AlopaxalgoWjd5480 commited on
Commit
ce41813
1 Parent(s): 1e2d007

Upload 3 files

Browse files
Files changed (4) hide show
  1. .gitattributes +1 -0
  2. config.json +47 -0
  3. tokenizer.json +3 -0
  4. tokenizer_config.json +320 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "CohereForAI/c4ai-command-r-v01",
3
+ "architectures": [
4
+ "CohereForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "auto_map": {
9
+ "AutoConfig": "CohereForAI/c4ai-command-r-v01--configuration_cohere.CohereConfig",
10
+ "AutoModel": "CohereForAI/c4ai-command-r-v01--configuration_cohere.CohereModel",
11
+ "AutoModelForCausalLM": "CohereForAI/c4ai-command-r-v01--modeling_cohere.CohereForCausalLM"
12
+ },
13
+ "bos_token_id": 5,
14
+ "eos_token_id": 255001,
15
+ "hidden_act": "silu",
16
+ "hidden_size": 8192,
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 22528,
19
+ "layer_norm_eps": 1e-05,
20
+ "logit_scale": 0.0625,
21
+ "max_position_embeddings": 8192,
22
+ "model_type": "cohere",
23
+ "num_attention_heads": 64,
24
+ "num_hidden_layers": 40,
25
+ "num_key_value_heads": 64,
26
+ "pad_token_id": 0,
27
+ "pretraining_tp": 1,
28
+ "quantization_config": {
29
+ "_load_in_4bit": true,
30
+ "_load_in_8bit": false,
31
+ "bnb_4bit_compute_dtype": "bfloat16",
32
+ "bnb_4bit_quant_type": "fp4",
33
+ "bnb_4bit_use_double_quant": false,
34
+ "llm_int8_enable_fp32_cpu_offload": false,
35
+ "llm_int8_has_fp16_weight": false,
36
+ "llm_int8_skip_modules": null,
37
+ "llm_int8_threshold": 6.0,
38
+ "load_in_4bit": true,
39
+ "load_in_8bit": false,
40
+ "quant_method": "bitsandbytes"
41
+ },
42
+ "rope_theta": 8000000.0,
43
+ "torch_dtype": "float16",
44
+ "transformers_version": "4.39.0.dev0",
45
+ "use_cache": true,
46
+ "vocab_size": 256000
47
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0cc8a79eafcf1043fbfad77df083de446a61424b222284d602c4edee497ce1e4
3
+ size 12777405
tokenizer_config.json ADDED
@@ -0,0 +1,320 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<PAD>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<UNK>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "<CLS>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "3": {
30
+ "content": "<SEP>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "4": {
38
+ "content": "<MASK_TOKEN>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "5": {
46
+ "content": "<BOS_TOKEN>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "6": {
54
+ "content": "<EOS_TOKEN>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "7": {
62
+ "content": "<EOP_TOKEN>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "255000": {
70
+ "content": "<|START_OF_TURN_TOKEN|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": false
76
+ },
77
+ "255001": {
78
+ "content": "<|END_OF_TURN_TOKEN|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "255002": {
86
+ "content": "<|YES_TOKEN|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": false
92
+ },
93
+ "255003": {
94
+ "content": "<|NO_TOKEN|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": false
100
+ },
101
+ "255004": {
102
+ "content": "<|GOOD_TOKEN|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": false
108
+ },
109
+ "255005": {
110
+ "content": "<|BAD_TOKEN|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": false
116
+ },
117
+ "255006": {
118
+ "content": "<|USER_TOKEN|>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "255007": {
126
+ "content": "<|CHATBOT_TOKEN|>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "255008": {
134
+ "content": "<|SYSTEM_TOKEN|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "255009": {
142
+ "content": "<|USER_0_TOKEN|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "255010": {
150
+ "content": "<|USER_1_TOKEN|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "255011": {
158
+ "content": "<|USER_2_TOKEN|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "255012": {
166
+ "content": "<|USER_3_TOKEN|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "255013": {
174
+ "content": "<|USER_4_TOKEN|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "255014": {
182
+ "content": "<|USER_5_TOKEN|>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": false
188
+ },
189
+ "255015": {
190
+ "content": "<|USER_6_TOKEN|>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": false
196
+ },
197
+ "255016": {
198
+ "content": "<|USER_7_TOKEN|>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": false
204
+ },
205
+ "255017": {
206
+ "content": "<|USER_8_TOKEN|>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": false
212
+ },
213
+ "255018": {
214
+ "content": "<|USER_9_TOKEN|>",
215
+ "lstrip": false,
216
+ "normalized": false,
217
+ "rstrip": false,
218
+ "single_word": false,
219
+ "special": false
220
+ },
221
+ "255019": {
222
+ "content": "<|EXTRA_0_TOKEN|>",
223
+ "lstrip": false,
224
+ "normalized": false,
225
+ "rstrip": false,
226
+ "single_word": false,
227
+ "special": false
228
+ },
229
+ "255020": {
230
+ "content": "<|EXTRA_1_TOKEN|>",
231
+ "lstrip": false,
232
+ "normalized": false,
233
+ "rstrip": false,
234
+ "single_word": false,
235
+ "special": false
236
+ },
237
+ "255021": {
238
+ "content": "<|EXTRA_2_TOKEN|>",
239
+ "lstrip": false,
240
+ "normalized": false,
241
+ "rstrip": false,
242
+ "single_word": false,
243
+ "special": false
244
+ },
245
+ "255022": {
246
+ "content": "<|EXTRA_3_TOKEN|>",
247
+ "lstrip": false,
248
+ "normalized": false,
249
+ "rstrip": false,
250
+ "single_word": false,
251
+ "special": false
252
+ },
253
+ "255023": {
254
+ "content": "<|EXTRA_4_TOKEN|>",
255
+ "lstrip": false,
256
+ "normalized": false,
257
+ "rstrip": false,
258
+ "single_word": false,
259
+ "special": false
260
+ },
261
+ "255024": {
262
+ "content": "<|EXTRA_5_TOKEN|>",
263
+ "lstrip": false,
264
+ "normalized": false,
265
+ "rstrip": false,
266
+ "single_word": false,
267
+ "special": false
268
+ },
269
+ "255025": {
270
+ "content": "<|EXTRA_6_TOKEN|>",
271
+ "lstrip": false,
272
+ "normalized": false,
273
+ "rstrip": false,
274
+ "single_word": false,
275
+ "special": false
276
+ },
277
+ "255026": {
278
+ "content": "<|EXTRA_7_TOKEN|>",
279
+ "lstrip": false,
280
+ "normalized": false,
281
+ "rstrip": false,
282
+ "single_word": false,
283
+ "special": false
284
+ },
285
+ "255027": {
286
+ "content": "<|EXTRA_8_TOKEN|>",
287
+ "lstrip": false,
288
+ "normalized": false,
289
+ "rstrip": false,
290
+ "single_word": false,
291
+ "special": false
292
+ },
293
+ "255028": {
294
+ "content": "<|EXTRA_9_TOKEN|>",
295
+ "lstrip": false,
296
+ "normalized": false,
297
+ "rstrip": false,
298
+ "single_word": false,
299
+ "special": false
300
+ }
301
+ },
302
+ "auto_map": {
303
+ "AutoTokenizer": [
304
+ null,
305
+ "CohereForAI/c4ai-command-r-v01--tokenization_cohere_fast.CohereTokenizerFast"
306
+ ]
307
+ },
308
+ "bos_token": "<BOS_TOKEN>",
309
+ "chat_template": "<BOS_TOKEN>{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{{ '<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>' + system_message + '<|END_OF_TURN_TOKEN|>' }}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message.role == 'user' %}<|START_OF_TURN_TOKEN|><|USER_TOKEN|>{{ message.content }}<|END_OF_TURN_TOKEN|>\n{% elif message.role == 'assistant' %}<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>{{ message.content }}<|END_OF_TURN_TOKEN|>{% endif %}{% endfor %}{% if add_generation_prompt %}<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>{% endif %}",
310
+ "clean_up_tokenization_spaces": false,
311
+ "eos_token": "<|END_OF_TURN_TOKEN|>",
312
+ "legacy": true,
313
+ "model_max_length": 1000000000000000019884624838656,
314
+ "pad_token": "<PAD>",
315
+ "sp_model_kwargs": {},
316
+ "spaces_between_special_tokens": false,
317
+ "tokenizer_class": "CohereTokenizer",
318
+ "unk_token": null,
319
+ "use_default_system_prompt": false
320
+ }