follows.
|
||||
```python
|
||||
def parse_result_nostep(result):
|
||||
think_pattern = r"<think>(.*?)</think>(.*)"
|
||||
|
||||
think_list = re.findall(think_pattern, result, re.DOTALL)
|
||||
|
||||
assert len(think_list) == 1, \
|
||||
f"The parsing results do not meet the expectations.\n{result}"
|
||||
|
||||
think = think_list[0][0].strip()
|
||||
summary = think_list[0][1].strip()
|
||||
return think, summary
|
||||
|
||||
thinking, summary = parse_result_nostep(response)
|
||||
```
|
||||
|
||||
## Citation
|
||||
If you find our work helpful, feel free to give us a cite.
|
||||
```
|
||||
@misc{confucius3-math,
|
||||
author = {NetEase Youdao Team},
|
||||
title = {Confucius3-Math: A Lightweight High-Performance Reasoning LLM for Chinese K-12 Mathematics Learning},
|
||||
url = {https://arxiv.org/abs/2506.18330},
|
||||
month = {June},
|
||||
year = {2025}
|
||||
}
|
||||
```
|
||||
31
config.json
Normal file
31
config.json
Normal file
@@ -0,0 +1,31 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Qwen2ForCausalLM"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 151646,
|
||||
"embd_pdrop": 0.0,
|
||||
"eos_token_id": 151643,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 5120,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 13824,
|
||||
"max_position_embeddings": 131072,
|
||||
"max_window_layers": 48,
|
||||
"model_type": "qwen2",
|
||||
"num_attention_heads": 40,
|
||||
"num_hidden_layers": 48,
|
||||
"num_key_value_heads": 8,
|
||||
"pad_token_id": 151643,
|
||||
"resid_pdrop": 0.0,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 1000000.0,
|
||||
"sliding_window": 131072,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.49.0",
|
||||
"use_cache": true,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 152064
|
||||
}
|
||||
1
configuration.json
Normal file
1
configuration.json
Normal file
@@ -0,0 +1 @@
|
||||
{"framework":"Pytorch","task":"text-generation"}
|
||||
BIN
figures/benchmark.png
Normal file
BIN
figures/benchmark.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 119 KiB |
BIN
figures/confucius_logo.png
Normal file
BIN
figures/confucius_logo.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 17 KiB |
7
generation_config.json
Normal file
7
generation_config.json
Normal file
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 151646,
|
||||
"eos_token_id": 151643,
|
||||
"pad_token_id": 151643,
|
||||
"transformers_version": "4.49.0"
|
||||
}
|
||||
3
model-00001-of-00008.safetensors
Normal file
3
model-00001-of-00008.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:110a79367a6bf5a5151978df38707babdffb99de08070a13cc4f7a04a6008cab
|
||||
size 3885134104
|
||||
3
model-00002-of-00008.safetensors
Normal file
3
model-00002-of-00008.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:6492da696410ace789203e40c32c30fc9b6ad27e28c62f5464fbde125ae15672
|
||||
size 3995327992
|
||||
3
model-00003-of-00008.safetensors
Normal file
3
model-00003-of-00008.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:f284b068a6de79741c8533a32ca1deae96d273eb29bd288673aa3d18b60e3870
|
||||
size 3995328064
|
||||
3
model-00004-of-00008.safetensors
Normal file
3
model-00004-of-00008.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a03745ce9656e348704474ea26e0a3c0e7050fc1c4ae9ccadc563b26e5a73586
|
||||
size 3995348776
|
||||
3
model-00005-of-00008.safetensors
Normal file
3
model-00005-of-00008.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:fe629946866f50124f70a71d41206c65423ad31fd87bb84ec6a57d66cbf4e5c2
|
||||
size 3979614448
|
||||
3
model-00006-of-00008.safetensors
Normal file
3
model-00006-of-00008.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:6ce26d77f1735b2d085ca1c215c663f8899fa9dd3a0d62f38034d3eb3cf69800
|
||||
size 3995328064
|
||||
3
model-00007-of-00008.safetensors
Normal file
3
model-00007-of-00008.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:773be7369520d4454e320e312f58676fbe699d8585c7708d0a5e79050a68c25d
|
||||
size 3995328064
|
||||
3
model-00008-of-00008.safetensors
Normal file
3
model-00008-of-00008.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c422e5a47e0f3d1ea3b9dfd860bcb0d1db559c722fcf10e880d5c5f4ed924fae
|
||||
size 1698724408
|
||||
586
model.safetensors.index.json
Normal file
586
model.safetensors.index.json
Normal file
@@ -0,0 +1,586 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 29540067328
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00008-of-00008.safetensors",
|
||||
"model.embed_tokens.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00008.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00008.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00008.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00008.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00008.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00008.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.bias": "model-00002-of-00008.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.bias": "model-00002-of-00008.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.bias": "model-00002-of-00008.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.bias": "model-00002-of-00008.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.bias": "model-00002-of-00008.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.bias": "model-00002-of-00008.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.bias": "model-00003-of-00008.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.bias": "model-00003-of-00008.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.bias": "model-00003-of-00008.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.bias": "model-00003-of-00008.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.bias": "model-00003-of-00008.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.bias": "model-00003-of-00008.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.bias": "model-00003-of-00008.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.bias": "model-00003-of-00008.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.bias": "model-00003-of-00008.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.bias": "model-00003-of-00008.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.bias": "model-00003-of-00008.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.bias": "model-00003-of-00008.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.bias": "model-00003-of-00008.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.bias": "model-00003-of-00008.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.bias": "model-00003-of-00008.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.bias": "model-00003-of-00008.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.bias": "model-00003-of-00008.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.bias": "model-00003-of-00008.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.bias": "model-00003-of-00008.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.bias": "model-00003-of-00008.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.bias": "model-00003-of-00008.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.bias": "model-00004-of-00008.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.bias": "model-00004-of-00008.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.bias": "model-00004-of-00008.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00008.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-00008.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-00008.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.bias": "model-00004-of-00008.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.bias": "model-00004-of-00008.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.bias": "model-00004-of-00008.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.bias": "model-00004-of-00008.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.bias": "model-00004-of-00008.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.bias": "model-00004-of-00008.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.bias": "model-00004-of-00008.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.bias": "model-00004-of-00008.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.bias": "model-00004-of-00008.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.bias": "model-00004-of-00008.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.bias": "model-00004-of-00008.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.bias": "model-00004-of-00008.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.bias": "model-00004-of-00008.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.bias": "model-00004-of-00008.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.bias": "model-00004-of-00008.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.bias": "model-00004-of-00008.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.bias": "model-00004-of-00008.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.bias": "model-00004-of-00008.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.bias": "model-00005-of-00008.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.bias": "model-00005-of-00008.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.bias": "model-00005-of-00008.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.bias": "model-00005-of-00008.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.bias": "model-00005-of-00008.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.bias": "model-00005-of-00008.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.bias": "model-00005-of-00008.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.bias": "model-00005-of-00008.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.bias": "model-00005-of-00008.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.bias": "model-00005-of-00008.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.bias": "model-00005-of-00008.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.bias": "model-00005-of-00008.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.bias": "model-00001-of-00008.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.bias": "model-00001-of-00008.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.bias": "model-00001-of-00008.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.bias": "model-00005-of-00008.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.bias": "model-00005-of-00008.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.bias": "model-00005-of-00008.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.bias": "model-00005-of-00008.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.bias": "model-00005-of-00008.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.bias": "model-00005-of-00008.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.32.input_layernorm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.32.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.32.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.32.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.32.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.32.self_attn.k_proj.bias": "model-00005-of-00008.safetensors",
|
||||
"model.layers.32.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.32.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.bias": "model-00005-of-00008.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.bias": "model-00005-of-00008.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.33.input_layernorm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.33.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.33.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.33.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.33.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.33.self_attn.k_proj.bias": "model-00005-of-00008.safetensors",
|
||||
"model.layers.33.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.33.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.33.self_attn.q_proj.bias": "model-00005-of-00008.safetensors",
|
||||
"model.layers.33.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.33.self_attn.v_proj.bias": "model-00005-of-00008.safetensors",
|
||||
"model.layers.33.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.34.input_layernorm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.34.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.34.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.34.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.34.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.34.self_attn.k_proj.bias": "model-00006-of-00008.safetensors",
|
||||
"model.layers.34.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.34.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.34.self_attn.q_proj.bias": "model-00006-of-00008.safetensors",
|
||||
"model.layers.34.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.34.self_attn.v_proj.bias": "model-00006-of-00008.safetensors",
|
||||
"model.layers.34.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.35.input_layernorm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.35.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.35.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.35.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.35.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.35.self_attn.k_proj.bias": "model-00006-of-00008.safetensors",
|
||||
"model.layers.35.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.35.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.35.self_attn.q_proj.bias": "model-00006-of-00008.safetensors",
|
||||
"model.layers.35.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.35.self_attn.v_proj.bias": "model-00006-of-00008.safetensors",
|
||||
"model.layers.35.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.36.input_layernorm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.36.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.36.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.36.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.36.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.36.self_attn.k_proj.bias": "model-00006-of-00008.safetensors",
|
||||
"model.layers.36.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.36.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.36.self_attn.q_proj.bias": "model-00006-of-00008.safetensors",
|
||||
"model.layers.36.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.36.self_attn.v_proj.bias": "model-00006-of-00008.safetensors",
|
||||
"model.layers.36.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.37.input_layernorm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.37.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.37.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.37.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.37.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.37.self_attn.k_proj.bias": "model-00006-of-00008.safetensors",
|
||||
"model.layers.37.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.37.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.37.self_attn.q_proj.bias": "model-00006-of-00008.safetensors",
|
||||
"model.layers.37.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.37.self_attn.v_proj.bias": "model-00006-of-00008.safetensors",
|
||||
"model.layers.37.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.38.input_layernorm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.38.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.38.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.38.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.38.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.38.self_attn.k_proj.bias": "model-00006-of-00008.safetensors",
|
||||
"model.layers.38.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.38.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.38.self_attn.q_proj.bias": "model-00006-of-00008.safetensors",
|
||||
"model.layers.38.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.38.self_attn.v_proj.bias": "model-00006-of-00008.safetensors",
|
||||
"model.layers.38.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.39.input_layernorm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.39.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.39.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.39.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.39.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.39.self_attn.k_proj.bias": "model-00006-of-00008.safetensors",
|
||||
"model.layers.39.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.39.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.39.self_attn.q_proj.bias": "model-00006-of-00008.safetensors",
|
||||
"model.layers.39.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.39.self_attn.v_proj.bias": "model-00006-of-00008.safetensors",
|
||||
"model.layers.39.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.bias": "model-00001-of-00008.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.bias": "model-00001-of-00008.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.bias": "model-00001-of-00008.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.40.input_layernorm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.40.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.40.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.40.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.40.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.40.self_attn.k_proj.bias": "model-00006-of-00008.safetensors",
|
||||
"model.layers.40.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.40.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.40.self_attn.q_proj.bias": "model-00006-of-00008.safetensors",
|
||||
"model.layers.40.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.40.self_attn.v_proj.bias": "model-00006-of-00008.safetensors",
|
||||
"model.layers.40.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.41.input_layernorm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.41.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.41.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.41.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.41.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.41.self_attn.k_proj.bias": "model-00007-of-00008.safetensors",
|
||||
"model.layers.41.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.41.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.41.self_attn.q_proj.bias": "model-00007-of-00008.safetensors",
|
||||
"model.layers.41.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.41.self_attn.v_proj.bias": "model-00007-of-00008.safetensors",
|
||||
"model.layers.41.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.42.input_layernorm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.42.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.42.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.42.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.42.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.42.self_attn.k_proj.bias": "model-00007-of-00008.safetensors",
|
||||
"model.layers.42.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.42.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.42.self_attn.q_proj.bias": "model-00007-of-00008.safetensors",
|
||||
"model.layers.42.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.42.self_attn.v_proj.bias": "model-00007-of-00008.safetensors",
|
||||
"model.layers.42.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.43.input_layernorm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.43.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.43.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.43.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.43.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.43.self_attn.k_proj.bias": "model-00007-of-00008.safetensors",
|
||||
"model.layers.43.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.43.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.43.self_attn.q_proj.bias": "model-00007-of-00008.safetensors",
|
||||
"model.layers.43.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.43.self_attn.v_proj.bias": "model-00007-of-00008.safetensors",
|
||||
"model.layers.43.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.44.input_layernorm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.44.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.44.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.44.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.44.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.44.self_attn.k_proj.bias": "model-00007-of-00008.safetensors",
|
||||
"model.layers.44.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.44.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.44.self_attn.q_proj.bias": "model-00007-of-00008.safetensors",
|
||||
"model.layers.44.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.44.self_attn.v_proj.bias": "model-00007-of-00008.safetensors",
|
||||
"model.layers.44.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.45.input_layernorm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.45.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.45.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.45.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.45.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.45.self_attn.k_proj.bias": "model-00007-of-00008.safetensors",
|
||||
"model.layers.45.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.45.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.45.self_attn.q_proj.bias": "model-00007-of-00008.safetensors",
|
||||
"model.layers.45.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.45.self_attn.v_proj.bias": "model-00007-of-00008.safetensors",
|
||||
"model.layers.45.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.46.input_layernorm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.46.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.46.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.46.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.46.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.46.self_attn.k_proj.bias": "model-00007-of-00008.safetensors",
|
||||
"model.layers.46.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.46.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.46.self_attn.q_proj.bias": "model-00007-of-00008.safetensors",
|
||||
"model.layers.46.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.46.self_attn.v_proj.bias": "model-00007-of-00008.safetensors",
|
||||
"model.layers.46.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.47.input_layernorm.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.47.mlp.down_proj.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.47.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.47.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.47.post_attention_layernorm.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.47.self_attn.k_proj.bias": "model-00007-of-00008.safetensors",
|
||||
"model.layers.47.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.47.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.47.self_attn.q_proj.bias": "model-00007-of-00008.safetensors",
|
||||
"model.layers.47.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.47.self_attn.v_proj.bias": "model-00007-of-00008.safetensors",
|
||||
"model.layers.47.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.bias": "model-00002-of-00008.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.bias": "model-00002-of-00008.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.bias": "model-00002-of-00008.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.bias": "model-00002-of-00008.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.bias": "model-00002-of-00008.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.bias": "model-00002-of-00008.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.bias": "model-00002-of-00008.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.bias": "model-00002-of-00008.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.bias": "model-00002-of-00008.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.bias": "model-00002-of-00008.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.bias": "model-00002-of-00008.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.bias": "model-00002-of-00008.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.bias": "model-00002-of-00008.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.bias": "model-00002-of-00008.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.bias": "model-00002-of-00008.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.norm.weight": "model-00008-of-00008.safetensors"
|
||||
}
|
||||
}
|
||||
23
special_tokens_map.json
Normal file
23
special_tokens_map.json
Normal file
@@ -0,0 +1,23 @@
|
||||
{
|
||||
"bos_token": {
|
||||
"content": "<｜begin▁of▁sentence｜>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "<｜end▁of▁sentence｜>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<｜end▁of▁sentence｜>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893
|
||||
size 11422778
|
||||
195
tokenizer_config.json
Normal file
195
tokenizer_config.json
Normal file
@@ -0,0 +1,195 @@
|
||||
{
|
||||
"add_bos_token": true,
|
||||
"add_eos_token": false,
|
||||
"add_prefix_space": null,
|
||||
"added_tokens_decoder": {
|
||||
"151643": {
|
||||
"content": "<｜end▁of▁sentence｜>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151644": {
|
||||
"content": "<｜User｜>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151645": {
|
||||
"content": "<｜Assistant｜>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151646": {
|
||||
"content": "<｜begin▁of▁sentence｜>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151647": {
|
||||
"content": "<|EOT|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151648": {
|
||||
"content": "<think>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151649": {
|
||||
"content": "</think>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151650": {
|
||||
"content": "<|quad_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151651": {
|
||||
"content": "<|quad_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151652": {
|
||||
"content": "<|vision_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151653": {
|
||||
"content": "<|vision_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151654": {
|
||||
"content": "<|vision_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151655": {
|
||||
"content": "<|image_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151656": {
|
||||
"content": "<|video_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151657": {
|
||||
"content": "<tool_call>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151658": {
|
||||
"content": "</tool_call>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151659": {
|
||||
"content": "<|fim_prefix|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151660": {
|
||||
"content": "<|fim_middle|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151661": {
|
||||
"content": "<|fim_suffix|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151662": {
|
||||
"content": "<|fim_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151663": {
|
||||
"content": "<|repo_name|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151664": {
|
||||
"content": "<|file_sep|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
}
|
||||
},
|
||||
"bos_token": "<｜begin▁of▁sentence｜>",
|
||||
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜>'}}{% endif %}",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<｜end▁of▁sentence｜>",
|
||||
"extra_special_tokens": {},
|
||||
"legacy": true,
|
||||
"model_max_length": 16384,
|
||||
"pad_token": "<｜end▁of▁sentence｜>",
|
||||
"sp_model_kwargs": {},
|
||||
"tokenizer_class": "LlamaTokenizerFast",
|
||||
"unk_token": null,
|
||||
"use_default_system_prompt": false
|
||||
}
|
||||
Reference in New Issue
Block a user