ishmanish commited on
Commit
3fa0c7f
1 Parent(s): 9cc01a2

Upload 10 files

Browse files
README.md CHANGED
@@ -1,3 +1,45 @@
1
- ---
2
- license: apache-2.0
3
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - autotrain
4
+ - text-generation-inference
5
+ - text-generation
6
+ - peft
7
+ library_name: transformers
8
+ widget:
9
+ - messages:
10
+ - role: user
11
+ content: What is your favorite condiment?
12
+ license: other
13
+ ---
14
+
15
+ # Model Trained Using AutoTrain
16
+
17
+ This model was trained using AutoTrain. For more information, please visit [AutoTrain](https://hf.co/docs/autotrain).
18
+
19
+ # Usage
20
+
21
+ ```python
22
+
23
+ from transformers import AutoModelForCausalLM, AutoTokenizer
24
+
25
+ model_path = "PATH_TO_THIS_REPO"
26
+
27
+ tokenizer = AutoTokenizer.from_pretrained(model_path)
28
+ model = AutoModelForCausalLM.from_pretrained(
29
+ model_path,
30
+ device_map="auto",
31
+ torch_dtype='auto'
32
+ ).eval()
33
+
34
+ # Prompt content: "hi"
35
+ messages = [
36
+ {"role": "user", "content": "hi"}
37
+ ]
38
+
39
+ input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, add_generation_prompt=True, return_tensors='pt')
40
+ output_ids = model.generate(input_ids.to('cuda'))
41
+ response = tokenizer.decode(output_ids[0][input_ids.shape[1]:], skip_special_tokens=True)
42
+
43
+ # Model response: "Hello! How can I assist you today?"
44
+ print(response)
45
+ ```
config.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
- "_name_or_path": "/content/Mistral-7B-autotrain-text-HrPolicy-v7",
3
  "architectures": [
4
- "MistralModel"
5
  ],
6
  "attention_dropout": 0.0,
7
  "bos_token_id": 1,
@@ -19,7 +19,7 @@
19
  "rope_theta": 1000000.0,
20
  "sliding_window": null,
21
  "tie_word_embeddings": false,
22
- "torch_dtype": "float32",
23
  "transformers_version": "4.41.0",
24
  "use_cache": true,
25
  "vocab_size": 32000
 
1
  {
2
+ "_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
3
  "architectures": [
4
+ "MistralForCausalLM"
5
  ],
6
  "attention_dropout": 0.0,
7
  "bos_token_id": 1,
 
19
  "rope_theta": 1000000.0,
20
  "sliding_window": null,
21
  "tie_word_embeddings": false,
22
+ "torch_dtype": "float16",
23
  "transformers_version": "4.41.0",
24
  "use_cache": true,
25
  "vocab_size": 32000
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.41.0"
6
+ }
model.safetensors.index.json CHANGED
@@ -1,297 +1,298 @@
1
  {
2
  "metadata": {
3
- "total_size": 28442640384
4
  },
5
  "weight_map": {
6
- "embed_tokens.weight": "model-00001-of-00006.safetensors",
7
- "layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
8
- "layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
9
- "layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
10
- "layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
11
- "layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
12
- "layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
13
- "layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
14
- "layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
15
- "layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
16
- "layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
17
- "layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
18
- "layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
19
- "layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
20
- "layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
21
- "layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
22
- "layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
23
- "layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
24
- "layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
25
- "layers.10.input_layernorm.weight": "model-00003-of-00006.safetensors",
26
- "layers.10.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
27
- "layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
28
- "layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
29
- "layers.10.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
30
- "layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
31
- "layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
32
- "layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
33
- "layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
34
- "layers.11.input_layernorm.weight": "model-00003-of-00006.safetensors",
35
- "layers.11.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
36
- "layers.11.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
37
- "layers.11.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
38
- "layers.11.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
39
- "layers.11.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
40
- "layers.11.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
41
- "layers.11.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
42
- "layers.11.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
43
- "layers.12.input_layernorm.weight": "model-00003-of-00006.safetensors",
44
- "layers.12.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
45
- "layers.12.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
46
- "layers.12.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
47
- "layers.12.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
48
- "layers.12.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
49
- "layers.12.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
50
- "layers.12.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
51
- "layers.12.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
52
- "layers.13.input_layernorm.weight": "model-00003-of-00006.safetensors",
53
- "layers.13.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
54
- "layers.13.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
55
- "layers.13.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
56
- "layers.13.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
57
- "layers.13.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
58
- "layers.13.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
59
- "layers.13.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
60
- "layers.13.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
61
- "layers.14.input_layernorm.weight": "model-00003-of-00006.safetensors",
62
- "layers.14.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
63
- "layers.14.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
64
- "layers.14.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
65
- "layers.14.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
66
- "layers.14.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
67
- "layers.14.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
68
- "layers.14.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
69
- "layers.14.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
70
- "layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
71
- "layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
72
- "layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
73
- "layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
74
- "layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
75
- "layers.15.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
76
- "layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
77
- "layers.15.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
78
- "layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
79
- "layers.16.input_layernorm.weight": "model-00004-of-00006.safetensors",
80
- "layers.16.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
81
- "layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
82
- "layers.16.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
83
- "layers.16.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
84
- "layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
85
- "layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
86
- "layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
87
- "layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
88
- "layers.17.input_layernorm.weight": "model-00004-of-00006.safetensors",
89
- "layers.17.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
90
- "layers.17.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
91
- "layers.17.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
92
- "layers.17.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
93
- "layers.17.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
94
- "layers.17.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
95
- "layers.17.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
96
- "layers.17.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
97
- "layers.18.input_layernorm.weight": "model-00004-of-00006.safetensors",
98
- "layers.18.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
99
- "layers.18.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
100
- "layers.18.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
101
- "layers.18.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
102
- "layers.18.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
103
- "layers.18.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
104
- "layers.18.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
105
- "layers.18.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
106
- "layers.19.input_layernorm.weight": "model-00004-of-00006.safetensors",
107
- "layers.19.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
108
- "layers.19.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
109
- "layers.19.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
110
- "layers.19.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
111
- "layers.19.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
112
- "layers.19.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
113
- "layers.19.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
114
- "layers.19.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
115
- "layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
116
- "layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
117
- "layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
118
- "layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
119
- "layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
120
- "layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
121
- "layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
122
- "layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
123
- "layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
124
- "layers.20.input_layernorm.weight": "model-00004-of-00006.safetensors",
125
- "layers.20.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
126
- "layers.20.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
127
- "layers.20.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
128
- "layers.20.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
129
- "layers.20.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
130
- "layers.20.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
131
- "layers.20.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
132
- "layers.20.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
133
- "layers.21.input_layernorm.weight": "model-00004-of-00006.safetensors",
134
- "layers.21.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
135
- "layers.21.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
136
- "layers.21.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
137
- "layers.21.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
138
- "layers.21.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
139
- "layers.21.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
140
- "layers.21.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
141
- "layers.21.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
142
- "layers.22.input_layernorm.weight": "model-00005-of-00006.safetensors",
143
- "layers.22.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
144
- "layers.22.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
145
- "layers.22.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
146
- "layers.22.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
147
- "layers.22.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
148
- "layers.22.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
149
- "layers.22.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
150
- "layers.22.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
151
- "layers.23.input_layernorm.weight": "model-00005-of-00006.safetensors",
152
- "layers.23.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
153
- "layers.23.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
154
- "layers.23.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
155
- "layers.23.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
156
- "layers.23.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
157
- "layers.23.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
158
- "layers.23.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
159
- "layers.23.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
160
- "layers.24.input_layernorm.weight": "model-00005-of-00006.safetensors",
161
- "layers.24.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
162
- "layers.24.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
163
- "layers.24.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
164
- "layers.24.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
165
- "layers.24.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
166
- "layers.24.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
167
- "layers.24.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
168
- "layers.24.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
169
- "layers.25.input_layernorm.weight": "model-00005-of-00006.safetensors",
170
- "layers.25.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
171
- "layers.25.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
172
- "layers.25.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
173
- "layers.25.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
174
- "layers.25.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
175
- "layers.25.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
176
- "layers.25.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
177
- "layers.25.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
178
- "layers.26.input_layernorm.weight": "model-00005-of-00006.safetensors",
179
- "layers.26.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
180
- "layers.26.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
181
- "layers.26.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
182
- "layers.26.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
183
- "layers.26.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
184
- "layers.26.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
185
- "layers.26.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
186
- "layers.26.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
187
- "layers.27.input_layernorm.weight": "model-00006-of-00006.safetensors",
188
- "layers.27.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
189
- "layers.27.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
190
- "layers.27.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
191
- "layers.27.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
192
- "layers.27.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
193
- "layers.27.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
194
- "layers.27.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
195
- "layers.27.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
196
- "layers.28.input_layernorm.weight": "model-00006-of-00006.safetensors",
197
- "layers.28.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
198
- "layers.28.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
199
- "layers.28.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
200
- "layers.28.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
201
- "layers.28.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
202
- "layers.28.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
203
- "layers.28.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
204
- "layers.28.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
205
- "layers.29.input_layernorm.weight": "model-00006-of-00006.safetensors",
206
- "layers.29.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
207
- "layers.29.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
208
- "layers.29.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
209
- "layers.29.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
210
- "layers.29.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
211
- "layers.29.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
212
- "layers.29.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
213
- "layers.29.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
214
- "layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
215
- "layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
216
- "layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
217
- "layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
218
- "layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
219
- "layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
220
- "layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
221
- "layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
222
- "layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
223
- "layers.30.input_layernorm.weight": "model-00006-of-00006.safetensors",
224
- "layers.30.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
225
- "layers.30.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
226
- "layers.30.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
227
- "layers.30.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
228
- "layers.30.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
229
- "layers.30.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
230
- "layers.30.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
231
- "layers.30.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
232
- "layers.31.input_layernorm.weight": "model-00006-of-00006.safetensors",
233
- "layers.31.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
234
- "layers.31.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
235
- "layers.31.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
236
- "layers.31.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
237
- "layers.31.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
238
- "layers.31.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
239
- "layers.31.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
240
- "layers.31.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
241
- "layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
242
- "layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
243
- "layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
244
- "layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
245
- "layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
246
- "layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
247
- "layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
248
- "layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
249
- "layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
250
- "layers.5.input_layernorm.weight": "model-00002-of-00006.safetensors",
251
- "layers.5.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
252
- "layers.5.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
253
- "layers.5.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
254
- "layers.5.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
255
- "layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
256
- "layers.5.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
257
- "layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
258
- "layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
259
- "layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
260
- "layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
261
- "layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
262
- "layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
263
- "layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
264
- "layers.6.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
265
- "layers.6.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
266
- "layers.6.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
267
- "layers.6.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
268
- "layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
269
- "layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
270
- "layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
271
- "layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
272
- "layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
273
- "layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
274
- "layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
275
- "layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
276
- "layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
277
- "layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
278
- "layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
279
- "layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
280
- "layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
281
- "layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
282
- "layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
283
- "layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
284
- "layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
285
- "layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
286
- "layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
287
- "layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
288
- "layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
289
- "layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
290
- "layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
291
- "layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
292
- "layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
293
- "layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
294
- "layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
295
- "norm.weight": "model-00006-of-00006.safetensors"
 
296
  }
297
  }
 
1
  {
2
  "metadata": {
3
+ "total_size": 14483464192
4
  },
5
  "weight_map": {
6
+ "lm_head.weight": "model-00003-of-00003.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
44
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
45
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
46
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
47
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
48
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
53
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
55
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
56
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
62
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
63
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
64
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
65
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
66
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
71
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
72
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
73
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
74
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
75
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
80
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
82
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
83
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
85
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
86
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
87
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
88
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
89
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
90
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
91
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
92
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
93
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
98
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
99
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
100
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
101
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
102
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
103
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
104
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
105
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
106
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
107
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
108
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
109
+ "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
110
+ "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
111
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
112
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
113
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
114
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
115
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
116
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
117
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
118
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
119
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
120
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
121
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
122
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
123
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
124
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
125
+ "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
126
+ "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
127
+ "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
128
+ "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
129
+ "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
130
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
131
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
132
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
133
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
134
+ "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
135
+ "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
136
+ "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
137
+ "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
138
+ "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
139
+ "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
140
+ "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
141
+ "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
142
+ "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
143
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
144
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
148
+ "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
149
+ "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
150
+ "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
151
+ "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
152
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
153
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
154
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
155
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
156
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
157
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
161
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
162
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
163
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
164
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
165
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
166
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
167
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
168
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
169
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
170
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
171
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
172
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
173
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
174
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
175
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
176
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
177
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
178
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
179
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
180
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
181
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
182
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
183
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
184
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
185
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
186
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
187
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
188
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
190
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
191
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
192
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
193
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
194
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
195
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
196
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
197
+ "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
198
+ "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
199
+ "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
200
+ "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
201
+ "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
202
+ "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
203
+ "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
204
+ "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
205
+ "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
206
+ "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
207
+ "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
208
+ "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
209
+ "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
210
+ "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
211
+ "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
212
+ "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
213
+ "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
214
+ "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
215
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
216
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
217
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
218
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
219
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
220
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
221
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
222
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
223
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
224
+ "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
225
+ "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
226
+ "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
227
+ "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
228
+ "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
229
+ "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
230
+ "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
231
+ "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
232
+ "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
233
+ "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
234
+ "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
235
+ "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
236
+ "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
237
+ "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
238
+ "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
239
+ "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
240
+ "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
241
+ "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
242
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
243
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
244
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
245
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
246
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
247
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
248
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
249
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
250
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
251
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
252
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
253
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
254
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
255
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
256
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
257
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
258
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
259
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
260
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
261
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
262
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
263
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
264
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
265
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
266
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
267
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
268
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
269
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
270
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
271
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
272
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
273
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
274
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
275
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
276
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
277
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
278
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
279
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
280
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
281
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
282
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
283
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
284
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
285
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
286
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
287
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
288
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
289
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
290
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
291
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
292
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
293
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
294
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
295
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
296
+ "model.norm.weight": "model-00003-of-00003.safetensors"
297
  }
298
  }
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
tokenizer_config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "additional_special_tokens": [],
31
+ "bos_token": "<s>",
32
+ "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
33
+ "clean_up_tokenization_spaces": false,
34
+ "eos_token": "</s>",
35
+ "model_max_length": 1024,
36
+ "pad_token": "</s>",
37
+ "sp_model_kwargs": {},
38
+ "spaces_between_special_tokens": false,
39
+ "tokenizer_class": "LlamaTokenizer",
40
+ "unk_token": "<unk>",
41
+ "use_default_system_prompt": false
42
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d8ee983e14bd0942fa779ab3bde25bd59952bbba5fae7b546a15b731969284f
3
+ size 5112
training_params.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model": "mistralai/Mistral-7B-Instruct-v0.2",
3
+ "project_name": "Mistral-7B-autotrain-text-HrPolicy-v7",
4
+ "data_path": "data/",
5
+ "train_split": "train",
6
+ "valid_split": null,
7
+ "add_eos_token": false,
8
+ "block_size": 2048,
9
+ "model_max_length": 1024,
10
+ "padding": null,
11
+ "trainer": "default",
12
+ "use_flash_attention_2": false,
13
+ "log": "none",
14
+ "disable_gradient_checkpointing": false,
15
+ "logging_steps": -1,
16
+ "evaluation_strategy": "epoch",
17
+ "save_total_limit": 1,
18
+ "auto_find_batch_size": false,
19
+ "mixed_precision": "fp16",
20
+ "lr": 0.00005,
21
+ "epochs": 50,
22
+ "batch_size": 2,
23
+ "warmup_ratio": 0.1,
24
+ "gradient_accumulation": 4,
25
+ "optimizer": "adamw_torch",
26
+ "scheduler": "linear",
27
+ "weight_decay": 0.01,
28
+ "max_grad_norm": 1.0,
29
+ "seed": 42,
30
+ "chat_template": null,
31
+ "quantization": "int8",
32
+ "target_modules": "all-linear",
33
+ "merge_adapter": true,
34
+ "peft": true,
35
+ "lora_r": 16,
36
+ "lora_alpha": 32,
37
+ "lora_dropout": 0.1,
38
+ "model_ref": null,
39
+ "dpo_beta": 0.1,
40
+ "max_prompt_length": 128,
41
+ "max_completion_length": null,
42
+ "prompt_text_column": "prompt",
43
+ "text_column": "text",
44
+ "rejected_text_column": "rejected",
45
+ "push_to_hub": false,
46
+ "username": null,
47
+ "token": null
48
+ }