Hugging Face's logo

airedefined
/
dpo-exp

Text Generation
Transformers
PyTorch
gpt2
text-generation-inference
Inference Endpoints
Model card Files Community
medric49 commited on
Commit
983bd36
•
1 Parent(s): 2ecd760

Training in progress, epoch 1

Browse files
Files changed (9) hide show
  1. adapter_config.json +3 -3
  2. adapter_model.bin +2 -2
  3. added_tokens.json +3 -0
  4. merges.txt +0 -0
  5. special_tokens_map.json +0 -7
  6. tokenizer.json +0 -0
  7. tokenizer_config.json +4 -226
  8. training_args.bin +1 -1
  9. vocab.json +0 -0
adapter_config.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "auto_mapping": null,
3
- "base_model_name_or_path": "airedefined/pythia-14m-dolly-rag",
4
  "bias": "none",
5
- "fan_in_fan_out": false,
6
  "inference_mode": true,
7
  "init_lora_weights": true,
8
  "layers_pattern": null,
@@ -14,7 +14,7 @@
14
  "r": 64,
15
  "revision": null,
16
  "target_modules": [
17
- "query_key_value"
18
  ],
19
  "task_type": "CAUSAL_LM"
20
  }
 
1
  {
2
  "auto_mapping": null,
3
+ "base_model_name_or_path": "gpt2",
4
  "bias": "none",
5
+ "fan_in_fan_out": true,
6
  "inference_mode": true,
7
  "init_lora_weights": true,
8
  "layers_pattern": null,
 
14
  "r": 64,
15
  "revision": null,
16
  "target_modules": [
17
+ "c_attn"
18
  ],
19
  "task_type": "CAUSAL_LM"
20
  }
adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8e2bca31cf77b18c08005cd69939e34fff685c15005ed5e3da16480be453a960
3
- size 791061
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebf02cfd772894102d2e5b0eecc6af4ae7104f4216c547138718681051c8dba2
3
+ size 9445561
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<|endoftext|>": 50256
3
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json CHANGED
@@ -1,11 +1,4 @@
1
  {
2
- "additional_special_tokens": [
3
- "<|endoftext|>",
4
- "<|padding|>",
5
- "### End",
6
- "### Instruction:",
7
- "### Response:\n"
8
- ],
9
  "bos_token": "<|endoftext|>",
10
  "eos_token": "<|endoftext|>",
11
  "pad_token": "<|endoftext|>",
 
1
  {
 
 
 
 
 
 
 
2
  "bos_token": "<|endoftext|>",
3
  "eos_token": "<|endoftext|>",
4
  "pad_token": "<|endoftext|>",
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,242 +1,20 @@
1
  {
2
  "add_prefix_space": false,
3
  "added_tokens_decoder": {
4
- "0": {
5
  "content": "<|endoftext|>",
6
  "lstrip": false,
7
  "normalized": false,
8
  "rstrip": false,
9
  "single_word": false,
10
  "special": true
11
- },
12
- "1": {
13
- "content": "<|padding|>",
14
- "lstrip": false,
15
- "normalized": false,
16
- "rstrip": false,
17
- "single_word": false,
18
- "special": true
19
- },
20
- "50254": {
21
- "content": " ",
22
- "lstrip": false,
23
- "normalized": true,
24
- "rstrip": false,
25
- "single_word": false,
26
- "special": false
27
- },
28
- "50255": {
29
- "content": " ",
30
- "lstrip": false,
31
- "normalized": true,
32
- "rstrip": false,
33
- "single_word": false,
34
- "special": false
35
- },
36
- "50256": {
37
- "content": " ",
38
- "lstrip": false,
39
- "normalized": true,
40
- "rstrip": false,
41
- "single_word": false,
42
- "special": false
43
- },
44
- "50257": {
45
- "content": " ",
46
- "lstrip": false,
47
- "normalized": true,
48
- "rstrip": false,
49
- "single_word": false,
50
- "special": false
51
- },
52
- "50258": {
53
- "content": " ",
54
- "lstrip": false,
55
- "normalized": true,
56
- "rstrip": false,
57
- "single_word": false,
58
- "special": false
59
- },
60
- "50259": {
61
- "content": " ",
62
- "lstrip": false,
63
- "normalized": true,
64
- "rstrip": false,
65
- "single_word": false,
66
- "special": false
67
- },
68
- "50260": {
69
- "content": " ",
70
- "lstrip": false,
71
- "normalized": true,
72
- "rstrip": false,
73
- "single_word": false,
74
- "special": false
75
- },
76
- "50261": {
77
- "content": " ",
78
- "lstrip": false,
79
- "normalized": true,
80
- "rstrip": false,
81
- "single_word": false,
82
- "special": false
83
- },
84
- "50262": {
85
- "content": " ",
86
- "lstrip": false,
87
- "normalized": true,
88
- "rstrip": false,
89
- "single_word": false,
90
- "special": false
91
- },
92
- "50263": {
93
- "content": " ",
94
- "lstrip": false,
95
- "normalized": true,
96
- "rstrip": false,
97
- "single_word": false,
98
- "special": false
99
- },
100
- "50264": {
101
- "content": " ",
102
- "lstrip": false,
103
- "normalized": true,
104
- "rstrip": false,
105
- "single_word": false,
106
- "special": false
107
- },
108
- "50265": {
109
- "content": " ",
110
- "lstrip": false,
111
- "normalized": true,
112
- "rstrip": false,
113
- "single_word": false,
114
- "special": false
115
- },
116
- "50266": {
117
- "content": " ",
118
- "lstrip": false,
119
- "normalized": true,
120
- "rstrip": false,
121
- "single_word": false,
122
- "special": false
123
- },
124
- "50267": {
125
- "content": " ",
126
- "lstrip": false,
127
- "normalized": true,
128
- "rstrip": false,
129
- "single_word": false,
130
- "special": false
131
- },
132
- "50268": {
133
- "content": " ",
134
- "lstrip": false,
135
- "normalized": true,
136
- "rstrip": false,
137
- "single_word": false,
138
- "special": false
139
- },
140
- "50269": {
141
- "content": " ",
142
- "lstrip": false,
143
- "normalized": true,
144
- "rstrip": false,
145
- "single_word": false,
146
- "special": false
147
- },
148
- "50270": {
149
- "content": " ",
150
- "lstrip": false,
151
- "normalized": true,
152
- "rstrip": false,
153
- "single_word": false,
154
- "special": false
155
- },
156
- "50271": {
157
- "content": " ",
158
- "lstrip": false,
159
- "normalized": true,
160
- "rstrip": false,
161
- "single_word": false,
162
- "special": false
163
- },
164
- "50272": {
165
- "content": " ",
166
- "lstrip": false,
167
- "normalized": true,
168
- "rstrip": false,
169
- "single_word": false,
170
- "special": false
171
- },
172
- "50273": {
173
- "content": " ",
174
- "lstrip": false,
175
- "normalized": true,
176
- "rstrip": false,
177
- "single_word": false,
178
- "special": false
179
- },
180
- "50274": {
181
- "content": " ",
182
- "lstrip": false,
183
- "normalized": true,
184
- "rstrip": false,
185
- "single_word": false,
186
- "special": false
187
- },
188
- "50275": {
189
- "content": " ",
190
- "lstrip": false,
191
- "normalized": true,
192
- "rstrip": false,
193
- "single_word": false,
194
- "special": false
195
- },
196
- "50276": {
197
- "content": " ",
198
- "lstrip": false,
199
- "normalized": true,
200
- "rstrip": false,
201
- "single_word": false,
202
- "special": false
203
- },
204
- "50277": {
205
- "content": "### End",
206
- "lstrip": true,
207
- "normalized": false,
208
- "rstrip": true,
209
- "single_word": false,
210
- "special": true
211
- },
212
- "50278": {
213
- "content": "### Instruction:",
214
- "lstrip": true,
215
- "normalized": false,
216
- "rstrip": true,
217
- "single_word": false,
218
- "special": true
219
- },
220
- "50279": {
221
- "content": "### Response:\n",
222
- "lstrip": true,
223
- "normalized": false,
224
- "rstrip": true,
225
- "single_word": false,
226
- "special": true
227
  }
228
  },
229
- "additional_special_tokens": [
230
- "<|endoftext|>",
231
- "<|padding|>",
232
- "### End",
233
- "### Instruction:",
234
- "### Response:\n"
235
- ],
236
  "bos_token": "<|endoftext|>",
237
  "clean_up_tokenization_spaces": true,
238
  "eos_token": "<|endoftext|>",
239
- "model_max_length": 1000000000000000019884624838656,
240
- "tokenizer_class": "GPTNeoXTokenizer",
241
  "unk_token": "<|endoftext|>"
242
  }
 
1
  {
2
  "add_prefix_space": false,
3
  "added_tokens_decoder": {
4
+ "50256": {
5
  "content": "<|endoftext|>",
6
  "lstrip": false,
7
  "normalized": false,
8
  "rstrip": false,
9
  "single_word": false,
10
  "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
11
  }
12
  },
13
+ "additional_special_tokens": [],
 
 
 
 
 
 
14
  "bos_token": "<|endoftext|>",
15
  "clean_up_tokenization_spaces": true,
16
  "eos_token": "<|endoftext|>",
17
+ "model_max_length": 1024,
18
+ "tokenizer_class": "GPT2Tokenizer",
19
  "unk_token": "<|endoftext|>"
20
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a29665cf28de057959f83f89bf1a22a0651d23046314d7bbd0109b7fed5fb4d6
3
  size 4091
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e2b72919aafb934f457db9fa877641dcabbb4cd2aea6ac4d3d7cea556878f46
3
  size 4091
vocab.json ADDED
The diff for this file is too large to render. See raw diff