Hugging Face's logo

jerryzh168
/
opt-125m-int4wo-per-module

Text Generation
Transformers
PyTorch
opt
text-generation-inference
torchao
Model card Files Community
jerryzh168 commited on
Commit
35a5471
·
verified ·
1 Parent(s): c62df8e

Upload OPTForCausalLM

Browse files
Files changed (4) hide show
  1. README.md +199 -0
  2. config.json +551 -0
  3. generation_config.json +7 -0
  4. pytorch_model.bin +3 -0
README.md ADDED
@@ -0,0 +1,199 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ tags: []
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+ This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
config.json ADDED
@@ -0,0 +1,551 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_remove_final_layer_norm": false,
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "relu",
5
+ "architectures": [
6
+ "OPTForCausalLM"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "bos_token_id": 2,
10
+ "do_layer_norm_before": true,
11
+ "dropout": 0.1,
12
+ "enable_bias": true,
13
+ "eos_token_id": 2,
14
+ "ffn_dim": 3072,
15
+ "hidden_size": 768,
16
+ "init_std": 0.02,
17
+ "layer_norm_elementwise_affine": true,
18
+ "layerdrop": 0.0,
19
+ "max_position_embeddings": 2048,
20
+ "model_type": "opt",
21
+ "num_attention_heads": 12,
22
+ "num_hidden_layers": 12,
23
+ "pad_token_id": 1,
24
+ "prefix": "</s>",
25
+ "quantization_config": {
26
+ "include_embedding": false,
27
+ "modules_to_not_convert": null,
28
+ "quant_method": "torchao",
29
+ "quant_type": {
30
+ "default": {
31
+ "_data": {
32
+ "module_fqn_to_config": {
33
+ "model.decoder.layers.0.fc1": {
34
+ "_data": {
35
+ "group_size": 128,
36
+ "layout": {
37
+ "_data": {
38
+ "inner_k_tiles": 8
39
+ },
40
+ "_type": "TensorCoreTiledLayout",
41
+ "_version": 1
42
+ },
43
+ "preserve_zero": null,
44
+ "set_inductor_config": true,
45
+ "use_hqq": true,
46
+ "zero_point_domain": {
47
+ "_data": "NONE",
48
+ "_type": "ZeroPointDomain"
49
+ }
50
+ },
51
+ "_type": "Int4WeightOnlyConfig",
52
+ "_version": 1
53
+ },
54
+ "model.decoder.layers.0.fc2": {
55
+ "_data": {
56
+ "group_size": 128,
57
+ "layout": {
58
+ "_data": {
59
+ "inner_k_tiles": 8
60
+ },
61
+ "_type": "TensorCoreTiledLayout",
62
+ "_version": 1
63
+ },
64
+ "preserve_zero": null,
65
+ "set_inductor_config": true,
66
+ "use_hqq": true,
67
+ "zero_point_domain": {
68
+ "_data": "NONE",
69
+ "_type": "ZeroPointDomain"
70
+ }
71
+ },
72
+ "_type": "Int4WeightOnlyConfig",
73
+ "_version": 1
74
+ },
75
+ "model.decoder.layers.1.fc1": {
76
+ "_data": {
77
+ "group_size": 128,
78
+ "layout": {
79
+ "_data": {
80
+ "inner_k_tiles": 8
81
+ },
82
+ "_type": "TensorCoreTiledLayout",
83
+ "_version": 1
84
+ },
85
+ "preserve_zero": null,
86
+ "set_inductor_config": true,
87
+ "use_hqq": true,
88
+ "zero_point_domain": {
89
+ "_data": "NONE",
90
+ "_type": "ZeroPointDomain"
91
+ }
92
+ },
93
+ "_type": "Int4WeightOnlyConfig",
94
+ "_version": 1
95
+ },
96
+ "model.decoder.layers.1.fc2": {
97
+ "_data": {
98
+ "group_size": 128,
99
+ "layout": {
100
+ "_data": {
101
+ "inner_k_tiles": 8
102
+ },
103
+ "_type": "TensorCoreTiledLayout",
104
+ "_version": 1
105
+ },
106
+ "preserve_zero": null,
107
+ "set_inductor_config": true,
108
+ "use_hqq": true,
109
+ "zero_point_domain": {
110
+ "_data": "NONE",
111
+ "_type": "ZeroPointDomain"
112
+ }
113
+ },
114
+ "_type": "Int4WeightOnlyConfig",
115
+ "_version": 1
116
+ },
117
+ "model.decoder.layers.10.fc1": {
118
+ "_data": {
119
+ "group_size": 128,
120
+ "layout": {
121
+ "_data": {
122
+ "inner_k_tiles": 8
123
+ },
124
+ "_type": "TensorCoreTiledLayout",
125
+ "_version": 1
126
+ },
127
+ "preserve_zero": null,
128
+ "set_inductor_config": true,
129
+ "use_hqq": true,
130
+ "zero_point_domain": {
131
+ "_data": "NONE",
132
+ "_type": "ZeroPointDomain"
133
+ }
134
+ },
135
+ "_type": "Int4WeightOnlyConfig",
136
+ "_version": 1
137
+ },
138
+ "model.decoder.layers.10.fc2": {
139
+ "_data": {
140
+ "group_size": 128,
141
+ "layout": {
142
+ "_data": {
143
+ "inner_k_tiles": 8
144
+ },
145
+ "_type": "TensorCoreTiledLayout",
146
+ "_version": 1
147
+ },
148
+ "preserve_zero": null,
149
+ "set_inductor_config": true,
150
+ "use_hqq": true,
151
+ "zero_point_domain": {
152
+ "_data": "NONE",
153
+ "_type": "ZeroPointDomain"
154
+ }
155
+ },
156
+ "_type": "Int4WeightOnlyConfig",
157
+ "_version": 1
158
+ },
159
+ "model.decoder.layers.11.fc1": {
160
+ "_data": {
161
+ "group_size": 128,
162
+ "layout": {
163
+ "_data": {
164
+ "inner_k_tiles": 8
165
+ },
166
+ "_type": "TensorCoreTiledLayout",
167
+ "_version": 1
168
+ },
169
+ "preserve_zero": null,
170
+ "set_inductor_config": true,
171
+ "use_hqq": true,
172
+ "zero_point_domain": {
173
+ "_data": "NONE",
174
+ "_type": "ZeroPointDomain"
175
+ }
176
+ },
177
+ "_type": "Int4WeightOnlyConfig",
178
+ "_version": 1
179
+ },
180
+ "model.decoder.layers.11.fc2": {
181
+ "_data": {
182
+ "group_size": 128,
183
+ "layout": {
184
+ "_data": {
185
+ "inner_k_tiles": 8
186
+ },
187
+ "_type": "TensorCoreTiledLayout",
188
+ "_version": 1
189
+ },
190
+ "preserve_zero": null,
191
+ "set_inductor_config": true,
192
+ "use_hqq": true,
193
+ "zero_point_domain": {
194
+ "_data": "NONE",
195
+ "_type": "ZeroPointDomain"
196
+ }
197
+ },
198
+ "_type": "Int4WeightOnlyConfig",
199
+ "_version": 1
200
+ },
201
+ "model.decoder.layers.2.fc1": {
202
+ "_data": {
203
+ "group_size": 128,
204
+ "layout": {
205
+ "_data": {
206
+ "inner_k_tiles": 8
207
+ },
208
+ "_type": "TensorCoreTiledLayout",
209
+ "_version": 1
210
+ },
211
+ "preserve_zero": null,
212
+ "set_inductor_config": true,
213
+ "use_hqq": true,
214
+ "zero_point_domain": {
215
+ "_data": "NONE",
216
+ "_type": "ZeroPointDomain"
217
+ }
218
+ },
219
+ "_type": "Int4WeightOnlyConfig",
220
+ "_version": 1
221
+ },
222
+ "model.decoder.layers.2.fc2": {
223
+ "_data": {
224
+ "group_size": 128,
225
+ "layout": {
226
+ "_data": {
227
+ "inner_k_tiles": 8
228
+ },
229
+ "_type": "TensorCoreTiledLayout",
230
+ "_version": 1
231
+ },
232
+ "preserve_zero": null,
233
+ "set_inductor_config": true,
234
+ "use_hqq": true,
235
+ "zero_point_domain": {
236
+ "_data": "NONE",
237
+ "_type": "ZeroPointDomain"
238
+ }
239
+ },
240
+ "_type": "Int4WeightOnlyConfig",
241
+ "_version": 1
242
+ },
243
+ "model.decoder.layers.3.fc1": {
244
+ "_data": {
245
+ "group_size": 128,
246
+ "layout": {
247
+ "_data": {
248
+ "inner_k_tiles": 8
249
+ },
250
+ "_type": "TensorCoreTiledLayout",
251
+ "_version": 1
252
+ },
253
+ "preserve_zero": null,
254
+ "set_inductor_config": true,
255
+ "use_hqq": true,
256
+ "zero_point_domain": {
257
+ "_data": "NONE",
258
+ "_type": "ZeroPointDomain"
259
+ }
260
+ },
261
+ "_type": "Int4WeightOnlyConfig",
262
+ "_version": 1
263
+ },
264
+ "model.decoder.layers.3.fc2": {
265
+ "_data": {
266
+ "group_size": 128,
267
+ "layout": {
268
+ "_data": {
269
+ "inner_k_tiles": 8
270
+ },
271
+ "_type": "TensorCoreTiledLayout",
272
+ "_version": 1
273
+ },
274
+ "preserve_zero": null,
275
+ "set_inductor_config": true,
276
+ "use_hqq": true,
277
+ "zero_point_domain": {
278
+ "_data": "NONE",
279
+ "_type": "ZeroPointDomain"
280
+ }
281
+ },
282
+ "_type": "Int4WeightOnlyConfig",
283
+ "_version": 1
284
+ },
285
+ "model.decoder.layers.4.fc1": {
286
+ "_data": {
287
+ "group_size": 128,
288
+ "layout": {
289
+ "_data": {
290
+ "inner_k_tiles": 8
291
+ },
292
+ "_type": "TensorCoreTiledLayout",
293
+ "_version": 1
294
+ },
295
+ "preserve_zero": null,
296
+ "set_inductor_config": true,
297
+ "use_hqq": true,
298
+ "zero_point_domain": {
299
+ "_data": "NONE",
300
+ "_type": "ZeroPointDomain"
301
+ }
302
+ },
303
+ "_type": "Int4WeightOnlyConfig",
304
+ "_version": 1
305
+ },
306
+ "model.decoder.layers.4.fc2": {
307
+ "_data": {
308
+ "group_size": 128,
309
+ "layout": {
310
+ "_data": {
311
+ "inner_k_tiles": 8
312
+ },
313
+ "_type": "TensorCoreTiledLayout",
314
+ "_version": 1
315
+ },
316
+ "preserve_zero": null,
317
+ "set_inductor_config": true,
318
+ "use_hqq": true,
319
+ "zero_point_domain": {
320
+ "_data": "NONE",
321
+ "_type": "ZeroPointDomain"
322
+ }
323
+ },
324
+ "_type": "Int4WeightOnlyConfig",
325
+ "_version": 1
326
+ },
327
+ "model.decoder.layers.5.fc1": {
328
+ "_data": {
329
+ "group_size": 128,
330
+ "layout": {
331
+ "_data": {
332
+ "inner_k_tiles": 8
333
+ },
334
+ "_type": "TensorCoreTiledLayout",
335
+ "_version": 1
336
+ },
337
+ "preserve_zero": null,
338
+ "set_inductor_config": true,
339
+ "use_hqq": true,
340
+ "zero_point_domain": {
341
+ "_data": "NONE",
342
+ "_type": "ZeroPointDomain"
343
+ }
344
+ },
345
+ "_type": "Int4WeightOnlyConfig",
346
+ "_version": 1
347
+ },
348
+ "model.decoder.layers.5.fc2": {
349
+ "_data": {
350
+ "group_size": 128,
351
+ "layout": {
352
+ "_data": {
353
+ "inner_k_tiles": 8
354
+ },
355
+ "_type": "TensorCoreTiledLayout",
356
+ "_version": 1
357
+ },
358
+ "preserve_zero": null,
359
+ "set_inductor_config": true,
360
+ "use_hqq": true,
361
+ "zero_point_domain": {
362
+ "_data": "NONE",
363
+ "_type": "ZeroPointDomain"
364
+ }
365
+ },
366
+ "_type": "Int4WeightOnlyConfig",
367
+ "_version": 1
368
+ },
369
+ "model.decoder.layers.6.fc1": {
370
+ "_data": {
371
+ "group_size": 128,
372
+ "layout": {
373
+ "_data": {
374
+ "inner_k_tiles": 8
375
+ },
376
+ "_type": "TensorCoreTiledLayout",
377
+ "_version": 1
378
+ },
379
+ "preserve_zero": null,
380
+ "set_inductor_config": true,
381
+ "use_hqq": true,
382
+ "zero_point_domain": {
383
+ "_data": "NONE",
384
+ "_type": "ZeroPointDomain"
385
+ }
386
+ },
387
+ "_type": "Int4WeightOnlyConfig",
388
+ "_version": 1
389
+ },
390
+ "model.decoder.layers.6.fc2": {
391
+ "_data": {
392
+ "group_size": 128,
393
+ "layout": {
394
+ "_data": {
395
+ "inner_k_tiles": 8
396
+ },
397
+ "_type": "TensorCoreTiledLayout",
398
+ "_version": 1
399
+ },
400
+ "preserve_zero": null,
401
+ "set_inductor_config": true,
402
+ "use_hqq": true,
403
+ "zero_point_domain": {
404
+ "_data": "NONE",
405
+ "_type": "ZeroPointDomain"
406
+ }
407
+ },
408
+ "_type": "Int4WeightOnlyConfig",
409
+ "_version": 1
410
+ },
411
+ "model.decoder.layers.7.fc1": {
412
+ "_data": {
413
+ "group_size": 128,
414
+ "layout": {
415
+ "_data": {
416
+ "inner_k_tiles": 8
417
+ },
418
+ "_type": "TensorCoreTiledLayout",
419
+ "_version": 1
420
+ },
421
+ "preserve_zero": null,
422
+ "set_inductor_config": true,
423
+ "use_hqq": true,
424
+ "zero_point_domain": {
425
+ "_data": "NONE",
426
+ "_type": "ZeroPointDomain"
427
+ }
428
+ },
429
+ "_type": "Int4WeightOnlyConfig",
430
+ "_version": 1
431
+ },
432
+ "model.decoder.layers.7.fc2": {
433
+ "_data": {
434
+ "group_size": 128,
435
+ "layout": {
436
+ "_data": {
437
+ "inner_k_tiles": 8
438
+ },
439
+ "_type": "TensorCoreTiledLayout",
440
+ "_version": 1
441
+ },
442
+ "preserve_zero": null,
443
+ "set_inductor_config": true,
444
+ "use_hqq": true,
445
+ "zero_point_domain": {
446
+ "_data": "NONE",
447
+ "_type": "ZeroPointDomain"
448
+ }
449
+ },
450
+ "_type": "Int4WeightOnlyConfig",
451
+ "_version": 1
452
+ },
453
+ "model.decoder.layers.8.fc1": {
454
+ "_data": {
455
+ "group_size": 128,
456
+ "layout": {
457
+ "_data": {
458
+ "inner_k_tiles": 8
459
+ },
460
+ "_type": "TensorCoreTiledLayout",
461
+ "_version": 1
462
+ },
463
+ "preserve_zero": null,
464
+ "set_inductor_config": true,
465
+ "use_hqq": true,
466
+ "zero_point_domain": {
467
+ "_data": "NONE",
468
+ "_type": "ZeroPointDomain"
469
+ }
470
+ },
471
+ "_type": "Int4WeightOnlyConfig",
472
+ "_version": 1
473
+ },
474
+ "model.decoder.layers.8.fc2": {
475
+ "_data": {
476
+ "group_size": 128,
477
+ "layout": {
478
+ "_data": {
479
+ "inner_k_tiles": 8
480
+ },
481
+ "_type": "TensorCoreTiledLayout",
482
+ "_version": 1
483
+ },
484
+ "preserve_zero": null,
485
+ "set_inductor_config": true,
486
+ "use_hqq": true,
487
+ "zero_point_domain": {
488
+ "_data": "NONE",
489
+ "_type": "ZeroPointDomain"
490
+ }
491
+ },
492
+ "_type": "Int4WeightOnlyConfig",
493
+ "_version": 1
494
+ },
495
+ "model.decoder.layers.9.fc1": {
496
+ "_data": {
497
+ "group_size": 128,
498
+ "layout": {
499
+ "_data": {
500
+ "inner_k_tiles": 8
501
+ },
502
+ "_type": "TensorCoreTiledLayout",
503
+ "_version": 1
504
+ },
505
+ "preserve_zero": null,
506
+ "set_inductor_config": true,
507
+ "use_hqq": true,
508
+ "zero_point_domain": {
509
+ "_data": "NONE",
510
+ "_type": "ZeroPointDomain"
511
+ }
512
+ },
513
+ "_type": "Int4WeightOnlyConfig",
514
+ "_version": 1
515
+ },
516
+ "model.decoder.layers.9.fc2": {
517
+ "_data": {
518
+ "group_size": 128,
519
+ "layout": {
520
+ "_data": {
521
+ "inner_k_tiles": 8
522
+ },
523
+ "_type": "TensorCoreTiledLayout",
524
+ "_version": 1
525
+ },
526
+ "preserve_zero": null,
527
+ "set_inductor_config": true,
528
+ "use_hqq": true,
529
+ "zero_point_domain": {
530
+ "_data": "NONE",
531
+ "_type": "ZeroPointDomain"
532
+ }
533
+ },
534
+ "_type": "Int4WeightOnlyConfig",
535
+ "_version": 1
536
+ }
537
+ }
538
+ },
539
+ "_type": "AOPerModuleConfig",
540
+ "_version": 1
541
+ }
542
+ },
543
+ "quant_type_kwargs": {},
544
+ "untie_embedding_weights": false
545
+ },
546
+ "torch_dtype": "bfloat16",
547
+ "transformers_version": "4.52.0.dev0",
548
+ "use_cache": true,
549
+ "vocab_size": 50272,
550
+ "word_embed_proj_dim": 768
551
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 2,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 1,
6
+ "transformers_version": "4.52.0.dev0"
7
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cda9be250c73a98ba148e241dafdac6b2ecedf82a8bb231bf07e124a91e9f99
3
+ size 172407635