Shubhra Pandit commited on
Commit
ffe6ea4
·
1 Parent(s): ff8f320

Upload model files

Browse files
config.json ADDED
@@ -0,0 +1,355 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "ibm-granite/granite-3.1-8b-base",
3
+ "architectures": [
4
+ "GraniteForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.1,
8
+ "attention_multiplier": 0.0078125,
9
+ "bos_token_id": 0,
10
+ "embedding_multiplier": 12.0,
11
+ "eos_token_id": 0,
12
+ "hidden_act": "silu",
13
+ "hidden_size": 4096,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 12800,
16
+ "logits_scaling": 16.0,
17
+ "max_position_embeddings": 131072,
18
+ "mlp_bias": false,
19
+ "model_type": "granite",
20
+ "num_attention_heads": 32,
21
+ "num_hidden_layers": 40,
22
+ "num_key_value_heads": 8,
23
+ "pad_token_id": 0,
24
+ "quantization_config": {
25
+ "config_groups": {
26
+ "group_0": {
27
+ "input_activations": null,
28
+ "output_activations": null,
29
+ "targets": [
30
+ "Linear"
31
+ ],
32
+ "weights": {
33
+ "actorder": "weight",
34
+ "block_structure": null,
35
+ "dynamic": false,
36
+ "group_size": 128,
37
+ "num_bits": 4,
38
+ "observer": "mse",
39
+ "observer_kwargs": {},
40
+ "strategy": "group",
41
+ "symmetric": true,
42
+ "type": "int"
43
+ }
44
+ }
45
+ },
46
+ "format": "pack-quantized",
47
+ "global_compression_ratio": 2.0797148031390904,
48
+ "ignore": [
49
+ "lm_head"
50
+ ],
51
+ "kv_cache_scheme": null,
52
+ "quant_method": "compressed-tensors",
53
+ "quantization_status": "compressed",
54
+ "sparsity_config": {
55
+ "format": "dense",
56
+ "global_sparsity": 0.15342155897542373,
57
+ "ignore": [
58
+ "model.layers.0.self_attn.q_proj",
59
+ "model.layers.0.self_attn.k_proj",
60
+ "model.layers.0.self_attn.v_proj",
61
+ "model.layers.0.self_attn.o_proj",
62
+ "model.layers.0.mlp.gate_proj",
63
+ "model.layers.0.mlp.up_proj",
64
+ "model.layers.0.mlp.down_proj",
65
+ "model.layers.1.self_attn.q_proj",
66
+ "model.layers.1.self_attn.k_proj",
67
+ "model.layers.1.self_attn.v_proj",
68
+ "model.layers.1.self_attn.o_proj",
69
+ "model.layers.1.mlp.gate_proj",
70
+ "model.layers.1.mlp.up_proj",
71
+ "model.layers.1.mlp.down_proj",
72
+ "model.layers.2.self_attn.q_proj",
73
+ "model.layers.2.self_attn.k_proj",
74
+ "model.layers.2.self_attn.v_proj",
75
+ "model.layers.2.self_attn.o_proj",
76
+ "model.layers.2.mlp.gate_proj",
77
+ "model.layers.2.mlp.up_proj",
78
+ "model.layers.2.mlp.down_proj",
79
+ "model.layers.3.self_attn.q_proj",
80
+ "model.layers.3.self_attn.k_proj",
81
+ "model.layers.3.self_attn.v_proj",
82
+ "model.layers.3.self_attn.o_proj",
83
+ "model.layers.3.mlp.gate_proj",
84
+ "model.layers.3.mlp.up_proj",
85
+ "model.layers.3.mlp.down_proj",
86
+ "model.layers.4.self_attn.q_proj",
87
+ "model.layers.4.self_attn.k_proj",
88
+ "model.layers.4.self_attn.v_proj",
89
+ "model.layers.4.self_attn.o_proj",
90
+ "model.layers.4.mlp.gate_proj",
91
+ "model.layers.4.mlp.up_proj",
92
+ "model.layers.4.mlp.down_proj",
93
+ "model.layers.5.self_attn.q_proj",
94
+ "model.layers.5.self_attn.k_proj",
95
+ "model.layers.5.self_attn.v_proj",
96
+ "model.layers.5.self_attn.o_proj",
97
+ "model.layers.5.mlp.gate_proj",
98
+ "model.layers.5.mlp.up_proj",
99
+ "model.layers.5.mlp.down_proj",
100
+ "model.layers.6.self_attn.q_proj",
101
+ "model.layers.6.self_attn.k_proj",
102
+ "model.layers.6.self_attn.v_proj",
103
+ "model.layers.6.self_attn.o_proj",
104
+ "model.layers.6.mlp.gate_proj",
105
+ "model.layers.6.mlp.up_proj",
106
+ "model.layers.6.mlp.down_proj",
107
+ "model.layers.7.self_attn.q_proj",
108
+ "model.layers.7.self_attn.k_proj",
109
+ "model.layers.7.self_attn.v_proj",
110
+ "model.layers.7.self_attn.o_proj",
111
+ "model.layers.7.mlp.gate_proj",
112
+ "model.layers.7.mlp.up_proj",
113
+ "model.layers.7.mlp.down_proj",
114
+ "model.layers.8.self_attn.q_proj",
115
+ "model.layers.8.self_attn.k_proj",
116
+ "model.layers.8.self_attn.v_proj",
117
+ "model.layers.8.self_attn.o_proj",
118
+ "model.layers.8.mlp.gate_proj",
119
+ "model.layers.8.mlp.up_proj",
120
+ "model.layers.8.mlp.down_proj",
121
+ "model.layers.9.self_attn.q_proj",
122
+ "model.layers.9.self_attn.k_proj",
123
+ "model.layers.9.self_attn.v_proj",
124
+ "model.layers.9.self_attn.o_proj",
125
+ "model.layers.9.mlp.gate_proj",
126
+ "model.layers.9.mlp.up_proj",
127
+ "model.layers.9.mlp.down_proj",
128
+ "model.layers.10.self_attn.q_proj",
129
+ "model.layers.10.self_attn.k_proj",
130
+ "model.layers.10.self_attn.v_proj",
131
+ "model.layers.10.self_attn.o_proj",
132
+ "model.layers.10.mlp.gate_proj",
133
+ "model.layers.10.mlp.up_proj",
134
+ "model.layers.10.mlp.down_proj",
135
+ "model.layers.11.self_attn.q_proj",
136
+ "model.layers.11.self_attn.k_proj",
137
+ "model.layers.11.self_attn.v_proj",
138
+ "model.layers.11.self_attn.o_proj",
139
+ "model.layers.11.mlp.gate_proj",
140
+ "model.layers.11.mlp.up_proj",
141
+ "model.layers.11.mlp.down_proj",
142
+ "model.layers.12.self_attn.q_proj",
143
+ "model.layers.12.self_attn.k_proj",
144
+ "model.layers.12.self_attn.v_proj",
145
+ "model.layers.12.self_attn.o_proj",
146
+ "model.layers.12.mlp.gate_proj",
147
+ "model.layers.12.mlp.up_proj",
148
+ "model.layers.12.mlp.down_proj",
149
+ "model.layers.13.self_attn.q_proj",
150
+ "model.layers.13.self_attn.k_proj",
151
+ "model.layers.13.self_attn.v_proj",
152
+ "model.layers.13.self_attn.o_proj",
153
+ "model.layers.13.mlp.gate_proj",
154
+ "model.layers.13.mlp.up_proj",
155
+ "model.layers.13.mlp.down_proj",
156
+ "model.layers.14.self_attn.q_proj",
157
+ "model.layers.14.self_attn.k_proj",
158
+ "model.layers.14.self_attn.v_proj",
159
+ "model.layers.14.self_attn.o_proj",
160
+ "model.layers.14.mlp.gate_proj",
161
+ "model.layers.14.mlp.up_proj",
162
+ "model.layers.14.mlp.down_proj",
163
+ "model.layers.15.self_attn.q_proj",
164
+ "model.layers.15.self_attn.k_proj",
165
+ "model.layers.15.self_attn.v_proj",
166
+ "model.layers.15.self_attn.o_proj",
167
+ "model.layers.15.mlp.gate_proj",
168
+ "model.layers.15.mlp.up_proj",
169
+ "model.layers.15.mlp.down_proj",
170
+ "model.layers.16.self_attn.q_proj",
171
+ "model.layers.16.self_attn.k_proj",
172
+ "model.layers.16.self_attn.v_proj",
173
+ "model.layers.16.self_attn.o_proj",
174
+ "model.layers.16.mlp.gate_proj",
175
+ "model.layers.16.mlp.up_proj",
176
+ "model.layers.16.mlp.down_proj",
177
+ "model.layers.17.self_attn.q_proj",
178
+ "model.layers.17.self_attn.k_proj",
179
+ "model.layers.17.self_attn.v_proj",
180
+ "model.layers.17.self_attn.o_proj",
181
+ "model.layers.17.mlp.gate_proj",
182
+ "model.layers.17.mlp.up_proj",
183
+ "model.layers.17.mlp.down_proj",
184
+ "model.layers.18.self_attn.q_proj",
185
+ "model.layers.18.self_attn.k_proj",
186
+ "model.layers.18.self_attn.v_proj",
187
+ "model.layers.18.self_attn.o_proj",
188
+ "model.layers.18.mlp.gate_proj",
189
+ "model.layers.18.mlp.up_proj",
190
+ "model.layers.18.mlp.down_proj",
191
+ "model.layers.19.self_attn.q_proj",
192
+ "model.layers.19.self_attn.k_proj",
193
+ "model.layers.19.self_attn.v_proj",
194
+ "model.layers.19.self_attn.o_proj",
195
+ "model.layers.19.mlp.gate_proj",
196
+ "model.layers.19.mlp.up_proj",
197
+ "model.layers.19.mlp.down_proj",
198
+ "model.layers.20.self_attn.v_proj",
199
+ "model.layers.20.self_attn.o_proj",
200
+ "model.layers.20.mlp.gate_proj",
201
+ "model.layers.20.mlp.up_proj",
202
+ "model.layers.20.mlp.down_proj",
203
+ "model.layers.21.self_attn.q_proj",
204
+ "model.layers.21.self_attn.k_proj",
205
+ "model.layers.21.self_attn.v_proj",
206
+ "model.layers.21.self_attn.o_proj",
207
+ "model.layers.21.mlp.gate_proj",
208
+ "model.layers.21.mlp.up_proj",
209
+ "model.layers.21.mlp.down_proj",
210
+ "model.layers.22.self_attn.q_proj",
211
+ "model.layers.22.self_attn.k_proj",
212
+ "model.layers.22.self_attn.v_proj",
213
+ "model.layers.22.self_attn.o_proj",
214
+ "model.layers.22.mlp.gate_proj",
215
+ "model.layers.22.mlp.up_proj",
216
+ "model.layers.22.mlp.down_proj",
217
+ "model.layers.23.self_attn.v_proj",
218
+ "model.layers.23.self_attn.o_proj",
219
+ "model.layers.23.mlp.gate_proj",
220
+ "model.layers.23.mlp.up_proj",
221
+ "model.layers.23.mlp.down_proj",
222
+ "model.layers.24.self_attn.v_proj",
223
+ "model.layers.24.self_attn.o_proj",
224
+ "model.layers.24.mlp.gate_proj",
225
+ "model.layers.24.mlp.up_proj",
226
+ "model.layers.24.mlp.down_proj",
227
+ "model.layers.25.self_attn.q_proj",
228
+ "model.layers.25.self_attn.k_proj",
229
+ "model.layers.25.self_attn.v_proj",
230
+ "model.layers.25.self_attn.o_proj",
231
+ "model.layers.25.mlp.gate_proj",
232
+ "model.layers.25.mlp.up_proj",
233
+ "model.layers.25.mlp.down_proj",
234
+ "model.layers.26.self_attn.v_proj",
235
+ "model.layers.26.self_attn.o_proj",
236
+ "model.layers.26.mlp.gate_proj",
237
+ "model.layers.26.mlp.up_proj",
238
+ "model.layers.26.mlp.down_proj",
239
+ "model.layers.27.self_attn.v_proj",
240
+ "model.layers.27.self_attn.o_proj",
241
+ "model.layers.27.mlp.gate_proj",
242
+ "model.layers.27.mlp.up_proj",
243
+ "model.layers.27.mlp.down_proj",
244
+ "model.layers.28.self_attn.q_proj",
245
+ "model.layers.28.self_attn.k_proj",
246
+ "model.layers.28.self_attn.v_proj",
247
+ "model.layers.28.self_attn.o_proj",
248
+ "model.layers.28.mlp.gate_proj",
249
+ "model.layers.28.mlp.up_proj",
250
+ "model.layers.28.mlp.down_proj",
251
+ "model.layers.29.self_attn.v_proj",
252
+ "model.layers.29.self_attn.o_proj",
253
+ "model.layers.29.mlp.gate_proj",
254
+ "model.layers.29.mlp.up_proj",
255
+ "model.layers.29.mlp.down_proj",
256
+ "model.layers.30.self_attn.q_proj",
257
+ "model.layers.30.self_attn.k_proj",
258
+ "model.layers.30.self_attn.v_proj",
259
+ "model.layers.30.self_attn.o_proj",
260
+ "model.layers.30.mlp.gate_proj",
261
+ "model.layers.30.mlp.up_proj",
262
+ "model.layers.30.mlp.down_proj",
263
+ "model.layers.31.self_attn.q_proj",
264
+ "model.layers.31.self_attn.k_proj",
265
+ "model.layers.31.self_attn.v_proj",
266
+ "model.layers.31.self_attn.o_proj",
267
+ "model.layers.31.mlp.gate_proj",
268
+ "model.layers.31.mlp.up_proj",
269
+ "model.layers.31.mlp.down_proj",
270
+ "model.layers.32.self_attn.q_proj",
271
+ "model.layers.32.self_attn.k_proj",
272
+ "model.layers.32.self_attn.v_proj",
273
+ "model.layers.32.self_attn.o_proj",
274
+ "model.layers.32.mlp.gate_proj",
275
+ "model.layers.32.mlp.up_proj",
276
+ "model.layers.32.mlp.down_proj",
277
+ "model.layers.33.self_attn.q_proj",
278
+ "model.layers.33.self_attn.k_proj",
279
+ "model.layers.33.self_attn.v_proj",
280
+ "model.layers.33.self_attn.o_proj",
281
+ "model.layers.33.mlp.gate_proj",
282
+ "model.layers.33.mlp.up_proj",
283
+ "model.layers.33.mlp.down_proj",
284
+ "model.layers.34.self_attn.q_proj",
285
+ "model.layers.34.self_attn.k_proj",
286
+ "model.layers.34.self_attn.v_proj",
287
+ "model.layers.34.self_attn.o_proj",
288
+ "model.layers.34.mlp.gate_proj",
289
+ "model.layers.34.mlp.up_proj",
290
+ "model.layers.34.mlp.down_proj",
291
+ "model.layers.35.self_attn.q_proj",
292
+ "model.layers.35.self_attn.k_proj",
293
+ "model.layers.35.self_attn.v_proj",
294
+ "model.layers.35.self_attn.o_proj",
295
+ "model.layers.35.mlp.gate_proj",
296
+ "model.layers.35.mlp.up_proj",
297
+ "model.layers.35.mlp.down_proj",
298
+ "model.layers.36.self_attn.q_proj",
299
+ "model.layers.36.self_attn.k_proj",
300
+ "model.layers.36.self_attn.v_proj",
301
+ "model.layers.36.self_attn.o_proj",
302
+ "model.layers.36.mlp.gate_proj",
303
+ "model.layers.36.mlp.up_proj",
304
+ "model.layers.36.mlp.down_proj",
305
+ "model.layers.37.self_attn.q_proj",
306
+ "model.layers.37.self_attn.k_proj",
307
+ "model.layers.37.self_attn.v_proj",
308
+ "model.layers.37.self_attn.o_proj",
309
+ "model.layers.37.mlp.gate_proj",
310
+ "model.layers.37.mlp.up_proj",
311
+ "model.layers.37.mlp.down_proj",
312
+ "model.layers.38.self_attn.q_proj",
313
+ "model.layers.38.self_attn.k_proj",
314
+ "model.layers.38.self_attn.v_proj",
315
+ "model.layers.38.self_attn.o_proj",
316
+ "model.layers.38.mlp.gate_proj",
317
+ "model.layers.38.mlp.up_proj",
318
+ "model.layers.38.mlp.down_proj",
319
+ "model.layers.39.self_attn.q_proj",
320
+ "model.layers.39.self_attn.k_proj",
321
+ "model.layers.39.self_attn.v_proj",
322
+ "model.layers.39.self_attn.o_proj",
323
+ "model.layers.39.mlp.gate_proj",
324
+ "model.layers.39.mlp.up_proj",
325
+ "model.layers.39.mlp.down_proj",
326
+ "lm_head"
327
+ ],
328
+ "registry_requires_subclass": false,
329
+ "sparsity_structure": "unstructured",
330
+ "targets": [
331
+ "model.layers.20.self_attn.q_proj",
332
+ "model.layers.20.self_attn.k_proj",
333
+ "model.layers.23.self_attn.q_proj",
334
+ "model.layers.23.self_attn.k_proj",
335
+ "model.layers.24.self_attn.q_proj",
336
+ "model.layers.24.self_attn.k_proj",
337
+ "model.layers.26.self_attn.q_proj",
338
+ "model.layers.26.self_attn.k_proj",
339
+ "model.layers.27.self_attn.q_proj",
340
+ "model.layers.27.self_attn.k_proj",
341
+ "model.layers.29.self_attn.q_proj",
342
+ "model.layers.29.self_attn.k_proj"
343
+ ]
344
+ }
345
+ },
346
+ "residual_multiplier": 0.22,
347
+ "rms_norm_eps": 1e-05,
348
+ "rope_scaling": null,
349
+ "rope_theta": 10000000.0,
350
+ "tie_word_embeddings": true,
351
+ "torch_dtype": "bfloat16",
352
+ "transformers_version": "4.48.0",
353
+ "use_cache": true,
354
+ "vocab_size": 49152
355
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 0,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.48.0"
7
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b65d655749c2e94f7b32a5013645b9476a17d6af38f16f4ee40c39bb6ee713a5
3
+ size 4915187088
recipe.yaml ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ quant_stage:
2
+ quant_modifiers:
3
+ GPTQModifier:
4
+ sequential_update: true
5
+ dampening_frac: 0.1
6
+ ignore: [lm_head]
7
+ config_groups:
8
+ group_0:
9
+ weights: {num_bits: 4, type: int, symmetric: true, strategy: group, group_size: 128,
10
+ observer: mse, actorder: weight}
11
+ targets: [Linear]
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|endoftext|>",
4
+ "<fim_prefix>",
5
+ "<fim_middle>",
6
+ "<fim_suffix>",
7
+ "<fim_pad>",
8
+ "<filename>",
9
+ "<gh_stars>",
10
+ "<issue_start>",
11
+ "<issue_comment>",
12
+ "<issue_closed>",
13
+ "<jupyter_start>",
14
+ "<jupyter_text>",
15
+ "<jupyter_code>",
16
+ "<jupyter_output>",
17
+ "<empty_output>",
18
+ "<commit_before>",
19
+ "<commit_msg>",
20
+ "<commit_after>",
21
+ "<reponame>"
22
+ ],
23
+ "bos_token": {
24
+ "content": "<|endoftext|>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "eos_token": {
31
+ "content": "<|endoftext|>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "pad_token": {
38
+ "content": "<|endoftext|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<|endoftext|>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,188 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<fim_prefix>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "<fim_middle>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<fim_suffix>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "4": {
37
+ "content": "<fim_pad>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "5": {
45
+ "content": "<filename>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "6": {
53
+ "content": "<gh_stars>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "7": {
61
+ "content": "<issue_start>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "8": {
69
+ "content": "<issue_comment>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "9": {
77
+ "content": "<issue_closed>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "10": {
85
+ "content": "<jupyter_start>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "11": {
93
+ "content": "<jupyter_text>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "12": {
101
+ "content": "<jupyter_code>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "13": {
109
+ "content": "<jupyter_output>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "14": {
117
+ "content": "<empty_output>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "15": {
125
+ "content": "<commit_before>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "16": {
133
+ "content": "<commit_msg>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": true
139
+ },
140
+ "17": {
141
+ "content": "<commit_after>",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "18": {
149
+ "content": "<reponame>",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": true
155
+ }
156
+ },
157
+ "additional_special_tokens": [
158
+ "<|endoftext|>",
159
+ "<fim_prefix>",
160
+ "<fim_middle>",
161
+ "<fim_suffix>",
162
+ "<fim_pad>",
163
+ "<filename>",
164
+ "<gh_stars>",
165
+ "<issue_start>",
166
+ "<issue_comment>",
167
+ "<issue_closed>",
168
+ "<jupyter_start>",
169
+ "<jupyter_text>",
170
+ "<jupyter_code>",
171
+ "<jupyter_output>",
172
+ "<empty_output>",
173
+ "<commit_before>",
174
+ "<commit_msg>",
175
+ "<commit_after>",
176
+ "<reponame>"
177
+ ],
178
+ "bos_token": "<|endoftext|>",
179
+ "clean_up_tokenization_spaces": true,
180
+ "eos_token": "<|endoftext|>",
181
+ "extra_special_tokens": {},
182
+ "model_max_length": 9223372036854775807,
183
+ "pad_token": "<|endoftext|>",
184
+ "padding_side": "left",
185
+ "tokenizer_class": "GPT2Tokenizer",
186
+ "unk_token": "<|endoftext|>",
187
+ "vocab_size": 49152
188
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff