初始化项目，由ModelHub XC社区提供模型
Model: gaotang/RM-R1-DeepSeek-Distilled-Qwen-14B 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
|
||||
115
README.md
Normal file
115
README.md
Normal file
@@ -0,0 +1,115 @@
|
||||
---
|
||||
base_model:
|
||||
- deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
|
||||
language:
|
||||
- en
|
||||
license: mit
|
||||
pipeline_tag: text-generation
|
||||
library_name: transformers
|
||||
---
|
||||
|
||||
|
||||
|
||||
<font size=3><div align='center' >
|
||||
[[**🤗 Model & Dataset**](https://huggingface.co/collections/gaotang/rm-r1-681128cdab932701cad844c8)]
|
||||
[[**📊 Code**](https://github.com/RM-R1-UIUC/RM-R1)]
|
||||
[[**📖 Paper**](https://arxiv.org/abs/2505.02387)]
|
||||
</div></font>
|
||||
|
||||
# 🚀 Can we cast reward modeling as a reasoning task?
|
||||
|
||||
**RM-R1** is a training framework for *Reasoning Reward Model* (ReasRM) that judges two candidate answers by first **thinking out loud**—generating structured rubrics or reasoning traces—then emitting its preference. Compared to traditional scalar or generative reward models, RM-R1 delivers **state-of-the-art performance** on public RM benchmarks on average while offering fully interpretable justifications.
|
||||
|
||||
|
||||
## 🧠 TL;DR
|
||||
* **Two-stage training**
|
||||
1. **Distillation** of ~8.7 K high-quality reasoning traces (Chain-of-Rubrics).
|
||||
2. **Reinforcement Learning with Verifiable Rewards** (RLVR) on ~64 K preference pairs.
|
||||
|
||||
* **Backbones** released: 7 B / 14 B / 32 B Qwen-2.5-Instruct variants + DeepSeek-distilled checkpoints.
|
||||
|
||||
## 💡 Intended uses
|
||||
* **RLHF / RLAIF**: plug-and-play reward function for policy optimisation.
|
||||
* **Automated evaluation**: LLM-as-a-judge for open-domain QA, chat, and reasoning.
|
||||
* **Research**: study process supervision, chain-of-thought verification, or rubric generation.
|
||||
|
||||
## 🔍 Demo Code
|
||||
|
||||
Try the model with this example. Full demo notebook available at:
|
||||
|
||||
📎 [Official Demo Link](https://github.com/RM-R1-UIUC/RM-R1/blob/main/demo/demo.ipynb)
|
||||
|
||||
### 🧾 Prompt Template
|
||||
|
||||
```python
|
||||
REASONING_SINGLE_PROMPT_TEMPLATE = (
|
||||
"Please act as an impartial judge and evaluate the quality of the responses provided by two AI Chatbots to the Client question displayed below. \n\n"
|
||||
"[Client Question]\n{question}\n\n[The Start of Chatbot A's Response]\n{answer_a}\n[The End of Chatbot A's Response]\n\n"
|
||||
"[The Start of Chatbot B's Response]\n{answer_b}\n[The End of Chatbot B's Response]" + "\n\n"
|
||||
"Output your final verdict at last by strictly following this format: "
|
||||
"'<answer>[[A]]</answer>' if Chatbot A is better, or '<answer>[[B]]</answer>' if Chatbot B is better."
|
||||
)
|
||||
```
|
||||
|
||||
### 📦 Inference Code
|
||||
|
||||
```python
|
||||
# Load the Model
|
||||
import torch
|
||||
from transformers import AutoModelForCausalLM, AutoTokenizer
|
||||
|
||||
model_name = "gaotang/RM-R1-DeepSeek-Distilled-Qwen-14B"
|
||||
model = AutoModelForCausalLM.from_pretrained(
|
||||
model_name,
|
||||
torch_dtype="auto",
|
||||
device_map="auto" # or specify the specific device map if needed
|
||||
)
|
||||
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
||||
|
||||
# Single Turn Example - from Reward Bench
|
||||
|
||||
prompt = "How do I detail a car?"
|
||||
answer_a = "Detailing a car involves a thorough cleaning inside and out, as well as polishing and waxing to protect the vehicle's surfaces. Here's a step-by-step guide to detailing a car:\n\n**Exterior Detailing:**\n\n1. **Wash the Car:**\n - Rinse the car with water to remove loose dirt.\n - Use a car wash soap and microfiber wash mitt to clean the car from top to bottom.\n - Clean the wheels and tires with a brush and a wheel cleaner.\n - Rinse the car thoroughly to remove all soap.\n\n2. **Dry the Car:**\n - Use a microfiber towel or a chamois to dry the car to prevent water spots.\n\n3. **Clay Bar Treatment:**\n - Use a clay bar with a lubricant to remove embedded surface contaminants from the paint.\n\n4. **Polishing:**\n - Apply car polish with a dual-action polisher or by hand to correct paint imperfections and create a smooth surface.\n\n5. **Waxing:**\n - Apply a coat of wax or paint sealant to protect the paint and give it a glossy finish.\n\n6. **Windows and Mirrors:**\n - Clean the windows and mirrors with a glass cleaner and a microfiber towel.\n\n7. **Tire and Trim Dressing:**\n - Apply a tire dressing to the tires for a shiny finish.\n - Use a trim restorer or protectant on plastic and rubber parts to prevent fading.\n\n**Interior Detailing:**\n\n1. **Remove Trash:**\n - Clear out any trash and remove personal items from the car.\n\n2. **Vacuum:**\n - Vacuum the seats, carpets, floor mats, and trunk.\n - Use a brush attachment for the dashboard and door panels.\n\n3. **Shampoo Carpets and Upholstery:**\n - Use a carpet cleaner and a brush to clean the carpets and upholstery.\n - For leather interiors, use a leather cleaner and conditioner.\n\n4. **Clean Hard Surfaces:**\n - Wipe down all hard surfaces (dashboard, center console, door panels, etc.) with a mild all-purpose cleaner and a microfiber cloth.\n\n5. **Windows and Mirrors:**\n - Clean the interior side of windows and mirrors.\n\n6. **Air Vents and Crevices:**\n - Use a detailing brush or compressed air to clean out air vents and hard-to-reach crevices.\n\n7. **Final Touches:**\n - Apply a protectant to the dashboard and other plastic components.\n - Replace air fresheners if needed.\n\n**Additional Tips:**\n\n- Work in the shade or a cool, well-ventilated garage to prevent products from drying too quickly and leaving residue.\n- Use separate buckets for washing and rinsing to avoid contaminating the clean water with dirt.\n- Always use gentle, non-abrasive materials and cleaners specifically designed for automotive use to avoid damaging surfaces.\n- Move in a systematic way to ensure you don't miss any spots.\n\nBy following these steps, you'll give your car a thorough clean that not only makes it look great but also helps in maintaining its value. Remember, regular detailing can prevent wear and tear and keep your car looking new for years to come." # Accepted
|
||||
answer_b = "Detailing a car involves washing the exterior and interior of the car, as well as polishing and waxing the exterior. Interior detailing typically involves vacuuming, cleaning the upholstery and air vents, polishing the dashboard and console, and dusting. Polishing and waxing the exterior will depend on the condition of the paint, but typically involves applying a polish and wax to make it shine." # Rejected
|
||||
|
||||
user_prompt_single = REASONING_SINGLE_PROMPT_TEMPLATE.format(
|
||||
question=prompt,
|
||||
answer_a=answer_a,
|
||||
answer_b=answer_b
|
||||
)
|
||||
|
||||
conversation = [
|
||||
{"role":"user", "content": user_prompt_single}
|
||||
]
|
||||
|
||||
input_ids = tokenizer.apply_chat_template(
|
||||
conversation,
|
||||
tokenize=True,
|
||||
add_generation_prompt=True,
|
||||
return_tensors="pt").to(model.device)
|
||||
|
||||
generation = model.generate(
|
||||
input_ids=input_ids,
|
||||
max_new_tokens=8192, # For optimal performance benchmarking, please set this to unlimited (e.g., 50000)
|
||||
do_sample=False,
|
||||
)
|
||||
|
||||
completion = tokenizer.decode(
|
||||
generation[0][len(input_ids[0]):],
|
||||
skip_special_tokens=True,
|
||||
clean_up_tokenization_spaces=True
|
||||
)
|
||||
|
||||
print(completion)
|
||||
```
|
||||
|
||||
## Citations
|
||||
|
||||
```bibtex
|
||||
@article{chen2025rm,
|
||||
title={RM-R1: Reward Modeling as Reasoning},
|
||||
author={Chen, Xiusi and Li, Gaotang and Wang, Ziqi and Jin, Bowen and Qian, Cheng and Wang, Yu and Wang, Hongru and Zhang, Yu and Zhang, Denghui and Zhang, Tong and others},
|
||||
journal={arXiv preprint arXiv:2505.02387},
|
||||
year={2025}
|
||||
}
|
||||
```
|
||||
29
config.json
Normal file
29
config.json
Normal file
@@ -0,0 +1,29 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Qwen2ForCausalLM"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 151646,
|
||||
"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,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 1000000.0,
|
||||
"sliding_window": 131072,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.50.3",
|
||||
"use_cache": true,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 152064
|
||||
}
|
||||
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": "4.50.3"
|
||||
}
|
||||
3
model-00001-of-00007.safetensors
Normal file
3
model-00001-of-00007.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:f1903145ff414e54ab01634db76b2c005b6c8ba60030f6d5c2ab54cc255864a2
|
||||
size 4991453648
|
||||
3
model-00002-of-00007.safetensors
Normal file
3
model-00002-of-00007.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:2337ff6aca57d8dde99ac3f27c088ea3e8f1b646c92abdc264224e844d166a37
|
||||
size 4954858776
|
||||
3
model-00003-of-00007.safetensors
Normal file
3
model-00003-of-00007.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:1abb0a5e1087ec5442fe2fbeea7bec54cbbebecd33cc0b2de06157d6e7c64ec6
|
||||
size 3533992024
|
||||
3
model-00004-of-00007.safetensors
Normal file
3
model-00004-of-00007.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:4f32c85ae7b9bb7257a1ce2497536aae7462eb9333d3f686ca22c79127031496
|
||||
size 4918009016
|
||||
3
model-00005-of-00007.safetensors
Normal file
3
model-00005-of-00007.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c35943c0a1beae3b3c2ff48a41ecfec097abdecc90e3044eef761d6d24bc5ac8
|
||||
size 4923383256
|
||||
3
model-00006-of-00007.safetensors
Normal file
3
model-00006-of-00007.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:4d65c5c349e61c5f648f1e84c685ac3ceddd4c1d6d958984d60fe2361968e379
|
||||
size 4991507488
|
||||
3
model-00007-of-00007.safetensors
Normal file
3
model-00007-of-00007.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:fb41258d5d40d6413246753f9fb53d557269c6595ccc7efa92ade1ea4722acca
|
||||
size 1226929640
|
||||
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-00004-of-00007.safetensors",
|
||||
"model.embed_tokens.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.bias": "model-00007-of-00007.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.bias": "model-00007-of-00007.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.bias": "model-00007-of-00007.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.32.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.32.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.32.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.32.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.32.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.32.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
|
||||
"model.layers.32.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.32.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.33.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.33.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.33.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.33.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.33.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.33.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
|
||||
"model.layers.33.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.33.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.33.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
|
||||
"model.layers.33.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.33.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"model.layers.33.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.34.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.34.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.34.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.34.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.34.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.34.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
|
||||
"model.layers.34.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.34.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.34.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
|
||||
"model.layers.34.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.34.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
|
||||
"model.layers.34.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.35.input_layernorm.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.35.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.35.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.35.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.35.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.35.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"model.layers.35.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.35.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.35.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
|
||||
"model.layers.35.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.35.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
|
||||
"model.layers.35.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.36.input_layernorm.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.36.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.36.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.36.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.36.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.36.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
|
||||
"model.layers.36.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.36.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.36.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
|
||||
"model.layers.36.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.36.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
|
||||
"model.layers.36.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.37.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.37.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.37.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.37.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.37.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.37.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
|
||||
"model.layers.37.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.37.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.37.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
|
||||
"model.layers.37.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.37.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
|
||||
"model.layers.37.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.38.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.38.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.38.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.38.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.38.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.38.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"model.layers.38.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.38.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.38.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
|
||||
"model.layers.38.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.38.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
|
||||
"model.layers.38.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.39.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.39.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.39.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.39.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.39.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.39.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
|
||||
"model.layers.39.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.39.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.39.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
|
||||
"model.layers.39.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.39.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
|
||||
"model.layers.39.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.40.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.40.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.40.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.40.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.40.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.40.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
|
||||
"model.layers.40.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.40.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.40.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
|
||||
"model.layers.40.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.40.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
|
||||
"model.layers.40.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.41.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.41.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.41.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.41.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.41.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.41.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"model.layers.41.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.41.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.41.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
|
||||
"model.layers.41.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.41.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"model.layers.41.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.42.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.42.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.42.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.42.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.42.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.42.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
|
||||
"model.layers.42.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.42.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.42.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
|
||||
"model.layers.42.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.42.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"model.layers.42.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.43.input_layernorm.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.43.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.43.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.43.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.43.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.43.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
|
||||
"model.layers.43.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.43.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.43.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
|
||||
"model.layers.43.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.43.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
|
||||
"model.layers.43.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.44.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.44.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.44.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.44.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.44.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.44.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
|
||||
"model.layers.44.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.44.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.44.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
|
||||
"model.layers.44.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.44.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
|
||||
"model.layers.44.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.45.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.45.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.45.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.45.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.45.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.45.self_attn.k_proj.bias": "model-00007-of-00007.safetensors",
|
||||
"model.layers.45.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.45.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.45.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
|
||||
"model.layers.45.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.45.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
|
||||
"model.layers.45.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.46.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.46.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.46.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.46.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.46.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.46.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
|
||||
"model.layers.46.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.46.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.46.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
|
||||
"model.layers.46.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.46.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
|
||||
"model.layers.46.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.47.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.47.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.47.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.47.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.47.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.47.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
|
||||
"model.layers.47.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.47.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.47.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
|
||||
"model.layers.47.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.47.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
|
||||
"model.layers.47.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.norm.weight": "model-00005-of-00007.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｜><think>\\n'}}{% 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