初始化项目，由ModelHub XC社区提供模型
Model: dongboklee/gPRM-14B-merged 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
|
||||
94
README.md
Normal file
94
README.md
Normal file
@@ -0,0 +1,94 @@
|
||||
---
|
||||
base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
|
||||
library_name: transformers
|
||||
pipeline_tag: text-generation
|
||||
tags:
|
||||
- base_model:adapter:deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
|
||||
- lora
|
||||
- transformers
|
||||
- reward-model
|
||||
license: apache-2.0
|
||||
language:
|
||||
- en
|
||||
---
|
||||
|
||||
# gPRM-14B-merged
|
||||
|
||||
|
||||
This model is a LoRA-merged version of [gPRM-14B](https://huggingface.co/dongboklee/gPRM-14B) for vLLM inference.
|
||||
|
||||
For details:
|
||||
- **Paper:** [Rethinking Reward Models for Multi-Domain Test-Time Scaling](https://huggingface.co/papers/2510.00492)
|
||||
- **Repository:** [https://github.com/db-Lee/Multi-RM](https://github.com/db-Lee/Multi-RM)
|
||||
|
||||
|
||||
### Direct Use
|
||||
```python
|
||||
import math
|
||||
import torch
|
||||
from transformers import AutoModelForCausalLM, AutoTokenizer
|
||||
|
||||
# tokenizer
|
||||
tokenizer = AutoTokenizer.from_pretrained('dongboklee/gPRM-14B-merged')
|
||||
yes_id = tokenizer.encode(" Yes", add_special_tokens=False)[-1]
|
||||
no_id = tokenizer.encode(" No", add_special_tokens=False)[-1]
|
||||
|
||||
# model
|
||||
device = 'cuda' if torch.cuda.is_available() else 'cpu'
|
||||
model = AutoModelForCausalLM.from_pretrained('dongboklee/gPRM-14B-merged')
|
||||
model.eval()
|
||||
model.to(device)
|
||||
|
||||
# prompt formatting
|
||||
question = 'Question: In Python 3, which of the following function convert a string to an int in python?\nA. short(x)\nB. float(x)\nC. integer(x [,base])\nD. double(x)\nE. int(x [,base])\nF. long(x [,base] )\nG. num(x)\nH. str(x)\nI. char(x)\nJ. digit(x [,base])'
|
||||
solution = ["To convert a string to an integer in Python 3, we use the built-in function int().",
|
||||
"The int() function takes two arguments: the string to be converted and an optional base (default is 10, which is for decimal).",
|
||||
"For example: int(\"123\", 10) converts the string \"123\" to the integer 123.",
|
||||
"Looking at the options, we can see that the correct function is option E: int(x [,base]).",
|
||||
"The answer is (E)."]
|
||||
category_name = "computer science"
|
||||
steps = [ f"Step {str(i+1)}: {step}" for i, step in enumerate(solution) ]
|
||||
prefix = "\n".join(steps)
|
||||
|
||||
# Create the prompt
|
||||
prompt_text = (
|
||||
f"You are given a {category_name} problem and a proposed step-by-step solution:\n\n"
|
||||
f"[{category_name.capitalize()} Problem]\n{question}\n\n"
|
||||
f"[Solution]\n{prefix}\n\n"
|
||||
"Review and critique each step in the proposed solution to determine whether each step is correct. If the solution is incomplete, only verify the provided steps."
|
||||
)
|
||||
|
||||
prompt = tokenizer.apply_chat_template(
|
||||
[{'role': "user", "content": prompt_text}],
|
||||
tokenize=False, add_generation_prompt=True, add_special_tokens=False
|
||||
) + "Let's verify step by step:"
|
||||
|
||||
# Tokenize the prompt
|
||||
inputs = tokenizer(prompt, return_tensors="pt").to(device)
|
||||
|
||||
# generate
|
||||
with torch.no_grad():
|
||||
outputs = model.generate(
|
||||
**inputs,
|
||||
max_new_tokens=8192,
|
||||
return_dict_in_generate=True,
|
||||
output_scores=True,
|
||||
pad_token_id=tokenizer.eos_token_id
|
||||
)
|
||||
|
||||
# compute reward
|
||||
logits = outputs.logits[0, -2, :]
|
||||
yes_logit, no_logit = logits[yes_id].item(), logits[no_id].item()
|
||||
reward = math.exp(yes_logit) / (math.exp(yes_logit) + math.exp(no_logit))
|
||||
```
|
||||
|
||||
## Citation
|
||||
|
||||
```
|
||||
@article{multi-rm,
|
||||
title = {Rethinking Reward Models for Multi-Domain Test-Time Scaling},
|
||||
author = {Lee, Dong Bok and Lee, Seanie and Park, Sangwoo and Kang, Minki and Baek, Jinheon and Kim, Dongki and Wagner, Dominik and Jin, Jiongdao and Lee, Heejun and Bocklet, Tobias and Wang, Jinyu and Fu, Jingjing and Hwang, Sung Ju and Bian, Jiang and Song, Lei},
|
||||
journal = {arXiv preprint arXiv:2510.00492},
|
||||
year = {2025}
|
||||
}
|
||||
```
|
||||
10
chat_template.jinja
Normal file
10
chat_template.jinja
Normal file
@@ -0,0 +1,10 @@
|
||||
{% 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'] + '
|
||||
' + '```json' + '
|
||||
' + tool['function']['arguments'] + '
|
||||
' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'
|
||||
' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '
|
||||
' + '```json' + '
|
||||
' + tool['function']['arguments'] + '
|
||||
' + '```' + '<｜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'] %}{{'<｜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 %}{{'
|
||||
<｜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>
|
||||
'}}{% endif %}
|
||||
78
config.json
Normal file
78
config.json
Normal file
@@ -0,0 +1,78 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Qwen2ForCausalLM"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 151643,
|
||||
"eos_token_id": 151643,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 5120,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 13824,
|
||||
"layer_types": [
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention"
|
||||
],
|
||||
"max_position_embeddings": 131072,
|
||||
"max_window_layers": 48,
|
||||
"model_type": "qwen2",
|
||||
"num_attention_heads": 40,
|
||||
"num_hidden_layers": 48,
|
||||
"num_key_value_heads": 8,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 1000000.0,
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "float32",
|
||||
"transformers_version": "4.53.0",
|
||||
"use_cache": true,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 152064
|
||||
}
|
||||
9
generation_config.json
Normal file
9
generation_config.json
Normal file
@@ -0,0 +1,9 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 151646,
|
||||
"do_sample": true,
|
||||
"eos_token_id": 151643,
|
||||
"temperature": 0.6,
|
||||
"top_p": 0.95,
|
||||
"transformers_version": "4.53.0"
|
||||
}
|
||||
3
model-00001-of-00012.safetensors
Normal file
3
model-00001-of-00012.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:263f25fca9c3abbea2f9b4cb837daa2479a0af4e776b30f8d89167525c24da04
|
||||
size 4750149992
|
||||
3
model-00002-of-00012.safetensors
Normal file
3
model-00002-of-00012.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:092fb96cd7a315ac28065c02a07d8622bbd73ac6a61fd101384c6d51a6fe0d93
|
||||
size 4970575640
|
||||
3
model-00003-of-00012.safetensors
Normal file
3
model-00003-of-00012.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:8568d3ad9e4ead1e656e52ae6347d7bb1ec387b7279248fd7379adde2e18c131
|
||||
size 4939106528
|
||||
3
model-00004-of-00012.safetensors
Normal file
3
model-00004-of-00012.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:86026337df22d3523857b552b22476eb4abc8bbf320d3d6947bbfe71a0164ed7
|
||||
size 4970575688
|
||||
3
model-00005-of-00012.safetensors
Normal file
3
model-00005-of-00012.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c5134d16777e40fc08391d352ee407bc91f201e4fb697e286c08231559dcc893
|
||||
size 4939106568
|
||||
3
model-00006-of-00012.safetensors
Normal file
3
model-00006-of-00012.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d8583b4b54e9feaa3fbf9cff74cc88fd5074c22d636a8ed0866e46a38b379842
|
||||
size 4970575688
|
||||
3
model-00007-of-00012.safetensors
Normal file
3
model-00007-of-00012.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:2ee1e81b51981a352a2ce2ecbed5740cc2bd3ec9ba64b4f001bb8d782825384c
|
||||
size 4939106568
|
||||
3
model-00008-of-00012.safetensors
Normal file
3
model-00008-of-00012.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:0e744f596f7fb22ea3bafb2a29162fe0179c3f193315f385ccf307f20ea9e940
|
||||
size 4970575688
|
||||
3
model-00009-of-00012.safetensors
Normal file
3
model-00009-of-00012.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:878933d1416d7bd4828381c29aafd445de3f8ce75cd411c030a41c59618440c6
|
||||
size 4939106568
|
||||
3
model-00010-of-00012.safetensors
Normal file
3
model-00010-of-00012.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:fe2717cd2eca4784d84603bda78d5e96190bb59ed1cdedb10aa07f87e853a8c9
|
||||
size 4970575688
|
||||
3
model-00011-of-00012.safetensors
Normal file
3
model-00011-of-00012.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:8ce52f606957f707161e59c22cbfb2059ea468284607df1f674beced5f79835c
|
||||
size 4939106568
|
||||
3
model-00012-of-00012.safetensors
Normal file
3
model-00012-of-00012.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:470e491c1d31a55d7999f87148e3e11a9d96e71a6f552bd4f34e94a4d897f25d
|
||||
size 4781639680
|
||||
587
model.safetensors.index.json
Normal file
587
model.safetensors.index.json
Normal file
@@ -0,0 +1,587 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_parameters": 14770033664,
|
||||
"total_size": 59080134656
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00012-of-00012.safetensors",
|
||||
"model.embed_tokens.weight": "model-00001-of-00012.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00012.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00012.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00012.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00012.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00012.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00012.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00002-of-00012.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00002-of-00012.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00012.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00002-of-00012.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00002-of-00012.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00012.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00004-of-00012.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00004-of-00012.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00003-of-00012.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00004-of-00012.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00004-of-00012.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.bias": "model-00003-of-00012.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00003-of-00012.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00003-of-00012.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.bias": "model-00003-of-00012.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00003-of-00012.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.bias": "model-00003-of-00012.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00003-of-00012.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00004-of-00012.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00004-of-00012.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00004-of-00012.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00004-of-00012.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00004-of-00012.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.bias": "model-00004-of-00012.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00004-of-00012.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00004-of-00012.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.bias": "model-00004-of-00012.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00004-of-00012.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.bias": "model-00004-of-00012.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00004-of-00012.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00004-of-00012.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00004-of-00012.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00004-of-00012.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00004-of-00012.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00004-of-00012.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.bias": "model-00004-of-00012.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00004-of-00012.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00004-of-00012.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.bias": "model-00004-of-00012.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00004-of-00012.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.bias": "model-00004-of-00012.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00004-of-00012.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00004-of-00012.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00004-of-00012.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00004-of-00012.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00004-of-00012.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00004-of-00012.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.bias": "model-00004-of-00012.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00004-of-00012.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00004-of-00012.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.bias": "model-00004-of-00012.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00004-of-00012.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.bias": "model-00004-of-00012.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00004-of-00012.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00004-of-00012.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00004-of-00012.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00004-of-00012.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00004-of-00012.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00004-of-00012.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.bias": "model-00004-of-00012.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00004-of-00012.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00004-of-00012.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.bias": "model-00004-of-00012.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00004-of-00012.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.bias": "model-00004-of-00012.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00004-of-00012.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00005-of-00012.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00005-of-00012.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00005-of-00012.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00005-of-00012.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00005-of-00012.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.bias": "model-00005-of-00012.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00005-of-00012.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00005-of-00012.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.bias": "model-00005-of-00012.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00005-of-00012.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.bias": "model-00005-of-00012.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00005-of-00012.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00005-of-00012.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00005-of-00012.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00005-of-00012.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00005-of-00012.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00005-of-00012.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.bias": "model-00005-of-00012.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00005-of-00012.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00005-of-00012.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.bias": "model-00005-of-00012.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00005-of-00012.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.bias": "model-00005-of-00012.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00005-of-00012.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00005-of-00012.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00005-of-00012.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00005-of-00012.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00005-of-00012.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00005-of-00012.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.bias": "model-00005-of-00012.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00005-of-00012.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00005-of-00012.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.bias": "model-00005-of-00012.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00005-of-00012.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.bias": "model-00005-of-00012.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00005-of-00012.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00005-of-00012.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00005-of-00012.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00005-of-00012.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00005-of-00012.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00005-of-00012.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.bias": "model-00005-of-00012.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00005-of-00012.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00005-of-00012.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.bias": "model-00005-of-00012.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00005-of-00012.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.bias": "model-00005-of-00012.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00005-of-00012.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00006-of-00012.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00006-of-00012.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00005-of-00012.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00006-of-00012.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00006-of-00012.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.bias": "model-00005-of-00012.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00005-of-00012.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00005-of-00012.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.bias": "model-00005-of-00012.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00005-of-00012.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.bias": "model-00005-of-00012.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00005-of-00012.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00002-of-00012.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00002-of-00012.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00002-of-00012.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00002-of-00012.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00002-of-00012.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.bias": "model-00002-of-00012.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00002-of-00012.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00002-of-00012.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.bias": "model-00002-of-00012.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00002-of-00012.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.bias": "model-00002-of-00012.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00002-of-00012.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00006-of-00012.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00006-of-00012.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00006-of-00012.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00006-of-00012.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00006-of-00012.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.bias": "model-00006-of-00012.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00006-of-00012.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00006-of-00012.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.bias": "model-00006-of-00012.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00006-of-00012.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.bias": "model-00006-of-00012.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00006-of-00012.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00006-of-00012.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00006-of-00012.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00006-of-00012.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00006-of-00012.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00006-of-00012.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.bias": "model-00006-of-00012.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00006-of-00012.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00006-of-00012.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.bias": "model-00006-of-00012.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00006-of-00012.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.bias": "model-00006-of-00012.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00006-of-00012.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00006-of-00012.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00006-of-00012.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00006-of-00012.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00006-of-00012.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00006-of-00012.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.bias": "model-00006-of-00012.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00006-of-00012.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00006-of-00012.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.bias": "model-00006-of-00012.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00006-of-00012.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.bias": "model-00006-of-00012.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00006-of-00012.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00006-of-00012.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00006-of-00012.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00006-of-00012.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00006-of-00012.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00006-of-00012.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.bias": "model-00006-of-00012.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00006-of-00012.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00006-of-00012.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.bias": "model-00006-of-00012.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00006-of-00012.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.bias": "model-00006-of-00012.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00006-of-00012.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00007-of-00012.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00007-of-00012.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00007-of-00012.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00007-of-00012.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00007-of-00012.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.bias": "model-00007-of-00012.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00007-of-00012.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00007-of-00012.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.bias": "model-00007-of-00012.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00007-of-00012.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.bias": "model-00007-of-00012.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00007-of-00012.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00007-of-00012.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00007-of-00012.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00007-of-00012.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00007-of-00012.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00007-of-00012.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.bias": "model-00007-of-00012.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00007-of-00012.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00007-of-00012.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.bias": "model-00007-of-00012.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00007-of-00012.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.bias": "model-00007-of-00012.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00007-of-00012.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00007-of-00012.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00007-of-00012.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00007-of-00012.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00007-of-00012.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00007-of-00012.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.bias": "model-00007-of-00012.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00007-of-00012.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00007-of-00012.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.bias": "model-00007-of-00012.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00007-of-00012.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.bias": "model-00007-of-00012.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00007-of-00012.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00007-of-00012.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00007-of-00012.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00007-of-00012.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00007-of-00012.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00007-of-00012.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.bias": "model-00007-of-00012.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00007-of-00012.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00007-of-00012.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.bias": "model-00007-of-00012.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00007-of-00012.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.bias": "model-00007-of-00012.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00007-of-00012.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00008-of-00012.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00008-of-00012.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00007-of-00012.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00008-of-00012.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00008-of-00012.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.bias": "model-00007-of-00012.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00007-of-00012.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00007-of-00012.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.bias": "model-00007-of-00012.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00007-of-00012.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.bias": "model-00007-of-00012.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00007-of-00012.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00008-of-00012.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00008-of-00012.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00008-of-00012.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00008-of-00012.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00008-of-00012.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.bias": "model-00008-of-00012.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00008-of-00012.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00008-of-00012.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.bias": "model-00008-of-00012.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00008-of-00012.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.bias": "model-00008-of-00012.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00008-of-00012.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00002-of-00012.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00002-of-00012.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00002-of-00012.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00002-of-00012.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00002-of-00012.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.bias": "model-00002-of-00012.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00002-of-00012.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00002-of-00012.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.bias": "model-00002-of-00012.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00002-of-00012.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.bias": "model-00002-of-00012.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00002-of-00012.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00008-of-00012.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00008-of-00012.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model-00008-of-00012.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00008-of-00012.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00008-of-00012.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.bias": "model-00008-of-00012.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00008-of-00012.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00008-of-00012.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.bias": "model-00008-of-00012.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00008-of-00012.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.bias": "model-00008-of-00012.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00008-of-00012.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00008-of-00012.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00008-of-00012.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight": "model-00008-of-00012.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model-00008-of-00012.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00008-of-00012.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.bias": "model-00008-of-00012.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00008-of-00012.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00008-of-00012.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.bias": "model-00008-of-00012.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00008-of-00012.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.bias": "model-00008-of-00012.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00008-of-00012.safetensors",
|
||||
"model.layers.32.input_layernorm.weight": "model-00008-of-00012.safetensors",
|
||||
"model.layers.32.mlp.down_proj.weight": "model-00008-of-00012.safetensors",
|
||||
"model.layers.32.mlp.gate_proj.weight": "model-00008-of-00012.safetensors",
|
||||
"model.layers.32.mlp.up_proj.weight": "model-00008-of-00012.safetensors",
|
||||
"model.layers.32.post_attention_layernorm.weight": "model-00008-of-00012.safetensors",
|
||||
"model.layers.32.self_attn.k_proj.bias": "model-00008-of-00012.safetensors",
|
||||
"model.layers.32.self_attn.k_proj.weight": "model-00008-of-00012.safetensors",
|
||||
"model.layers.32.self_attn.o_proj.weight": "model-00008-of-00012.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.bias": "model-00008-of-00012.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.weight": "model-00008-of-00012.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.bias": "model-00008-of-00012.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.weight": "model-00008-of-00012.safetensors",
|
||||
"model.layers.33.input_layernorm.weight": "model-00009-of-00012.safetensors",
|
||||
"model.layers.33.mlp.down_proj.weight": "model-00009-of-00012.safetensors",
|
||||
"model.layers.33.mlp.gate_proj.weight": "model-00009-of-00012.safetensors",
|
||||
"model.layers.33.mlp.up_proj.weight": "model-00009-of-00012.safetensors",
|
||||
"model.layers.33.post_attention_layernorm.weight": "model-00009-of-00012.safetensors",
|
||||
"model.layers.33.self_attn.k_proj.bias": "model-00009-of-00012.safetensors",
|
||||
"model.layers.33.self_attn.k_proj.weight": "model-00009-of-00012.safetensors",
|
||||
"model.layers.33.self_attn.o_proj.weight": "model-00009-of-00012.safetensors",
|
||||
"model.layers.33.self_attn.q_proj.bias": "model-00009-of-00012.safetensors",
|
||||
"model.layers.33.self_attn.q_proj.weight": "model-00009-of-00012.safetensors",
|
||||
"model.layers.33.self_attn.v_proj.bias": "model-00009-of-00012.safetensors",
|
||||
"model.layers.33.self_attn.v_proj.weight": "model-00009-of-00012.safetensors",
|
||||
"model.layers.34.input_layernorm.weight": "model-00009-of-00012.safetensors",
|
||||
"model.layers.34.mlp.down_proj.weight": "model-00009-of-00012.safetensors",
|
||||
"model.layers.34.mlp.gate_proj.weight": "model-00009-of-00012.safetensors",
|
||||
"model.layers.34.mlp.up_proj.weight": "model-00009-of-00012.safetensors",
|
||||
"model.layers.34.post_attention_layernorm.weight": "model-00009-of-00012.safetensors",
|
||||
"model.layers.34.self_attn.k_proj.bias": "model-00009-of-00012.safetensors",
|
||||
"model.layers.34.self_attn.k_proj.weight": "model-00009-of-00012.safetensors",
|
||||
"model.layers.34.self_attn.o_proj.weight": "model-00009-of-00012.safetensors",
|
||||
"model.layers.34.self_attn.q_proj.bias": "model-00009-of-00012.safetensors",
|
||||
"model.layers.34.self_attn.q_proj.weight": "model-00009-of-00012.safetensors",
|
||||
"model.layers.34.self_attn.v_proj.bias": "model-00009-of-00012.safetensors",
|
||||
"model.layers.34.self_attn.v_proj.weight": "model-00009-of-00012.safetensors",
|
||||
"model.layers.35.input_layernorm.weight": "model-00009-of-00012.safetensors",
|
||||
"model.layers.35.mlp.down_proj.weight": "model-00009-of-00012.safetensors",
|
||||
"model.layers.35.mlp.gate_proj.weight": "model-00009-of-00012.safetensors",
|
||||
"model.layers.35.mlp.up_proj.weight": "model-00009-of-00012.safetensors",
|
||||
"model.layers.35.post_attention_layernorm.weight": "model-00009-of-00012.safetensors",
|
||||
"model.layers.35.self_attn.k_proj.bias": "model-00009-of-00012.safetensors",
|
||||
"model.layers.35.self_attn.k_proj.weight": "model-00009-of-00012.safetensors",
|
||||
"model.layers.35.self_attn.o_proj.weight": "model-00009-of-00012.safetensors",
|
||||
"model.layers.35.self_attn.q_proj.bias": "model-00009-of-00012.safetensors",
|
||||
"model.layers.35.self_attn.q_proj.weight": "model-00009-of-00012.safetensors",
|
||||
"model.layers.35.self_attn.v_proj.bias": "model-00009-of-00012.safetensors",
|
||||
"model.layers.35.self_attn.v_proj.weight": "model-00009-of-00012.safetensors",
|
||||
"model.layers.36.input_layernorm.weight": "model-00009-of-00012.safetensors",
|
||||
"model.layers.36.mlp.down_proj.weight": "model-00009-of-00012.safetensors",
|
||||
"model.layers.36.mlp.gate_proj.weight": "model-00009-of-00012.safetensors",
|
||||
"model.layers.36.mlp.up_proj.weight": "model-00009-of-00012.safetensors",
|
||||
"model.layers.36.post_attention_layernorm.weight": "model-00009-of-00012.safetensors",
|
||||
"model.layers.36.self_attn.k_proj.bias": "model-00009-of-00012.safetensors",
|
||||
"model.layers.36.self_attn.k_proj.weight": "model-00009-of-00012.safetensors",
|
||||
"model.layers.36.self_attn.o_proj.weight": "model-00009-of-00012.safetensors",
|
||||
"model.layers.36.self_attn.q_proj.bias": "model-00009-of-00012.safetensors",
|
||||
"model.layers.36.self_attn.q_proj.weight": "model-00009-of-00012.safetensors",
|
||||
"model.layers.36.self_attn.v_proj.bias": "model-00009-of-00012.safetensors",
|
||||
"model.layers.36.self_attn.v_proj.weight": "model-00009-of-00012.safetensors",
|
||||
"model.layers.37.input_layernorm.weight": "model-00010-of-00012.safetensors",
|
||||
"model.layers.37.mlp.down_proj.weight": "model-00010-of-00012.safetensors",
|
||||
"model.layers.37.mlp.gate_proj.weight": "model-00009-of-00012.safetensors",
|
||||
"model.layers.37.mlp.up_proj.weight": "model-00010-of-00012.safetensors",
|
||||
"model.layers.37.post_attention_layernorm.weight": "model-00010-of-00012.safetensors",
|
||||
"model.layers.37.self_attn.k_proj.bias": "model-00009-of-00012.safetensors",
|
||||
"model.layers.37.self_attn.k_proj.weight": "model-00009-of-00012.safetensors",
|
||||
"model.layers.37.self_attn.o_proj.weight": "model-00009-of-00012.safetensors",
|
||||
"model.layers.37.self_attn.q_proj.bias": "model-00009-of-00012.safetensors",
|
||||
"model.layers.37.self_attn.q_proj.weight": "model-00009-of-00012.safetensors",
|
||||
"model.layers.37.self_attn.v_proj.bias": "model-00009-of-00012.safetensors",
|
||||
"model.layers.37.self_attn.v_proj.weight": "model-00009-of-00012.safetensors",
|
||||
"model.layers.38.input_layernorm.weight": "model-00010-of-00012.safetensors",
|
||||
"model.layers.38.mlp.down_proj.weight": "model-00010-of-00012.safetensors",
|
||||
"model.layers.38.mlp.gate_proj.weight": "model-00010-of-00012.safetensors",
|
||||
"model.layers.38.mlp.up_proj.weight": "model-00010-of-00012.safetensors",
|
||||
"model.layers.38.post_attention_layernorm.weight": "model-00010-of-00012.safetensors",
|
||||
"model.layers.38.self_attn.k_proj.bias": "model-00010-of-00012.safetensors",
|
||||
"model.layers.38.self_attn.k_proj.weight": "model-00010-of-00012.safetensors",
|
||||
"model.layers.38.self_attn.o_proj.weight": "model-00010-of-00012.safetensors",
|
||||
"model.layers.38.self_attn.q_proj.bias": "model-00010-of-00012.safetensors",
|
||||
"model.layers.38.self_attn.q_proj.weight": "model-00010-of-00012.safetensors",
|
||||
"model.layers.38.self_attn.v_proj.bias": "model-00010-of-00012.safetensors",
|
||||
"model.layers.38.self_attn.v_proj.weight": "model-00010-of-00012.safetensors",
|
||||
"model.layers.39.input_layernorm.weight": "model-00010-of-00012.safetensors",
|
||||
"model.layers.39.mlp.down_proj.weight": "model-00010-of-00012.safetensors",
|
||||
"model.layers.39.mlp.gate_proj.weight": "model-00010-of-00012.safetensors",
|
||||
"model.layers.39.mlp.up_proj.weight": "model-00010-of-00012.safetensors",
|
||||
"model.layers.39.post_attention_layernorm.weight": "model-00010-of-00012.safetensors",
|
||||
"model.layers.39.self_attn.k_proj.bias": "model-00010-of-00012.safetensors",
|
||||
"model.layers.39.self_attn.k_proj.weight": "model-00010-of-00012.safetensors",
|
||||
"model.layers.39.self_attn.o_proj.weight": "model-00010-of-00012.safetensors",
|
||||
"model.layers.39.self_attn.q_proj.bias": "model-00010-of-00012.safetensors",
|
||||
"model.layers.39.self_attn.q_proj.weight": "model-00010-of-00012.safetensors",
|
||||
"model.layers.39.self_attn.v_proj.bias": "model-00010-of-00012.safetensors",
|
||||
"model.layers.39.self_attn.v_proj.weight": "model-00010-of-00012.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00002-of-00012.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00002-of-00012.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00002-of-00012.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00002-of-00012.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00002-of-00012.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.bias": "model-00002-of-00012.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00002-of-00012.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00002-of-00012.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.bias": "model-00002-of-00012.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00002-of-00012.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.bias": "model-00002-of-00012.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00002-of-00012.safetensors",
|
||||
"model.layers.40.input_layernorm.weight": "model-00010-of-00012.safetensors",
|
||||
"model.layers.40.mlp.down_proj.weight": "model-00010-of-00012.safetensors",
|
||||
"model.layers.40.mlp.gate_proj.weight": "model-00010-of-00012.safetensors",
|
||||
"model.layers.40.mlp.up_proj.weight": "model-00010-of-00012.safetensors",
|
||||
"model.layers.40.post_attention_layernorm.weight": "model-00010-of-00012.safetensors",
|
||||
"model.layers.40.self_attn.k_proj.bias": "model-00010-of-00012.safetensors",
|
||||
"model.layers.40.self_attn.k_proj.weight": "model-00010-of-00012.safetensors",
|
||||
"model.layers.40.self_attn.o_proj.weight": "model-00010-of-00012.safetensors",
|
||||
"model.layers.40.self_attn.q_proj.bias": "model-00010-of-00012.safetensors",
|
||||
"model.layers.40.self_attn.q_proj.weight": "model-00010-of-00012.safetensors",
|
||||
"model.layers.40.self_attn.v_proj.bias": "model-00010-of-00012.safetensors",
|
||||
"model.layers.40.self_attn.v_proj.weight": "model-00010-of-00012.safetensors",
|
||||
"model.layers.41.input_layernorm.weight": "model-00010-of-00012.safetensors",
|
||||
"model.layers.41.mlp.down_proj.weight": "model-00010-of-00012.safetensors",
|
||||
"model.layers.41.mlp.gate_proj.weight": "model-00010-of-00012.safetensors",
|
||||
"model.layers.41.mlp.up_proj.weight": "model-00010-of-00012.safetensors",
|
||||
"model.layers.41.post_attention_layernorm.weight": "model-00010-of-00012.safetensors",
|
||||
"model.layers.41.self_attn.k_proj.bias": "model-00010-of-00012.safetensors",
|
||||
"model.layers.41.self_attn.k_proj.weight": "model-00010-of-00012.safetensors",
|
||||
"model.layers.41.self_attn.o_proj.weight": "model-00010-of-00012.safetensors",
|
||||
"model.layers.41.self_attn.q_proj.bias": "model-00010-of-00012.safetensors",
|
||||
"model.layers.41.self_attn.q_proj.weight": "model-00010-of-00012.safetensors",
|
||||
"model.layers.41.self_attn.v_proj.bias": "model-00010-of-00012.safetensors",
|
||||
"model.layers.41.self_attn.v_proj.weight": "model-00010-of-00012.safetensors",
|
||||
"model.layers.42.input_layernorm.weight": "model-00011-of-00012.safetensors",
|
||||
"model.layers.42.mlp.down_proj.weight": "model-00011-of-00012.safetensors",
|
||||
"model.layers.42.mlp.gate_proj.weight": "model-00011-of-00012.safetensors",
|
||||
"model.layers.42.mlp.up_proj.weight": "model-00011-of-00012.safetensors",
|
||||
"model.layers.42.post_attention_layernorm.weight": "model-00011-of-00012.safetensors",
|
||||
"model.layers.42.self_attn.k_proj.bias": "model-00011-of-00012.safetensors",
|
||||
"model.layers.42.self_attn.k_proj.weight": "model-00011-of-00012.safetensors",
|
||||
"model.layers.42.self_attn.o_proj.weight": "model-00011-of-00012.safetensors",
|
||||
"model.layers.42.self_attn.q_proj.bias": "model-00011-of-00012.safetensors",
|
||||
"model.layers.42.self_attn.q_proj.weight": "model-00011-of-00012.safetensors",
|
||||
"model.layers.42.self_attn.v_proj.bias": "model-00011-of-00012.safetensors",
|
||||
"model.layers.42.self_attn.v_proj.weight": "model-00011-of-00012.safetensors",
|
||||
"model.layers.43.input_layernorm.weight": "model-00011-of-00012.safetensors",
|
||||
"model.layers.43.mlp.down_proj.weight": "model-00011-of-00012.safetensors",
|
||||
"model.layers.43.mlp.gate_proj.weight": "model-00011-of-00012.safetensors",
|
||||
"model.layers.43.mlp.up_proj.weight": "model-00011-of-00012.safetensors",
|
||||
"model.layers.43.post_attention_layernorm.weight": "model-00011-of-00012.safetensors",
|
||||
"model.layers.43.self_attn.k_proj.bias": "model-00011-of-00012.safetensors",
|
||||
"model.layers.43.self_attn.k_proj.weight": "model-00011-of-00012.safetensors",
|
||||
"model.layers.43.self_attn.o_proj.weight": "model-00011-of-00012.safetensors",
|
||||
"model.layers.43.self_attn.q_proj.bias": "model-00011-of-00012.safetensors",
|
||||
"model.layers.43.self_attn.q_proj.weight": "model-00011-of-00012.safetensors",
|
||||
"model.layers.43.self_attn.v_proj.bias": "model-00011-of-00012.safetensors",
|
||||
"model.layers.43.self_attn.v_proj.weight": "model-00011-of-00012.safetensors",
|
||||
"model.layers.44.input_layernorm.weight": "model-00011-of-00012.safetensors",
|
||||
"model.layers.44.mlp.down_proj.weight": "model-00011-of-00012.safetensors",
|
||||
"model.layers.44.mlp.gate_proj.weight": "model-00011-of-00012.safetensors",
|
||||
"model.layers.44.mlp.up_proj.weight": "model-00011-of-00012.safetensors",
|
||||
"model.layers.44.post_attention_layernorm.weight": "model-00011-of-00012.safetensors",
|
||||
"model.layers.44.self_attn.k_proj.bias": "model-00011-of-00012.safetensors",
|
||||
"model.layers.44.self_attn.k_proj.weight": "model-00011-of-00012.safetensors",
|
||||
"model.layers.44.self_attn.o_proj.weight": "model-00011-of-00012.safetensors",
|
||||
"model.layers.44.self_attn.q_proj.bias": "model-00011-of-00012.safetensors",
|
||||
"model.layers.44.self_attn.q_proj.weight": "model-00011-of-00012.safetensors",
|
||||
"model.layers.44.self_attn.v_proj.bias": "model-00011-of-00012.safetensors",
|
||||
"model.layers.44.self_attn.v_proj.weight": "model-00011-of-00012.safetensors",
|
||||
"model.layers.45.input_layernorm.weight": "model-00011-of-00012.safetensors",
|
||||
"model.layers.45.mlp.down_proj.weight": "model-00011-of-00012.safetensors",
|
||||
"model.layers.45.mlp.gate_proj.weight": "model-00011-of-00012.safetensors",
|
||||
"model.layers.45.mlp.up_proj.weight": "model-00011-of-00012.safetensors",
|
||||
"model.layers.45.post_attention_layernorm.weight": "model-00011-of-00012.safetensors",
|
||||
"model.layers.45.self_attn.k_proj.bias": "model-00011-of-00012.safetensors",
|
||||
"model.layers.45.self_attn.k_proj.weight": "model-00011-of-00012.safetensors",
|
||||
"model.layers.45.self_attn.o_proj.weight": "model-00011-of-00012.safetensors",
|
||||
"model.layers.45.self_attn.q_proj.bias": "model-00011-of-00012.safetensors",
|
||||
"model.layers.45.self_attn.q_proj.weight": "model-00011-of-00012.safetensors",
|
||||
"model.layers.45.self_attn.v_proj.bias": "model-00011-of-00012.safetensors",
|
||||
"model.layers.45.self_attn.v_proj.weight": "model-00011-of-00012.safetensors",
|
||||
"model.layers.46.input_layernorm.weight": "model-00012-of-00012.safetensors",
|
||||
"model.layers.46.mlp.down_proj.weight": "model-00012-of-00012.safetensors",
|
||||
"model.layers.46.mlp.gate_proj.weight": "model-00011-of-00012.safetensors",
|
||||
"model.layers.46.mlp.up_proj.weight": "model-00012-of-00012.safetensors",
|
||||
"model.layers.46.post_attention_layernorm.weight": "model-00012-of-00012.safetensors",
|
||||
"model.layers.46.self_attn.k_proj.bias": "model-00011-of-00012.safetensors",
|
||||
"model.layers.46.self_attn.k_proj.weight": "model-00011-of-00012.safetensors",
|
||||
"model.layers.46.self_attn.o_proj.weight": "model-00011-of-00012.safetensors",
|
||||
"model.layers.46.self_attn.q_proj.bias": "model-00011-of-00012.safetensors",
|
||||
"model.layers.46.self_attn.q_proj.weight": "model-00011-of-00012.safetensors",
|
||||
"model.layers.46.self_attn.v_proj.bias": "model-00011-of-00012.safetensors",
|
||||
"model.layers.46.self_attn.v_proj.weight": "model-00011-of-00012.safetensors",
|
||||
"model.layers.47.input_layernorm.weight": "model-00012-of-00012.safetensors",
|
||||
"model.layers.47.mlp.down_proj.weight": "model-00012-of-00012.safetensors",
|
||||
"model.layers.47.mlp.gate_proj.weight": "model-00012-of-00012.safetensors",
|
||||
"model.layers.47.mlp.up_proj.weight": "model-00012-of-00012.safetensors",
|
||||
"model.layers.47.post_attention_layernorm.weight": "model-00012-of-00012.safetensors",
|
||||
"model.layers.47.self_attn.k_proj.bias": "model-00012-of-00012.safetensors",
|
||||
"model.layers.47.self_attn.k_proj.weight": "model-00012-of-00012.safetensors",
|
||||
"model.layers.47.self_attn.o_proj.weight": "model-00012-of-00012.safetensors",
|
||||
"model.layers.47.self_attn.q_proj.bias": "model-00012-of-00012.safetensors",
|
||||
"model.layers.47.self_attn.q_proj.weight": "model-00012-of-00012.safetensors",
|
||||
"model.layers.47.self_attn.v_proj.bias": "model-00012-of-00012.safetensors",
|
||||
"model.layers.47.self_attn.v_proj.weight": "model-00012-of-00012.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00002-of-00012.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00002-of-00012.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00002-of-00012.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00002-of-00012.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00002-of-00012.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.bias": "model-00002-of-00012.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00002-of-00012.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00002-of-00012.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.bias": "model-00002-of-00012.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00002-of-00012.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.bias": "model-00002-of-00012.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00002-of-00012.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00003-of-00012.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00003-of-00012.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00003-of-00012.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00003-of-00012.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00003-of-00012.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.bias": "model-00003-of-00012.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00003-of-00012.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00003-of-00012.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.bias": "model-00003-of-00012.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00003-of-00012.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.bias": "model-00003-of-00012.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00003-of-00012.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00003-of-00012.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00003-of-00012.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00003-of-00012.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00003-of-00012.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00003-of-00012.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.bias": "model-00003-of-00012.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00003-of-00012.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00003-of-00012.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.bias": "model-00003-of-00012.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00003-of-00012.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.bias": "model-00003-of-00012.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00003-of-00012.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00003-of-00012.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00003-of-00012.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00003-of-00012.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00003-of-00012.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00003-of-00012.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.bias": "model-00003-of-00012.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00003-of-00012.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00003-of-00012.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.bias": "model-00003-of-00012.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00003-of-00012.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.bias": "model-00003-of-00012.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00003-of-00012.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00003-of-00012.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00003-of-00012.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00003-of-00012.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00003-of-00012.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00003-of-00012.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.bias": "model-00003-of-00012.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00003-of-00012.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00003-of-00012.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.bias": "model-00003-of-00012.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00003-of-00012.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.bias": "model-00003-of-00012.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00003-of-00012.safetensors",
|
||||
"model.norm.weight": "model-00012-of-00012.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
|
||||
194
tokenizer_config.json
Normal file
194
tokenizer_config.json
Normal file
@@ -0,0 +1,194 @@
|
||||
{
|
||||
"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｜>",
|
||||
"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