Hugging Face's logo

mlx-community
/
stable-code-3b-mlx

Text Generation
Transformers
MLX
English
stablelm_epoch
causal-lm
code
custom_code
Eval Results
Model card Files
xet
Community
1
Pierre-obi commited on
Commit
2e0e400
·
verified ·
1 Parent(s): 4fde636

Upload folder using huggingface_hub

Browse files
Files changed (6) hide show
  1. README.md +68 -0
  2. config.json +85 -0
  3. special_tokens_map.json +23 -0
  4. tokenizer.json +0 -0
  5. tokenizer_config.json +363 -0
  6. weights.00.safetensors +3 -0
README.md ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - en
4
+ license: other
5
+ library_name: transformers
6
+ tags:
7
+ - causal-lm
8
+ - code
9
+ - mlx
10
+ datasets:
11
+ - tiiuae/falcon-refinedweb
12
+ - bigcode/the-stack-github-issues
13
+ - bigcode/commitpackft
14
+ - bigcode/starcoderdata
15
+ - EleutherAI/proof-pile-2
16
+ - meta-math/MetaMathQA
17
+ metrics:
18
+ - code_eval
19
+ model-index:
20
+ - name: StarCoderBase-3B
21
+ results:
22
+ - task:
23
+ type: text-generation
24
+ dataset:
25
+ name: MultiPL-HumanEval (Python)
26
+ type: nuprl/MultiPL-E
27
+ metrics:
28
+ - type: pass@1
29
+ value: 32.4
30
+ name: pass@1
31
+ verified: false
32
+ - type: pass@1
33
+ value: 30.9
34
+ name: pass@1
35
+ verified: false
36
+ - type: pass@1
37
+ value: 32.1
38
+ name: pass@1
39
+ verified: false
40
+ - type: pass@1
41
+ value: 32.1
42
+ name: pass@1
43
+ verified: false
44
+ - type: pass@1
45
+ value: 24.2
46
+ name: pass@1
47
+ verified: false
48
+ - type: pass@1
49
+ value: 23.0
50
+ name: pass@1
51
+ verified: false
52
+ ---
53
+
54
+ # mlx-community/stable-code-3b-mlx
55
+ This model was converted to MLX format from [`stabilityai/stable-code-3b`]().
56
+ Refer to the [original model card](https://huggingface.co/stabilityai/stable-code-3b) for more details on the model.
57
+ ## Use with mlx
58
+
59
+ ```bash
60
+ pip install mlx-lm
61
+ ```
62
+
63
+ ```python
64
+ from mlx_lm import load, generate
65
+
66
+ model, tokenizer = load("mlx-community/stable-code-3b-mlx")
67
+ response = generate(model, tokenizer, prompt="hello", verbose=True)
68
+ ```
config.json ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "vocab_size": 50304,
3
+ "max_position_embeddings": 16384,
4
+ "intermediate_size": 6912,
5
+ "hidden_size": 2560,
6
+ "num_hidden_layers": 32,
7
+ "num_attention_heads": 32,
8
+ "num_key_value_heads": 32,
9
+ "hidden_act": "silu",
10
+ "rope_pct": 0.25,
11
+ "rope_theta": 1000000,
12
+ "initializer_range": 0.02,
13
+ "norm_eps": 1e-05,
14
+ "use_cache": true,
15
+ "tie_word_embeddings": false,
16
+ "return_dict": true,
17
+ "output_hidden_states": false,
18
+ "output_attentions": false,
19
+ "torchscript": false,
20
+ "torch_dtype": "bfloat16",
21
+ "use_bfloat16": false,
22
+ "tf_legacy_loss": false,
23
+ "pruned_heads": {},
24
+ "is_encoder_decoder": false,
25
+ "is_decoder": false,
26
+ "cross_attention_hidden_size": null,
27
+ "add_cross_attention": false,
28
+ "tie_encoder_decoder": false,
29
+ "max_length": 20,
30
+ "min_length": 0,
31
+ "do_sample": false,
32
+ "early_stopping": false,
33
+ "num_beams": 1,
34
+ "num_beam_groups": 1,
35
+ "diversity_penalty": 0.0,
36
+ "temperature": 1.0,
37
+ "top_k": 50,
38
+ "top_p": 1.0,
39
+ "typical_p": 1.0,
40
+ "repetition_penalty": 1.0,
41
+ "length_penalty": 1.0,
42
+ "no_repeat_ngram_size": 0,
43
+ "encoder_no_repeat_ngram_size": 0,
44
+ "bad_words_ids": null,
45
+ "num_return_sequences": 1,
46
+ "chunk_size_feed_forward": 0,
47
+ "output_scores": false,
48
+ "return_dict_in_generate": false,
49
+ "forced_bos_token_id": null,
50
+ "forced_eos_token_id": null,
51
+ "remove_invalid_values": false,
52
+ "exponential_decay_length_penalty": null,
53
+ "suppress_tokens": null,
54
+ "begin_suppress_tokens": null,
55
+ "architectures": [
56
+ "StableLMEpochForCausalLM"
57
+ ],
58
+ "finetuning_task": null,
59
+ "id2label": {
60
+ "0": "LABEL_0",
61
+ "1": "LABEL_1"
62
+ },
63
+ "label2id": {
64
+ "LABEL_0": 0,
65
+ "LABEL_1": 1
66
+ },
67
+ "tokenizer_class": null,
68
+ "prefix": null,
69
+ "bos_token_id": 0,
70
+ "pad_token_id": null,
71
+ "eos_token_id": 0,
72
+ "sep_token_id": null,
73
+ "decoder_start_token_id": null,
74
+ "task_specific_params": null,
75
+ "problem_type": null,
76
+ "_name_or_path": "/Users/peterobi/.cache/huggingface/hub/models--stabilityai--stable-code-3b/snapshots/7088d0f69daea851cb1914044c0178ff68ec2d5f",
77
+ "transformers_version": "4.36.2",
78
+ "auto_map": {
79
+ "AutoConfig": "configuration_stablelm_epoch.StableLMEpochConfig",
80
+ "AutoModelForCausalLM": "modeling_stablelm_epoch.StableLMEpochForCausalLM"
81
+ },
82
+ "model_type": "stablelm_epoch",
83
+ "num_heads": 32,
84
+ "rotary_scaling_factor": 1.0
85
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<|endoftext|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,363 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<|padding|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "50254": {
21
+ "content": " ",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": false
27
+ },
28
+ "50255": {
29
+ "content": " ",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": false
35
+ },
36
+ "50256": {
37
+ "content": " ",
38
+ "lstrip": false,
39
+ "normalized": true,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": false
43
+ },
44
+ "50257": {
45
+ "content": " ",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": false
51
+ },
52
+ "50258": {
53
+ "content": " ",
54
+ "lstrip": false,
55
+ "normalized": true,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": false
59
+ },
60
+ "50259": {
61
+ "content": " ",
62
+ "lstrip": false,
63
+ "normalized": true,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": false
67
+ },
68
+ "50260": {
69
+ "content": " ",
70
+ "lstrip": false,
71
+ "normalized": true,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": false
75
+ },
76
+ "50261": {
77
+ "content": " ",
78
+ "lstrip": false,
79
+ "normalized": true,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": false
83
+ },
84
+ "50262": {
85
+ "content": " ",
86
+ "lstrip": false,
87
+ "normalized": true,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": false
91
+ },
92
+ "50263": {
93
+ "content": " ",
94
+ "lstrip": false,
95
+ "normalized": true,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": false
99
+ },
100
+ "50264": {
101
+ "content": " ",
102
+ "lstrip": false,
103
+ "normalized": true,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": false
107
+ },
108
+ "50265": {
109
+ "content": " ",
110
+ "lstrip": false,
111
+ "normalized": true,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": false
115
+ },
116
+ "50266": {
117
+ "content": " ",
118
+ "lstrip": false,
119
+ "normalized": true,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": false
123
+ },
124
+ "50267": {
125
+ "content": " ",
126
+ "lstrip": false,
127
+ "normalized": true,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": false
131
+ },
132
+ "50268": {
133
+ "content": " ",
134
+ "lstrip": false,
135
+ "normalized": true,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": false
139
+ },
140
+ "50269": {
141
+ "content": " ",
142
+ "lstrip": false,
143
+ "normalized": true,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": false
147
+ },
148
+ "50270": {
149
+ "content": " ",
150
+ "lstrip": false,
151
+ "normalized": true,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": false
155
+ },
156
+ "50271": {
157
+ "content": " ",
158
+ "lstrip": false,
159
+ "normalized": true,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": false
163
+ },
164
+ "50272": {
165
+ "content": " ",
166
+ "lstrip": false,
167
+ "normalized": true,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": false
171
+ },
172
+ "50273": {
173
+ "content": " ",
174
+ "lstrip": false,
175
+ "normalized": true,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": false
179
+ },
180
+ "50274": {
181
+ "content": " ",
182
+ "lstrip": false,
183
+ "normalized": true,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": false
187
+ },
188
+ "50275": {
189
+ "content": " ",
190
+ "lstrip": false,
191
+ "normalized": true,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": false
195
+ },
196
+ "50276": {
197
+ "content": " ",
198
+ "lstrip": false,
199
+ "normalized": true,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": false
203
+ },
204
+ "50277": {
205
+ "content": "<fim_prefix>",
206
+ "lstrip": false,
207
+ "normalized": false,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": true
211
+ },
212
+ "50278": {
213
+ "content": "<fim_middle>",
214
+ "lstrip": false,
215
+ "normalized": false,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": true
219
+ },
220
+ "50279": {
221
+ "content": "<fim_suffix>",
222
+ "lstrip": false,
223
+ "normalized": false,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": true
227
+ },
228
+ "50280": {
229
+ "content": "<fim_pad>",
230
+ "lstrip": false,
231
+ "normalized": false,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": true
235
+ },
236
+ "50281": {
237
+ "content": "<filename>",
238
+ "lstrip": false,
239
+ "normalized": false,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": true
243
+ },
244
+ "50282": {
245
+ "content": "<gh_stars>",
246
+ "lstrip": false,
247
+ "normalized": false,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": true
251
+ },
252
+ "50283": {
253
+ "content": "<issue_start>",
254
+ "lstrip": false,
255
+ "normalized": false,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": true
259
+ },
260
+ "50284": {
261
+ "content": "<issue_comment>",
262
+ "lstrip": false,
263
+ "normalized": false,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": true
267
+ },
268
+ "50285": {
269
+ "content": "<issue_closed>",
270
+ "lstrip": false,
271
+ "normalized": false,
272
+ "rstrip": false,
273
+ "single_word": false,
274
+ "special": true
275
+ },
276
+ "50286": {
277
+ "content": "<jupyter_start>",
278
+ "lstrip": false,
279
+ "normalized": false,
280
+ "rstrip": false,
281
+ "single_word": false,
282
+ "special": true
283
+ },
284
+ "50287": {
285
+ "content": "<jupyter_text>",
286
+ "lstrip": false,
287
+ "normalized": false,
288
+ "rstrip": false,
289
+ "single_word": false,
290
+ "special": true
291
+ },
292
+ "50288": {
293
+ "content": "<jupyter_code>",
294
+ "lstrip": false,
295
+ "normalized": false,
296
+ "rstrip": false,
297
+ "single_word": false,
298
+ "special": true
299
+ },
300
+ "50289": {
301
+ "content": "<jupyter_output>",
302
+ "lstrip": false,
303
+ "normalized": false,
304
+ "rstrip": false,
305
+ "single_word": false,
306
+ "special": true
307
+ },
308
+ "50290": {
309
+ "content": "<empty_output>",
310
+ "lstrip": false,
311
+ "normalized": false,
312
+ "rstrip": false,
313
+ "single_word": false,
314
+ "special": true
315
+ },
316
+ "50291": {
317
+ "content": "<commit_before>",
318
+ "lstrip": false,
319
+ "normalized": false,
320
+ "rstrip": false,
321
+ "single_word": false,
322
+ "special": true
323
+ },
324
+ "50292": {
325
+ "content": "<commit_msg>",
326
+ "lstrip": false,
327
+ "normalized": false,
328
+ "rstrip": false,
329
+ "single_word": false,
330
+ "special": true
331
+ },
332
+ "50293": {
333
+ "content": "<commit_after>",
334
+ "lstrip": false,
335
+ "normalized": false,
336
+ "rstrip": false,
337
+ "single_word": false,
338
+ "special": true
339
+ },
340
+ "50294": {
341
+ "content": "<reponame>",
342
+ "lstrip": false,
343
+ "normalized": false,
344
+ "rstrip": false,
345
+ "single_word": false,
346
+ "special": true
347
+ },
348
+ "50295": {
349
+ "content": "<repo_continuation>",
350
+ "lstrip": false,
351
+ "normalized": false,
352
+ "rstrip": false,
353
+ "single_word": false,
354
+ "special": true
355
+ }
356
+ },
357
+ "bos_token": "<|endoftext|>",
358
+ "clean_up_tokenization_spaces": true,
359
+ "eos_token": "<|endoftext|>",
360
+ "model_max_length": 1000000000000000019884624838656,
361
+ "tokenizer_class": "GPTNeoXTokenizer",
362
+ "unk_token": "<|endoftext|>"
363
+ }
weights.00.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e6e0318527a614072431633f9d23189aa46d88194c529b79685aa92c8903aed
3
+ size 5590927105