Hugging Face's logo

Striker-7
/
eleres

PEFT
Safetensors
trl
sft
Generated from Trainer
Model card Files
xet
Community
Striker-7 commited on
Commit
2d019c8
·
verified ·
1 Parent(s): 0255d9c

phi-2-ele

Browse files
Files changed (9) hide show
  1. README.md +2 -2
  2. adapter_config.json +6 -7
  3. adapter_model.safetensors +2 -2
  4. added_tokens.json +11 -38
  5. special_tokens_map.json +2 -2
  6. tokenizer.json +0 -0
  7. tokenizer.model +3 -0
  8. tokenizer_config.json +77 -271
  9. training_args.bin +1 -1
README.md CHANGED
@@ -5,7 +5,7 @@ tags:
5
  - trl
6
  - sft
7
  - generated_from_trainer
8
- base_model: microsoft/phi-2
9
  model-index:
10
  - name: eleres
11
  results: []
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  # eleres
18
 
19
- This model is a fine-tuned version of [microsoft/phi-2](https://huggingface.co/microsoft/phi-2) on an unknown dataset.
20
 
21
  ## Model description
22
 
 
5
  - trl
6
  - sft
7
  - generated_from_trainer
8
+ base_model: microsoft/Phi-3-mini-4k-instruct
9
  model-index:
10
  - name: eleres
11
  results: []
 
16
 
17
  # eleres
18
 
19
+ This model is a fine-tuned version of [microsoft/Phi-3-mini-4k-instruct](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct) on an unknown dataset.
20
 
21
  ## Model description
22
 
adapter_config.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "alpha_pattern": {},
3
  "auto_mapping": null,
4
- "base_model_name_or_path": "microsoft/phi-2",
5
  "bias": "none",
6
  "fan_in_fan_out": false,
7
  "inference_mode": true,
@@ -20,12 +20,11 @@
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
- "v_proj",
24
- "dense",
25
- "q_proj",
26
- "fc1",
27
- "k_proj",
28
- "fc2"
29
  ],
30
  "task_type": "CAUSAL_LM",
31
  "use_dora": false,
 
1
  {
2
  "alpha_pattern": {},
3
  "auto_mapping": null,
4
+ "base_model_name_or_path": "microsoft/Phi-3-mini-4k-instruct",
5
  "bias": "none",
6
  "fan_in_fan_out": false,
7
  "inference_mode": true,
 
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
+ "down_proj",
24
+ "qkv_proj",
25
+ "o_proj",
26
+ "embed_tokens",
27
+ "gate_up_proj"
 
28
  ],
29
  "task_type": "CAUSAL_LM",
30
  "use_dora": false,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5218734d6ce8b761c6beac196e59219180eddbee0ae753361cd3a53a0df652b0
3
- size 94422368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:505b14f9de8092651fbc36d831a6e64433e59ea30710ba83c2acda2649bdf217
3
+ size 496949808
added_tokens.json CHANGED
@@ -1,40 +1,13 @@
1
  {
2
- "\t\t": 50294,
3
- "\t\t\t": 50293,
4
- "\t\t\t\t": 50292,
5
- "\t\t\t\t\t": 50291,
6
- "\t\t\t\t\t\t": 50290,
7
- "\t\t\t\t\t\t\t": 50289,
8
- "\t\t\t\t\t\t\t\t": 50288,
9
- "\t\t\t\t\t\t\t\t\t": 50287,
10
- " ": 50286,
11
- " ": 50285,
12
- " ": 50284,
13
- " ": 50283,
14
- " ": 50282,
15
- " ": 50281,
16
- " ": 50280,
17
- " ": 50279,
18
- " ": 50278,
19
- " ": 50277,
20
- " ": 50276,
21
- " ": 50275,
22
- " ": 50274,
23
- " ": 50273,
24
- " ": 50272,
25
- " ": 50271,
26
- " ": 50270,
27
- " ": 50269,
28
- " ": 50268,
29
- " ": 50267,
30
- " ": 50266,
31
- " ": 50265,
32
- " ": 50264,
33
- " ": 50263,
34
- " ": 50262,
35
- " ": 50261,
36
- " ": 50260,
37
- " ": 50259,
38
- " ": 50258,
39
- " ": 50257
40
  }
 
1
  {
2
+ "<|assistant|>": 32001,
3
+ "<|endoftext|>": 32000,
4
+ "<|end|>": 32007,
5
+ "<|placeholder1|>": 32002,
6
+ "<|placeholder2|>": 32003,
7
+ "<|placeholder3|>": 32004,
8
+ "<|placeholder4|>": 32005,
9
+ "<|placeholder5|>": 32008,
10
+ "<|placeholder6|>": 32009,
11
+ "<|system|>": 32006,
12
+ "<|user|>": 32010
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
13
  }
special_tokens_map.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "bos_token": {
3
- "content": "<|endoftext|>",
4
  "lstrip": false,
5
  "normalized": false,
6
  "rstrip": false,
@@ -15,7 +15,7 @@
15
  },
16
  "pad_token": "<|endoftext|>",
17
  "unk_token": {
18
- "content": "<|endoftext|>",
19
  "lstrip": false,
20
  "normalized": false,
21
  "rstrip": false,
 
1
  {
2
  "bos_token": {
3
+ "content": "<s>",
4
  "lstrip": false,
5
  "normalized": false,
6
  "rstrip": false,
 
15
  },
16
  "pad_token": "<|endoftext|>",
17
  "unk_token": {
18
+ "content": "<unk>",
19
  "lstrip": false,
20
  "normalized": false,
21
  "rstrip": false,
tokenizer.json CHANGED
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 sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json CHANGED
@@ -1,325 +1,131 @@
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
- "50257": {
13
- "content": " ",
14
- "lstrip": false,
15
- "normalized": true,
16
- "rstrip": false,
17
- "single_word": false,
18
- "special": false
19
- },
20
- "50258": {
21
- "content": " ",
22
- "lstrip": false,
23
- "normalized": true,
24
- "rstrip": false,
25
- "single_word": false,
26
- "special": false
27
- },
28
- "50259": {
29
- "content": " ",
30
- "lstrip": false,
31
- "normalized": true,
32
- "rstrip": false,
33
- "single_word": false,
34
- "special": false
35
- },
36
- "50260": {
37
- "content": " ",
38
- "lstrip": false,
39
- "normalized": true,
40
- "rstrip": false,
41
- "single_word": false,
42
- "special": false
43
- },
44
- "50261": {
45
- "content": " ",
46
- "lstrip": false,
47
- "normalized": true,
48
- "rstrip": false,
49
- "single_word": false,
50
- "special": false
51
- },
52
- "50262": {
53
- "content": " ",
54
- "lstrip": false,
55
- "normalized": true,
56
- "rstrip": false,
57
- "single_word": false,
58
- "special": false
59
- },
60
- "50263": {
61
- "content": " ",
62
- "lstrip": false,
63
- "normalized": true,
64
- "rstrip": false,
65
- "single_word": false,
66
- "special": false
67
- },
68
- "50264": {
69
- "content": " ",
70
- "lstrip": false,
71
- "normalized": true,
72
- "rstrip": false,
73
- "single_word": false,
74
- "special": false
75
- },
76
- "50265": {
77
- "content": " ",
78
- "lstrip": false,
79
- "normalized": true,
80
- "rstrip": false,
81
- "single_word": false,
82
- "special": false
83
- },
84
- "50266": {
85
- "content": " ",
86
- "lstrip": false,
87
- "normalized": true,
88
- "rstrip": false,
89
- "single_word": false,
90
- "special": false
91
- },
92
- "50267": {
93
- "content": " ",
94
- "lstrip": false,
95
- "normalized": true,
96
- "rstrip": false,
97
- "single_word": false,
98
- "special": false
99
- },
100
- "50268": {
101
- "content": " ",
102
- "lstrip": false,
103
- "normalized": true,
104
- "rstrip": false,
105
- "single_word": false,
106
- "special": false
107
- },
108
- "50269": {
109
- "content": " ",
110
- "lstrip": false,
111
- "normalized": true,
112
- "rstrip": false,
113
- "single_word": false,
114
- "special": false
115
- },
116
- "50270": {
117
- "content": " ",
118
  "lstrip": false,
119
- "normalized": true,
120
- "rstrip": false,
121
- "single_word": false,
122
- "special": false
123
- },
124
- "50271": {
125
- "content": " ",
126
- "lstrip": false,
127
- "normalized": true,
128
- "rstrip": false,
129
- "single_word": false,
130
- "special": false
131
- },
132
- "50272": {
133
- "content": " ",
134
- "lstrip": false,
135
- "normalized": true,
136
- "rstrip": false,
137
- "single_word": false,
138
- "special": false
139
- },
140
- "50273": {
141
- "content": " ",
142
- "lstrip": false,
143
- "normalized": true,
144
- "rstrip": false,
145
- "single_word": false,
146
- "special": false
147
- },
148
- "50274": {
149
- "content": " ",
150
- "lstrip": false,
151
- "normalized": true,
152
- "rstrip": false,
153
- "single_word": false,
154
- "special": false
155
- },
156
- "50275": {
157
- "content": " ",
158
- "lstrip": false,
159
- "normalized": true,
160
- "rstrip": false,
161
- "single_word": false,
162
- "special": false
163
- },
164
- "50276": {
165
- "content": " ",
166
- "lstrip": false,
167
- "normalized": true,
168
- "rstrip": false,
169
- "single_word": false,
170
- "special": false
171
- },
172
- "50277": {
173
- "content": " ",
174
- "lstrip": false,
175
- "normalized": true,
176
- "rstrip": false,
177
- "single_word": false,
178
- "special": false
179
- },
180
- "50278": {
181
- "content": " ",
182
- "lstrip": false,
183
- "normalized": true,
184
- "rstrip": false,
185
- "single_word": false,
186
- "special": false
187
- },
188
- "50279": {
189
- "content": " ",
190
- "lstrip": false,
191
- "normalized": true,
192
- "rstrip": false,
193
- "single_word": false,
194
- "special": false
195
- },
196
- "50280": {
197
- "content": " ",
198
- "lstrip": false,
199
- "normalized": true,
200
- "rstrip": false,
201
- "single_word": false,
202
- "special": false
203
- },
204
- "50281": {
205
- "content": " ",
206
- "lstrip": false,
207
- "normalized": true,
208
- "rstrip": false,
209
- "single_word": false,
210
- "special": false
211
- },
212
- "50282": {
213
- "content": " ",
214
- "lstrip": false,
215
- "normalized": true,
216
  "rstrip": false,
217
  "single_word": false,
218
- "special": false
219
  },
220
- "50283": {
221
- "content": " ",
222
  "lstrip": false,
223
- "normalized": true,
224
- "rstrip": false,
225
  "single_word": false,
226
  "special": false
227
  },
228
- "50284": {
229
- "content": " ",
230
  "lstrip": false,
231
- "normalized": true,
232
  "rstrip": false,
233
  "single_word": false,
234
- "special": false
235
  },
236
- "50285": {
237
- "content": " ",
238
  "lstrip": false,
239
- "normalized": true,
240
- "rstrip": false,
241
  "single_word": false,
242
- "special": false
243
  },
244
- "50286": {
245
- "content": " ",
246
  "lstrip": false,
247
- "normalized": true,
248
- "rstrip": false,
249
  "single_word": false,
250
- "special": false
251
  },
252
- "50287": {
253
- "content": "\t\t\t\t\t\t\t\t\t",
254
  "lstrip": false,
255
- "normalized": true,
256
- "rstrip": false,
257
  "single_word": false,
258
- "special": false
259
  },
260
- "50288": {
261
- "content": "\t\t\t\t\t\t\t\t",
262
  "lstrip": false,
263
- "normalized": true,
264
- "rstrip": false,
265
  "single_word": false,
266
- "special": false
267
  },
268
- "50289": {
269
- "content": "\t\t\t\t\t\t\t",
270
  "lstrip": false,
271
- "normalized": true,
272
- "rstrip": false,
273
  "single_word": false,
274
- "special": false
275
  },
276
- "50290": {
277
- "content": "\t\t\t\t\t\t",
278
  "lstrip": false,
279
- "normalized": true,
280
- "rstrip": false,
281
  "single_word": false,
282
- "special": false
283
  },
284
- "50291": {
285
- "content": "\t\t\t\t\t",
286
  "lstrip": false,
287
- "normalized": true,
288
- "rstrip": false,
289
  "single_word": false,
290
- "special": false
291
  },
292
- "50292": {
293
- "content": "\t\t\t\t",
294
  "lstrip": false,
295
- "normalized": true,
296
- "rstrip": false,
297
  "single_word": false,
298
- "special": false
299
  },
300
- "50293": {
301
- "content": "\t\t\t",
302
  "lstrip": false,
303
- "normalized": true,
304
- "rstrip": false,
305
  "single_word": false,
306
- "special": false
307
  },
308
- "50294": {
309
- "content": "\t\t",
310
  "lstrip": false,
311
- "normalized": true,
312
- "rstrip": false,
313
  "single_word": false,
314
- "special": false
315
  }
316
  },
317
- "bos_token": "<|endoftext|>",
318
- "clean_up_tokenization_spaces": true,
 
319
  "eos_token": "<|endoftext|>",
320
- "model_max_length": 2048,
 
321
  "pad_token": "<|endoftext|>",
322
- "return_token_type_ids": false,
323
- "tokenizer_class": "CodeGenTokenizer",
324
- "unk_token": "<|endoftext|>"
 
 
325
  }
 
1
  {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
5
  "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
  "lstrip": false,
9
  "normalized": false,
10
  "rstrip": false,
11
  "single_word": false,
12
  "special": true
13
  },
14
+ "1": {
15
+ "content": "<s>",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
16
  "lstrip": false,
17
+ "normalized": false,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
18
  "rstrip": false,
19
  "single_word": false,
20
+ "special": true
21
  },
22
+ "2": {
23
+ "content": "</s>",
24
  "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": true,
27
  "single_word": false,
28
  "special": false
29
  },
30
+ "32000": {
31
+ "content": "<|endoftext|>",
32
  "lstrip": false,
33
+ "normalized": false,
34
  "rstrip": false,
35
  "single_word": false,
36
+ "special": true
37
  },
38
+ "32001": {
39
+ "content": "<|assistant|>",
40
  "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": true,
43
  "single_word": false,
44
+ "special": true
45
  },
46
+ "32002": {
47
+ "content": "<|placeholder1|>",
48
  "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": true,
51
  "single_word": false,
52
+ "special": true
53
  },
54
+ "32003": {
55
+ "content": "<|placeholder2|>",
56
  "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": true,
59
  "single_word": false,
60
+ "special": true
61
  },
62
+ "32004": {
63
+ "content": "<|placeholder3|>",
64
  "lstrip": false,
65
+ "normalized": false,
66
+ "rstrip": true,
67
  "single_word": false,
68
+ "special": true
69
  },
70
+ "32005": {
71
+ "content": "<|placeholder4|>",
72
  "lstrip": false,
73
+ "normalized": false,
74
+ "rstrip": true,
75
  "single_word": false,
76
+ "special": true
77
  },
78
+ "32006": {
79
+ "content": "<|system|>",
80
  "lstrip": false,
81
+ "normalized": false,
82
+ "rstrip": true,
83
  "single_word": false,
84
+ "special": true
85
  },
86
+ "32007": {
87
+ "content": "<|end|>",
88
  "lstrip": false,
89
+ "normalized": false,
90
+ "rstrip": true,
91
  "single_word": false,
92
+ "special": true
93
  },
94
+ "32008": {
95
+ "content": "<|placeholder5|>",
96
  "lstrip": false,
97
+ "normalized": false,
98
+ "rstrip": true,
99
  "single_word": false,
100
+ "special": true
101
  },
102
+ "32009": {
103
+ "content": "<|placeholder6|>",
104
  "lstrip": false,
105
+ "normalized": false,
106
+ "rstrip": true,
107
  "single_word": false,
108
+ "special": true
109
  },
110
+ "32010": {
111
+ "content": "<|user|>",
112
  "lstrip": false,
113
+ "normalized": false,
114
+ "rstrip": true,
115
  "single_word": false,
116
+ "special": true
117
  }
118
  },
119
+ "bos_token": "<s>",
120
+ "chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}{{'<|system|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'user' %}{{'<|user|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>\n' + message['content'] + '<|end|>\n'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
121
+ "clean_up_tokenization_spaces": false,
122
  "eos_token": "<|endoftext|>",
123
+ "legacy": false,
124
+ "model_max_length": 4096,
125
  "pad_token": "<|endoftext|>",
126
+ "padding_side": "left",
127
+ "sp_model_kwargs": {},
128
+ "tokenizer_class": "LlamaTokenizer",
129
+ "unk_token": "<unk>",
130
+ "use_default_system_prompt": false
131
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:478f84817af86eece2b95080e23f9df0db02cd4bd004fbdf29dcf98ef12226e4
3
  size 5368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72263f36057cbf194dda05734719904b9b048d9ee4d25b445c0aff0aa0d0ab50
3
  size 5368