nicholasKluge commited on
Commit
f9cb5e7
·
verified ·
1 Parent(s): a973491

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "head_dim": 96,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 1536,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "is_llama_config": true,
15
+ "max_position_embeddings": 4096,
16
+ "mlp_bias": false,
17
+ "model_type": "llama",
18
+ "num_attention_heads": 16,
19
+ "num_hidden_layers": 28,
20
+ "num_key_value_heads": 8,
21
+ "pad_token_id": 49109,
22
+ "pretraining_tp": 1,
23
+ "rms_norm_eps": 1e-06,
24
+ "rope_interleaved": false,
25
+ "rope_scaling": null,
26
+ "rope_theta": 50000.0,
27
+ "tie_word_embeddings": true,
28
+ "torch_dtype": "bfloat16",
29
+ "transformers_version": "4.53.2",
30
+ "use_cache": false,
31
+ "vocab_size": 49152
32
+ }
evals.yaml ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ evaluations:
2
+ ARC Challenge: 0.2617621899059025
3
+ Bangla MMLU: 0.2608813559322034
4
+ BoolQ-BN: 0.6064814814814815
5
+ CommonsenseQA-BN: 0.3243243243243243
6
+ HellaSwag: 0.3220082233282839
7
+ MMLU: 0.2706305716856138
8
+ OpenBookQA-BN: 0.3219315895372233
9
+ PIQA-BN: 0.6050054406964092
10
+ TruthfulQA MC1: 0.2548015364916773
11
+ step: 110000
generation_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 1,
3
+ "eos_token_id": 2,
4
+ "pad_token_id": 49109,
5
+ "transformers_version": "4.53.2",
6
+ "do_sample": true,
7
+ "max_new_tokens": 1024,
8
+ "renormalize_logits": true,
9
+ "repetition_penalty": 1.2,
10
+ "temperature": 0.1,
11
+ "top_k": 50,
12
+ "top_p": 1.0,
13
+ "use_cache": false
14
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80512d1532273e0969e5f2aafe07a9cd44e9433d858c263ec1fa7ad6fe2e9dea
3
+ size 1340284304
special_tokens_map.json ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<tools>",
4
+ "</tools>",
5
+ "<tool_call>",
6
+ "</tool_call>",
7
+ "<tool_response>",
8
+ "</tool_response>",
9
+ "<think>",
10
+ "</think>",
11
+ "<answer>",
12
+ "</answer>",
13
+ "<context>",
14
+ "</context>",
15
+ "<|fim_prefix|>",
16
+ "<|fim_suffix|>",
17
+ "<|fim_middle|>",
18
+ "<|repo_name|>",
19
+ "<|image|>",
20
+ "<|image_pad|>",
21
+ "<|image_placeholder|>",
22
+ " ",
23
+ " ",
24
+ " ",
25
+ " ",
26
+ " ",
27
+ " ",
28
+ " ",
29
+ " ",
30
+ " ",
31
+ " ",
32
+ " ",
33
+ " ",
34
+ " ",
35
+ " ",
36
+ " ",
37
+ " ",
38
+ " ",
39
+ " ",
40
+ " ",
41
+ " ",
42
+ " ",
43
+ " ",
44
+ " "
45
+ ],
46
+ "bos_token": {
47
+ "content": "<|im_start|>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": false,
51
+ "single_word": false
52
+ },
53
+ "eos_token": {
54
+ "content": "<|im_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false
59
+ },
60
+ "pad_token": {
61
+ "content": "<|pad|>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false
66
+ },
67
+ "unk_token": {
68
+ "content": "<|unk|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false
73
+ }
74
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,436 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<|im_start|>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "<|im_end|>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ },
30
+ "49109": {
31
+ "content": "<|pad|>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "49110": {
39
+ "content": "<tools>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": true
45
+ },
46
+ "49111": {
47
+ "content": "</tools>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": false,
51
+ "single_word": false,
52
+ "special": true
53
+ },
54
+ "49112": {
55
+ "content": "<tool_call>",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": false,
59
+ "single_word": false,
60
+ "special": true
61
+ },
62
+ "49113": {
63
+ "content": "</tool_call>",
64
+ "lstrip": false,
65
+ "normalized": false,
66
+ "rstrip": false,
67
+ "single_word": false,
68
+ "special": true
69
+ },
70
+ "49114": {
71
+ "content": "<tool_response>",
72
+ "lstrip": false,
73
+ "normalized": false,
74
+ "rstrip": false,
75
+ "single_word": false,
76
+ "special": true
77
+ },
78
+ "49115": {
79
+ "content": "</tool_response>",
80
+ "lstrip": false,
81
+ "normalized": false,
82
+ "rstrip": false,
83
+ "single_word": false,
84
+ "special": true
85
+ },
86
+ "49116": {
87
+ "content": "<think>",
88
+ "lstrip": false,
89
+ "normalized": false,
90
+ "rstrip": false,
91
+ "single_word": false,
92
+ "special": true
93
+ },
94
+ "49117": {
95
+ "content": "</think>",
96
+ "lstrip": false,
97
+ "normalized": false,
98
+ "rstrip": false,
99
+ "single_word": false,
100
+ "special": true
101
+ },
102
+ "49118": {
103
+ "content": "<answer>",
104
+ "lstrip": false,
105
+ "normalized": false,
106
+ "rstrip": false,
107
+ "single_word": false,
108
+ "special": true
109
+ },
110
+ "49119": {
111
+ "content": "</answer>",
112
+ "lstrip": false,
113
+ "normalized": false,
114
+ "rstrip": false,
115
+ "single_word": false,
116
+ "special": true
117
+ },
118
+ "49120": {
119
+ "content": "<context>",
120
+ "lstrip": false,
121
+ "normalized": false,
122
+ "rstrip": false,
123
+ "single_word": false,
124
+ "special": true
125
+ },
126
+ "49121": {
127
+ "content": "</context>",
128
+ "lstrip": false,
129
+ "normalized": false,
130
+ "rstrip": false,
131
+ "single_word": false,
132
+ "special": true
133
+ },
134
+ "49122": {
135
+ "content": "<|fim_prefix|>",
136
+ "lstrip": false,
137
+ "normalized": false,
138
+ "rstrip": false,
139
+ "single_word": false,
140
+ "special": true
141
+ },
142
+ "49123": {
143
+ "content": "<|fim_suffix|>",
144
+ "lstrip": false,
145
+ "normalized": false,
146
+ "rstrip": false,
147
+ "single_word": false,
148
+ "special": true
149
+ },
150
+ "49124": {
151
+ "content": "<|fim_middle|>",
152
+ "lstrip": false,
153
+ "normalized": false,
154
+ "rstrip": false,
155
+ "single_word": false,
156
+ "special": true
157
+ },
158
+ "49125": {
159
+ "content": "<|repo_name|>",
160
+ "lstrip": false,
161
+ "normalized": false,
162
+ "rstrip": false,
163
+ "single_word": false,
164
+ "special": true
165
+ },
166
+ "49126": {
167
+ "content": "<|image|>",
168
+ "lstrip": false,
169
+ "normalized": false,
170
+ "rstrip": false,
171
+ "single_word": false,
172
+ "special": true
173
+ },
174
+ "49127": {
175
+ "content": "<|image_pad|>",
176
+ "lstrip": false,
177
+ "normalized": false,
178
+ "rstrip": false,
179
+ "single_word": false,
180
+ "special": true
181
+ },
182
+ "49128": {
183
+ "content": "<|image_placeholder|>",
184
+ "lstrip": false,
185
+ "normalized": false,
186
+ "rstrip": false,
187
+ "single_word": false,
188
+ "special": true
189
+ },
190
+ "49129": {
191
+ "content": " ",
192
+ "lstrip": false,
193
+ "normalized": false,
194
+ "rstrip": false,
195
+ "single_word": false,
196
+ "special": true
197
+ },
198
+ "49130": {
199
+ "content": " ",
200
+ "lstrip": false,
201
+ "normalized": false,
202
+ "rstrip": false,
203
+ "single_word": false,
204
+ "special": true
205
+ },
206
+ "49131": {
207
+ "content": " ",
208
+ "lstrip": false,
209
+ "normalized": false,
210
+ "rstrip": false,
211
+ "single_word": false,
212
+ "special": true
213
+ },
214
+ "49132": {
215
+ "content": " ",
216
+ "lstrip": false,
217
+ "normalized": false,
218
+ "rstrip": false,
219
+ "single_word": false,
220
+ "special": true
221
+ },
222
+ "49133": {
223
+ "content": " ",
224
+ "lstrip": false,
225
+ "normalized": false,
226
+ "rstrip": false,
227
+ "single_word": false,
228
+ "special": true
229
+ },
230
+ "49134": {
231
+ "content": " ",
232
+ "lstrip": false,
233
+ "normalized": false,
234
+ "rstrip": false,
235
+ "single_word": false,
236
+ "special": true
237
+ },
238
+ "49135": {
239
+ "content": " ",
240
+ "lstrip": false,
241
+ "normalized": false,
242
+ "rstrip": false,
243
+ "single_word": false,
244
+ "special": true
245
+ },
246
+ "49136": {
247
+ "content": " ",
248
+ "lstrip": false,
249
+ "normalized": false,
250
+ "rstrip": false,
251
+ "single_word": false,
252
+ "special": true
253
+ },
254
+ "49137": {
255
+ "content": " ",
256
+ "lstrip": false,
257
+ "normalized": false,
258
+ "rstrip": false,
259
+ "single_word": false,
260
+ "special": true
261
+ },
262
+ "49138": {
263
+ "content": " ",
264
+ "lstrip": false,
265
+ "normalized": false,
266
+ "rstrip": false,
267
+ "single_word": false,
268
+ "special": true
269
+ },
270
+ "49139": {
271
+ "content": " ",
272
+ "lstrip": false,
273
+ "normalized": false,
274
+ "rstrip": false,
275
+ "single_word": false,
276
+ "special": true
277
+ },
278
+ "49140": {
279
+ "content": " ",
280
+ "lstrip": false,
281
+ "normalized": false,
282
+ "rstrip": false,
283
+ "single_word": false,
284
+ "special": true
285
+ },
286
+ "49141": {
287
+ "content": " ",
288
+ "lstrip": false,
289
+ "normalized": false,
290
+ "rstrip": false,
291
+ "single_word": false,
292
+ "special": true
293
+ },
294
+ "49142": {
295
+ "content": " ",
296
+ "lstrip": false,
297
+ "normalized": false,
298
+ "rstrip": false,
299
+ "single_word": false,
300
+ "special": true
301
+ },
302
+ "49143": {
303
+ "content": " ",
304
+ "lstrip": false,
305
+ "normalized": false,
306
+ "rstrip": false,
307
+ "single_word": false,
308
+ "special": true
309
+ },
310
+ "49144": {
311
+ "content": " ",
312
+ "lstrip": false,
313
+ "normalized": false,
314
+ "rstrip": false,
315
+ "single_word": false,
316
+ "special": true
317
+ },
318
+ "49145": {
319
+ "content": " ",
320
+ "lstrip": false,
321
+ "normalized": false,
322
+ "rstrip": false,
323
+ "single_word": false,
324
+ "special": true
325
+ },
326
+ "49146": {
327
+ "content": " ",
328
+ "lstrip": false,
329
+ "normalized": false,
330
+ "rstrip": false,
331
+ "single_word": false,
332
+ "special": true
333
+ },
334
+ "49147": {
335
+ "content": " ",
336
+ "lstrip": false,
337
+ "normalized": false,
338
+ "rstrip": false,
339
+ "single_word": false,
340
+ "special": true
341
+ },
342
+ "49148": {
343
+ "content": " ",
344
+ "lstrip": false,
345
+ "normalized": false,
346
+ "rstrip": false,
347
+ "single_word": false,
348
+ "special": true
349
+ },
350
+ "49149": {
351
+ "content": " ",
352
+ "lstrip": false,
353
+ "normalized": false,
354
+ "rstrip": false,
355
+ "single_word": false,
356
+ "special": true
357
+ },
358
+ "49150": {
359
+ "content": " ",
360
+ "lstrip": false,
361
+ "normalized": false,
362
+ "rstrip": false,
363
+ "single_word": false,
364
+ "special": true
365
+ },
366
+ "49151": {
367
+ "content": " ",
368
+ "lstrip": false,
369
+ "normalized": false,
370
+ "rstrip": false,
371
+ "single_word": false,
372
+ "special": true
373
+ }
374
+ },
375
+ "additional_special_tokens": [
376
+ "<tools>",
377
+ "</tools>",
378
+ "<tool_call>",
379
+ "</tool_call>",
380
+ "<tool_response>",
381
+ "</tool_response>",
382
+ "<think>",
383
+ "</think>",
384
+ "<answer>",
385
+ "</answer>",
386
+ "<context>",
387
+ "</context>",
388
+ "<|fim_prefix|>",
389
+ "<|fim_suffix|>",
390
+ "<|fim_middle|>",
391
+ "<|repo_name|>",
392
+ "<|image|>",
393
+ "<|image_pad|>",
394
+ "<|image_placeholder|>",
395
+ " ",
396
+ " ",
397
+ " ",
398
+ " ",
399
+ " ",
400
+ " ",
401
+ " ",
402
+ " ",
403
+ " ",
404
+ " ",
405
+ " ",
406
+ " ",
407
+ " ",
408
+ " ",
409
+ " ",
410
+ " ",
411
+ " ",
412
+ " ",
413
+ " ",
414
+ " ",
415
+ " ",
416
+ " ",
417
+ " "
418
+ ],
419
+ "bos_token": "<|im_start|>",
420
+ "bos_token_id": 1,
421
+ "clean_up_tokenization_spaces": false,
422
+ "eos_token": "<|im_end|>",
423
+ "eos_token_id": 2,
424
+ "extra_special_tokens": {},
425
+ "legacy": false,
426
+ "model_max_length": 4096,
427
+ "pad_token": "<|pad|>",
428
+ "pad_token_id": 49109,
429
+ "padding_side": "right",
430
+ "sp_model_kwargs": {},
431
+ "spaces_between_special_tokens": false,
432
+ "tokenizer_class": "PreTrainedTokenizerFast",
433
+ "unk_token": "<|unk|>",
434
+ "unk_token_id": 0,
435
+ "use_default_system_prompt": false
436
+ }