upload files
Browse files- README.md +277 -3
- config.json +29 -0
- generation_config.json +7 -0
- model-00001-of-00006.safetensors +3 -0
- model-00002-of-00006.safetensors +3 -0
- model-00003-of-00006.safetensors +3 -0
- model-00004-of-00006.safetensors +3 -0
- model-00005-of-00006.safetensors +3 -0
- model-00006-of-00006.safetensors +3 -0
- model.safetensors.index.json +298 -0
README.md
CHANGED
@@ -1,3 +1,277 @@
|
|
1 |
-
|
2 |
-
|
3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
**# Introduction**
|
2 |
+
|
3 |
+
This is a model for generating a jailbreak prompt based on knowledge point texts. The model is trained on the Llama-2-7b dataset and fine-tuned on the Knowledge-to-Jailbreak dataset. The model is intended to bridge the gap between theoretical vulnerabilities and real-world application scenarios, simulating sophisticated adversarial attacks that incorporate specialized knowledge.
|
4 |
+
|
5 |
+
Our proposed method and dataset serve as a critical starting point for both offensive and defensive research, enabling the development of new techniques to enhance the security and robustness of language models in practical settings.
|
6 |
+
|
7 |
+
**# How to load the model and tokenizer**
|
8 |
+
|
9 |
+
We provide two helper functions for loading the model and tokenizer.
|
10 |
+
|
11 |
+
\```python
|
12 |
+
|
13 |
+
import torch
|
14 |
+
|
15 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer, AutoModelForSequenceClassification, AutoModelForTokenClassification
|
16 |
+
|
17 |
+
import os
|
18 |
+
|
19 |
+
import json
|
20 |
+
|
21 |
+
from peft import PeftModel
|
22 |
+
|
23 |
+
\# from trl import AutoModelForCausalLMWithValueHead
|
24 |
+
|
25 |
+
from transformers import AutoModelForCausalLM as AutoGPTQForCausalLM
|
26 |
+
|
27 |
+
def load_tokenizer(dir_or_model):
|
28 |
+
|
29 |
+
"""
|
30 |
+
|
31 |
+
This function is used to load the tokenizer for a specific pre-trained model.
|
32 |
+
|
33 |
+
|
34 |
+
|
35 |
+
Args:
|
36 |
+
|
37 |
+
dir_or_model: It can be either a directory containing the pre-training model configuration details or a pretrained model.
|
38 |
+
|
39 |
+
|
40 |
+
|
41 |
+
Returns:
|
42 |
+
|
43 |
+
It returns a tokenizer that can convert text to tokens for the specific model input.
|
44 |
+
|
45 |
+
"""
|
46 |
+
|
47 |
+
is_lora_dir = os.path.isfile(os.path.join(dir_or_model, "adapter_config.json"))
|
48 |
+
|
49 |
+
if is_lora_dir:
|
50 |
+
|
51 |
+
loaded_json = json.load(open(os.path.join(dir_or_model, "adapter_config.json"), "r"))
|
52 |
+
|
53 |
+
model_name = loaded_json["base_model_name_or_path"]
|
54 |
+
|
55 |
+
else:
|
56 |
+
|
57 |
+
model_name = dir_or_model
|
58 |
+
|
59 |
+
|
60 |
+
|
61 |
+
if os.path.isfile(os.path.join(dir_or_model, "config.json")):
|
62 |
+
|
63 |
+
loaded_json = json.load(open(os.path.join(dir_or_model, "config.json"), "r"))
|
64 |
+
|
65 |
+
if "_name_or_path" in loaded_json:
|
66 |
+
|
67 |
+
model_name = loaded_json["_name_or_path"]
|
68 |
+
|
69 |
+
local_model_name = "/data3/MODELS/llama2-hf/llama-2-7b"#/data2/tsq/WaterBench/data/models/llama-2-7b-chat-hf
|
70 |
+
|
71 |
+
|
72 |
+
|
73 |
+
print(">>>>>>>>>>>>>>>>>>>>>>>>>>notice this<<<<<<<<<<<<<<<<<<<<<<<<<<<<")
|
74 |
+
|
75 |
+
|
76 |
+
|
77 |
+
\#print(model_name)
|
78 |
+
|
79 |
+
tokenizer = AutoTokenizer.from_pretrained(local_model_name)
|
80 |
+
|
81 |
+
if tokenizer.pad_token is None:
|
82 |
+
|
83 |
+
tokenizer.pad_token = tokenizer.eos_token
|
84 |
+
|
85 |
+
tokenizer.pad_token_id = tokenizer.eos_token_id
|
86 |
+
|
87 |
+
|
88 |
+
|
89 |
+
return tokenizer
|
90 |
+
|
91 |
+
def load_model(dir_or_model, classification=False, token_classification=False, return_tokenizer=False, dtype=torch.bfloat16, load_dtype=True,
|
92 |
+
|
93 |
+
rl=False, peft_config=None, device_map="auto", revision='main'):
|
94 |
+
|
95 |
+
"""
|
96 |
+
|
97 |
+
This function is used to load a model based on several parameters including the type of task it is targeted to perform.
|
98 |
+
|
99 |
+
|
100 |
+
|
101 |
+
Args:
|
102 |
+
|
103 |
+
dir_or_model: It can be either a directory containing the pre-training model configuration details or a pretrained model.
|
104 |
+
|
105 |
+
classification (bool): If True, loads the model for sequence classification.
|
106 |
+
|
107 |
+
token_classification (bool): If True, loads the model for token classification.
|
108 |
+
|
109 |
+
return_tokenizer (bool): If True, returns the tokenizer along with the model.
|
110 |
+
|
111 |
+
dtype: The data type that PyTorch should use internally to store the model’s parameters and do the computation.
|
112 |
+
|
113 |
+
load_dtype (bool): If False, sets dtype as torch.float32 regardless of the passed dtype value.
|
114 |
+
|
115 |
+
rl (bool): If True, loads model specifically designed to be used in reinforcement learning environment.
|
116 |
+
|
117 |
+
peft_config: Configuration details for Peft models.
|
118 |
+
|
119 |
+
|
120 |
+
|
121 |
+
Returns:
|
122 |
+
|
123 |
+
It returns a model for the required task along with its tokenizer, if specified.
|
124 |
+
|
125 |
+
"""
|
126 |
+
|
127 |
+
is_lora_dir = os.path.isfile(os.path.join(dir_or_model, "adapter_config.json"))
|
128 |
+
|
129 |
+
if not load_dtype:
|
130 |
+
|
131 |
+
dtype = torch.float32
|
132 |
+
|
133 |
+
if is_lora_dir:
|
134 |
+
|
135 |
+
loaded_json = json.load(open(os.path.join(dir_or_model, "adapter_config.json"), "r"))
|
136 |
+
|
137 |
+
model_name = loaded_json["base_model_name_or_path"]
|
138 |
+
|
139 |
+
else:
|
140 |
+
|
141 |
+
model_name = dir_or_model
|
142 |
+
|
143 |
+
original_model_name = model_name
|
144 |
+
|
145 |
+
\#local_model_name = "/data1/tsq/zkj_use/MODELS/phi-2"
|
146 |
+
|
147 |
+
\#local_model_name = "/data2/tsq/WaterBench/data/models/llama-2-7b-chat-hf"
|
148 |
+
|
149 |
+
\#local_model_name = "/data3/MODELS/llama2-hf/llama-2-7b"
|
150 |
+
|
151 |
+
\#print(model_name)
|
152 |
+
|
153 |
+
if classification:
|
154 |
+
|
155 |
+
model = AutoModelForSequenceClassification.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float32, use_auth_token=True, device_map=device_map, revision=revision) # to investigate: calling torch_dtype here fails.
|
156 |
+
|
157 |
+
elif token_classification:
|
158 |
+
|
159 |
+
model = AutoModelForTokenClassification.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float32, use_auth_token=True, device_map=device_map, revision=revision)
|
160 |
+
|
161 |
+
\# elif rl:
|
162 |
+
|
163 |
+
\# model = AutoModelForCausalLMWithValueHead.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float32, use_auth_token=True,
|
164 |
+
|
165 |
+
\# peft_config=peft_config, device_map=device_map, revision=revision)
|
166 |
+
|
167 |
+
else:
|
168 |
+
|
169 |
+
if model_name.endswith("GPTQ") or model_name.endswith("GGML"):
|
170 |
+
|
171 |
+
model = AutoGPTQForCausalLM.from_quantized(model_name,
|
172 |
+
|
173 |
+
use_safetensors=True,
|
174 |
+
|
175 |
+
trust_remote_code=True,
|
176 |
+
|
177 |
+
\# use_triton=True, # breaks currently, unfortunately generation time of the GPTQ model is quite slow
|
178 |
+
|
179 |
+
quantize_config=None, device_map=device_map)
|
180 |
+
|
181 |
+
else:
|
182 |
+
|
183 |
+
print('11111111111111111111111111111111111111')
|
184 |
+
|
185 |
+
model = AutoModelForCausalLM.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float32, use_auth_token=True, device_map=device_map, revision=revision)
|
186 |
+
|
187 |
+
if is_lora_dir:
|
188 |
+
|
189 |
+
model = PeftModel.from_pretrained(model, dir_or_model)
|
190 |
+
|
191 |
+
|
192 |
+
|
193 |
+
try:
|
194 |
+
|
195 |
+
tokenizer = load_tokenizer(original_model_name)
|
196 |
+
|
197 |
+
model.config.pad_token_id = tokenizer.pad_token_id
|
198 |
+
|
199 |
+
except Exception:
|
200 |
+
|
201 |
+
pass
|
202 |
+
|
203 |
+
if return_tokenizer:
|
204 |
+
|
205 |
+
return model, load_tokenizer(original_model_name)
|
206 |
+
|
207 |
+
return model
|
208 |
+
|
209 |
+
model_name = 'tsq2000/Jailbreak-generator'
|
210 |
+
|
211 |
+
model = load_model(model_name)
|
212 |
+
|
213 |
+
tokenizer = load_tokenizer(model_name)
|
214 |
+
|
215 |
+
\```
|
216 |
+
|
217 |
+
**# How to generate jailbreak prompts**
|
218 |
+
|
219 |
+
Here is an example of how to generate jailbreak prompts based on knowledge point texts.
|
220 |
+
|
221 |
+
\```python
|
222 |
+
|
223 |
+
model_name = 'tsq2000/Jailbreak-generator'
|
224 |
+
|
225 |
+
model = load_model(model_name)
|
226 |
+
|
227 |
+
tokenizer = load_tokenizer(model_name)
|
228 |
+
|
229 |
+
max_length = 2048
|
230 |
+
|
231 |
+
max_tokens = 64
|
232 |
+
|
233 |
+
knowledge_points = ["Kettling Kettling (also known as containment or corralling) is a police tactic for controlling large crowds during demonstrations or protests. It involves the formation of large cordons of police officers who then move to contain a crowd within a limited area. Protesters are left only one choice of exit controlled by the police – or are completely prevented from leaving, with the effect of denying the protesters access to food, water and toilet facilities for a time period determined by the police forces. The tactic has proved controversial, in part because it has resulted in the detention of ordinary bystanders."]
|
234 |
+
|
235 |
+
batch_texts = [f'### Input:\n{input_}\n\n### Response:\n' for input_ in knowledge_points]
|
236 |
+
|
237 |
+
inputs = tokenizer(batch_texts, return_tensors='pt', padding=True, truncation=True, max_length=max_length - max_tokens).to(model.device)
|
238 |
+
|
239 |
+
outputs = model.generate(**inputs, max_new_tokens=max_tokens, num_return_sequences=1, do_sample=False, temperature=1, top_p=1, eos_token_id=tokenizer.eos_token_id)
|
240 |
+
|
241 |
+
generated_texts = []
|
242 |
+
|
243 |
+
for output, input_text in zip(outputs, batch_texts):
|
244 |
+
|
245 |
+
text = tokenizer.decode(output, skip_special_tokens=True)
|
246 |
+
|
247 |
+
generated_texts.append(text[len(input_text):])
|
248 |
+
|
249 |
+
print(generated_texts)
|
250 |
+
|
251 |
+
\```
|
252 |
+
|
253 |
+
**# Citation**
|
254 |
+
|
255 |
+
If you find this model useful, please cite the following paper:
|
256 |
+
|
257 |
+
\```
|
258 |
+
|
259 |
+
@misc{tu2024knowledgetojailbreak,
|
260 |
+
|
261 |
+
title={Knowledge-to-Jailbreak: One Knowledge Point Worth One Attack},
|
262 |
+
|
263 |
+
author={Shangqing Tu and Zhuoran Pan and Wenxuan Wang and Zhexin Zhang and Yuliang Sun and Jifan Yu and Hongning Wang and Lei Hou and Juanzi Li},
|
264 |
+
|
265 |
+
year={2024},
|
266 |
+
|
267 |
+
eprint={2406.11682},
|
268 |
+
|
269 |
+
archivePrefix={arXiv},
|
270 |
+
|
271 |
+
primaryClass={cs.CL},
|
272 |
+
|
273 |
+
url={https://arxiv.org/abs/2406.11682},
|
274 |
+
|
275 |
+
}
|
276 |
+
|
277 |
+
\```
|
config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/data3/MODELS/llama2-hf/llama-2-7b",
|
3 |
+
"architectures": [
|
4 |
+
"LlamaForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 1,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_act": "silu",
|
11 |
+
"hidden_size": 4096,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 11008,
|
14 |
+
"max_position_embeddings": 2048,
|
15 |
+
"model_type": "llama",
|
16 |
+
"num_attention_heads": 32,
|
17 |
+
"num_hidden_layers": 32,
|
18 |
+
"num_key_value_heads": 32,
|
19 |
+
"pad_token_id": 2,
|
20 |
+
"pretraining_tp": 1,
|
21 |
+
"rms_norm_eps": 1e-05,
|
22 |
+
"rope_scaling": null,
|
23 |
+
"rope_theta": 10000.0,
|
24 |
+
"tie_word_embeddings": false,
|
25 |
+
"torch_dtype": "float32",
|
26 |
+
"transformers_version": "4.38.2",
|
27 |
+
"use_cache": true,
|
28 |
+
"vocab_size": 32000
|
29 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 1,
|
4 |
+
"eos_token_id": 2,
|
5 |
+
"pad_token_id": 0,
|
6 |
+
"transformers_version": "4.38.2"
|
7 |
+
}
|
model-00001-of-00006.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:507ba5e2eb2bd3a105b61af5e345bc7bc7791e24e9943fe3b9e30e57db754b79
|
3 |
+
size 4840396416
|
model-00002-of-00006.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9219f7c8fec6cc62574d18d0f832b144c87cf0bc413001e8a6d9ff8e1507f27b
|
3 |
+
size 4857206856
|
model-00003-of-00006.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f003ff3da0fb69fac73c5e33f97e7dbe833457449184713f36b34c768dbf97be
|
3 |
+
size 4857206904
|
model-00004-of-00006.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f396ce08abc0b9f5538dc73e17a64758bece0b2f5aa7c471fb521c2ab7586cd6
|
3 |
+
size 4857206904
|
model-00005-of-00006.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fffd60c69a7339047c2aef45680dd1b8b7dd62255d1afbe36a3a5d15c1d915c5
|
3 |
+
size 4857206904
|
model-00006-of-00006.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:99aeb3e19065f34de93854c9149fbdd6dea92721421d862ba73346ea6671d95e
|
3 |
+
size 2684472112
|
model.safetensors.index.json
ADDED
@@ -0,0 +1,298 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"metadata": {
|
3 |
+
"total_size": 26953662464
|
4 |
+
},
|
5 |
+
"weight_map": {
|
6 |
+
"lm_head.weight": "model-00006-of-00006.safetensors",
|
7 |
+
"model.embed_tokens.weight": "model-00001-of-00006.safetensors",
|
8 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
9 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
|
10 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
|
11 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
|
12 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
13 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
14 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
15 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
16 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
17 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
18 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
|
19 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
|
20 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
|
21 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
22 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
23 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
24 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
25 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
26 |
+
"model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
27 |
+
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
28 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
29 |
+
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
30 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
31 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
32 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
33 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
34 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
35 |
+
"model.layers.11.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
36 |
+
"model.layers.11.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
37 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
38 |
+
"model.layers.11.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
39 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
40 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
41 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
42 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
43 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
44 |
+
"model.layers.12.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
45 |
+
"model.layers.12.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
46 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
47 |
+
"model.layers.12.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
48 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
49 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
50 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
51 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
52 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
53 |
+
"model.layers.13.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
54 |
+
"model.layers.13.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
55 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
56 |
+
"model.layers.13.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
57 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
58 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
59 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
60 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
61 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
62 |
+
"model.layers.14.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
63 |
+
"model.layers.14.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
64 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
65 |
+
"model.layers.14.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
66 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
67 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
68 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
69 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
70 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
71 |
+
"model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
72 |
+
"model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
73 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
74 |
+
"model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
75 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
76 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
77 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
78 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
79 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
80 |
+
"model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
81 |
+
"model.layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
82 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
83 |
+
"model.layers.16.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
84 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
85 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
86 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
87 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
88 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
89 |
+
"model.layers.17.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
90 |
+
"model.layers.17.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
91 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
92 |
+
"model.layers.17.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
93 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
94 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
95 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
96 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
97 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
98 |
+
"model.layers.18.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
99 |
+
"model.layers.18.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
100 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
101 |
+
"model.layers.18.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
102 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
103 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
104 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
105 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
106 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
107 |
+
"model.layers.19.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
108 |
+
"model.layers.19.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
109 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
110 |
+
"model.layers.19.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
111 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
112 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
113 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
114 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
115 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
116 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
117 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
|
118 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
|
119 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
|
120 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
121 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
122 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
123 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
124 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
125 |
+
"model.layers.20.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
126 |
+
"model.layers.20.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
127 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
128 |
+
"model.layers.20.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
129 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
130 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
131 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
132 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
133 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
134 |
+
"model.layers.21.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
135 |
+
"model.layers.21.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
136 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
137 |
+
"model.layers.21.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
138 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
139 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
140 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
141 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
142 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
143 |
+
"model.layers.22.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
144 |
+
"model.layers.22.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
145 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
146 |
+
"model.layers.22.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
147 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
148 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
149 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
150 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
151 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
152 |
+
"model.layers.23.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
153 |
+
"model.layers.23.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
154 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
155 |
+
"model.layers.23.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
156 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
157 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
158 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
159 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
160 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
161 |
+
"model.layers.24.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
162 |
+
"model.layers.24.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
163 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
164 |
+
"model.layers.24.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
165 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
166 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
167 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
168 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
169 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
170 |
+
"model.layers.25.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
171 |
+
"model.layers.25.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
172 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
173 |
+
"model.layers.25.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
174 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
175 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
176 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
177 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
178 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
179 |
+
"model.layers.26.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
180 |
+
"model.layers.26.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
181 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
182 |
+
"model.layers.26.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
183 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
184 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
185 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
186 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
187 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
188 |
+
"model.layers.27.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
189 |
+
"model.layers.27.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
190 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
191 |
+
"model.layers.27.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
192 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
193 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
194 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
195 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
196 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
197 |
+
"model.layers.28.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
198 |
+
"model.layers.28.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
199 |
+
"model.layers.28.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
200 |
+
"model.layers.28.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
201 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
202 |
+
"model.layers.28.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
203 |
+
"model.layers.28.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
204 |
+
"model.layers.28.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
205 |
+
"model.layers.28.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
206 |
+
"model.layers.29.input_layernorm.weight": "model-00006-of-00006.safetensors",
|
207 |
+
"model.layers.29.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
|
208 |
+
"model.layers.29.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
|
209 |
+
"model.layers.29.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
|
210 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
|
211 |
+
"model.layers.29.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
212 |
+
"model.layers.29.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
213 |
+
"model.layers.29.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
214 |
+
"model.layers.29.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
215 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
216 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
|
217 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
|
218 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
|
219 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
220 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
221 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
222 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
223 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
224 |
+
"model.layers.30.input_layernorm.weight": "model-00006-of-00006.safetensors",
|
225 |
+
"model.layers.30.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
|
226 |
+
"model.layers.30.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
|
227 |
+
"model.layers.30.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
|
228 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
|
229 |
+
"model.layers.30.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
|
230 |
+
"model.layers.30.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
|
231 |
+
"model.layers.30.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
|
232 |
+
"model.layers.30.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
|
233 |
+
"model.layers.31.input_layernorm.weight": "model-00006-of-00006.safetensors",
|
234 |
+
"model.layers.31.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
|
235 |
+
"model.layers.31.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
|
236 |
+
"model.layers.31.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
|
237 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
|
238 |
+
"model.layers.31.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
|
239 |
+
"model.layers.31.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
|
240 |
+
"model.layers.31.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
|
241 |
+
"model.layers.31.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
|
242 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
243 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
|
244 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
|
245 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
|
246 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
247 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
248 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
249 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
250 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
251 |
+
"model.layers.5.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
252 |
+
"model.layers.5.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
253 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
254 |
+
"model.layers.5.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
255 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
256 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
257 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
258 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
259 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
260 |
+
"model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
261 |
+
"model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
262 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
263 |
+
"model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
264 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
265 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
266 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
267 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
268 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
269 |
+
"model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
270 |
+
"model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
271 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
272 |
+
"model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
273 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
274 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
275 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
276 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
277 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
278 |
+
"model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
279 |
+
"model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
280 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
281 |
+
"model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
282 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
283 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
284 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
285 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
286 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
287 |
+
"model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
288 |
+
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
289 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
290 |
+
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
291 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
292 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
293 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
294 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
295 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
296 |
+
"model.norm.weight": "model-00006-of-00006.safetensors"
|
297 |
+
}
|
298 |
+
}
|