daytoy-models commited on
Commit
5d8a26f
·
verified ·
1 Parent(s): 14e2da6

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +6 -456
README.md CHANGED
@@ -1,466 +1,16 @@
1
  ---
2
- pipeline_tag: text-generation
3
- inference: true
4
- widget:
5
- - text: 'def print_hello_world():'
6
- example_title: Hello world
7
- group: Python
8
- datasets:
9
- - bigcode/the-stack-dedup
10
- metrics:
11
- - code_eval
12
- library_namexxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx: adapter-transformers
13
- tags:
14
- - code
15
- - '123'
16
- - 1,3
17
- - '1234'
18
  model-index:
19
  - name: StarCoder
20
  results:
21
  - task:
22
  type: text-generation
23
  dataset:
24
- type: openai_humaneval1
25
- name: HumanEval1
26
- metrics:
27
- - name: pass@1
28
- type: pass@1
29
- value:
30
- verified: false
31
- - name: pass@2
32
- type: pass@2
33
- value: 0.12345
34
- verified: false
35
- - task:
36
- type: text-generation
37
- dataset:
38
  type: openai_humaneval
39
- name: HumanEval
40
- metrics:
41
- - name: pass@1
42
- type: pass@1
43
- value:
44
- dataset:
45
- type: openai_humaneval
46
- name: HumanEval
47
- args: haha
48
- verified: false
49
- - name: StarCoder2
50
- results:
51
- - task:
52
- type: text-generation
53
- dataset:
54
- type: mbpp
55
- name: MBPP
56
- metrics:
57
- - name: pass@1
58
- type: pass@1
59
- value: 0.527
60
- verified: false
61
- - task:
62
- type: text-generation
63
- dataset:
64
- type: ds1000
65
- name: DS-1000 (Overall Completion)
66
- metrics:
67
- - name: pass@1
68
- type: pass@1
69
- value: 0.26
70
- verified: false
71
- - task:
72
- type: text-generation
73
- dataset:
74
- type: nuprl/MultiPL-E
75
- name: MultiPL-HumanEval (C++)
76
- metrics:
77
- - name: pass@1
78
- type: pass@1
79
- value: 0.3155
80
- verified: false
81
- - task:
82
- type: text-generation
83
- dataset:
84
- type: nuprl/MultiPL-E
85
- name: MultiPL-HumanEval (C#)
86
- metrics:
87
- - name: pass@1
88
- type: pass@1
89
- value: 0.2101
90
- verified: false
91
- - task:
92
- type: text-generation
93
- dataset:
94
- type: nuprl/MultiPL-E
95
- name: MultiPL-HumanEval (D)
96
- metrics:
97
- - name: pass@1
98
- type: pass@1
99
- value: 0.1357
100
- verified: false
101
- - task:
102
- type: text-generation
103
- dataset:
104
- type: nuprl/MultiPL-E
105
- name: MultiPL-HumanEval (Go)
106
- metrics:
107
- - name: pass@1
108
- type: pass@1
109
- value: 0.1761
110
- verified: false
111
- - task:
112
- type: text-generation
113
- dataset:
114
- type: nuprl/MultiPL-E
115
- name: MultiPL-HumanEval (Java)
116
- metrics:
117
- - name: pass@1
118
- type: pass@1
119
- value: 0.3022
120
- verified: false
121
- - task:
122
- type: text-generation
123
- dataset:
124
- type: nuprl/MultiPL-E
125
- name: MultiPL-HumanEval (Julia)
126
- metrics:
127
- - name: pass@1
128
- type: pass@1
129
- value: 0.2302
130
- verified: false
131
- - task:
132
- type: text-generation
133
- dataset:
134
- type: nuprl/MultiPL-E
135
- name: MultiPL-HumanEval (JavaScript)
136
- metrics:
137
- - name: pass@1
138
- type: pass@1
139
- value: 0.3079
140
- verified: false
141
- - task:
142
- type: text-generation
143
- dataset:
144
- type: nuprl/MultiPL-E
145
- name: MultiPL-HumanEval (Lua)
146
  metrics:
147
- - name: pass@1
148
- type: pass@1
149
- value: 0.2389
150
  verified: false
151
- - task:
152
- type: text-generation
153
- dataset:
154
- type: nuprl/MultiPL-E
155
- name: MultiPL-HumanEval (PHP)
156
- metrics:
157
- - name: pass@1
158
- type: pass@1
159
- value: 0.2608
160
- verified: false
161
- - task:
162
- type: text-generation
163
- dataset:
164
- type: nuprl/MultiPL-E
165
- name: MultiPL-HumanEval (Perl)
166
- metrics:
167
- - name: pass@1
168
- type: pass@1
169
- value: 0.1734
170
- verified: false
171
- - task:
172
- type: text-generation
173
- dataset:
174
- type: nuprl/MultiPL-E
175
- name: MultiPL-HumanEval (Python)
176
- metrics:
177
- - name: pass@1
178
- type: pass@1
179
- value: 0.3357
180
- verified: false
181
- - task:
182
- type: text-generation
183
- dataset:
184
- type: nuprl/MultiPL-E
185
- name: MultiPL-HumanEval (R)
186
- metrics:
187
- - name: pass@1
188
- type: pass@1
189
- value: 0.155
190
- verified: false
191
- - task:
192
- type: text-generation
193
- dataset:
194
- type: nuprl/MultiPL-E
195
- name: MultiPL-HumanEval (Ruby)
196
- metrics:
197
- - name: pass@1
198
- type: pass@1
199
- value: 0.0124
200
- verified: false
201
- - task:
202
- type: text-generation
203
- dataset:
204
- type: nuprl/MultiPL-E
205
- name: MultiPL-HumanEval (Racket)
206
- metrics:
207
- - name: pass@1
208
- type: pass@1
209
- value: 0.0007
210
- verified: false
211
- - task:
212
- type: text-generation
213
- dataset:
214
- type: nuprl/MultiPL-E
215
- name: MultiPL-HumanEval (Rust)
216
- metrics:
217
- - name: pass@1
218
- type: pass@1
219
- value: 0.2184
220
- verified: false
221
- - task:
222
- type: text-generation
223
- dataset:
224
- type: nuprl/MultiPL-E
225
- name: MultiPL-HumanEval (Scala)
226
- metrics:
227
- - name: pass@1
228
- type: pass@1
229
- value: 0.2761
230
- verified: false
231
- - task:
232
- type: text-generation
233
- dataset:
234
- type: nuprl/MultiPL-E
235
- name: MultiPL-HumanEval (Bash)
236
- metrics:
237
- - name: pass@1
238
- type: pass@1
239
- value: 0.1046
240
- verified: false
241
- - task:
242
- type: text-generation
243
- dataset:
244
- type: nuprl/MultiPL-E
245
- name: MultiPL-HumanEval (Swift)
246
- metrics:
247
- - name: pass@1
248
- type: pass@1
249
- value: 0.2274
250
- verified: false
251
- - task:
252
- type: text-generation
253
- dataset:
254
- type: nuprl/MultiPL-E
255
- name: MultiPL-HumanEval (TypeScript)
256
- metrics:
257
- - name: pass@1
258
- type: pass@1
259
- value: 0.3229
260
- verified: false
261
- extra_gated_prompt: >-
262
- ## Model License Agreement Please read the BigCode [OpenRAIL-M
263
- license](https://huggingface.co/spaces/bigcode/bigcode-model-license-agreement)
264
- agreement before accepting it.
265
-
266
- extra_gated_fields:
267
- I accept the above license agreement, and will use the Model complying with the set of use restrictions and sharing requirements: checkbox
268
- language:
269
- - aa
270
- - af
271
- license: apache-2.0
272
- ---
273
- # Model Card for Model ID
274
-
275
- <!-- Provide a quick summary of what the model is/does. -->
276
-
277
- This modelcard aims to be a base template for new models. It has been generated using [this raw template](https://github.com/huggingface/huggingface_hub/blob/main/src/huggingface_hub/templates/modelcard_template.md?plain=1).
278
-
279
- ## Model Details
280
-
281
- ### Model Description
282
-
283
- <!-- Provide a longer summary of what this model is. -->
284
-
285
-
286
-
287
- - **Developed by:** [More Information Needed]
288
- - **Funded by [optional]:** [More Information Needed]
289
- - **Shared by [optional]:** [More Information Needed]
290
- - **Model type:** [More Information Needed]
291
- - **Language(s) (NLP):** [More Information Needed]
292
- - **License:** [More Information Needed]
293
- - **Finetuned from model [optional]:** [More Information Needed]
294
-
295
- ### Model Sources [optional]
296
-
297
- <!-- Provide the basic links for the model. -->
298
-
299
- - **Repository:** [More Information Needed]
300
- - **Paper [optional]:** [More Information Needed]
301
- - **Demo [optional]:** [More Information Needed]
302
-
303
- ## Uses
304
-
305
- <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
306
-
307
- ### Direct Use
308
-
309
- <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
310
-
311
- [More Information Needed]
312
-
313
- ### Downstream Use [optional]
314
-
315
- <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
316
-
317
- [More Information Needed]
318
-
319
- ### Out-of-Scope Use
320
-
321
- <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
322
-
323
- [More Information Needed]
324
-
325
- ## Bias, Risks, and Limitations
326
-
327
- <!-- This section is meant to convey both technical and sociotechnical limitations. -->
328
-
329
- [More Information Needed]
330
-
331
- ### Recommendations
332
-
333
- <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
334
-
335
- Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
336
-
337
- ## How to Get Started with the Model
338
-
339
- Use the code below to get started with the model.
340
-
341
- [More Information Needed]
342
-
343
- ## Training Details
344
-
345
- ### Training Data
346
-
347
- <!-- 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. -->
348
-
349
- [More Information Needed]
350
-
351
- ### Training Procedure
352
-
353
- <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
354
-
355
- #### Preprocessing [optional]
356
-
357
- [More Information Needed]
358
-
359
-
360
- #### Training Hyperparameters
361
-
362
- - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
363
-
364
- #### Speeds, Sizes, Times [optional]
365
-
366
- <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
367
-
368
- [More Information Needed]
369
-
370
- ## Evaluation
371
-
372
- <!-- This section describes the evaluation protocols and provides the results. -->
373
-
374
- ### Testing Data, Factors & Metrics
375
-
376
- #### Testing Data
377
-
378
- <!-- This should link to a Dataset Card if possible. -->
379
-
380
- [More Information Needed]
381
-
382
- #### Factors
383
-
384
- <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
385
-
386
- [More Information Needed]
387
-
388
- #### Metrics
389
-
390
- <!-- These are the evaluation metrics being used, ideally with a description of why. -->
391
-
392
- [More Information Needed]
393
-
394
- ### Results
395
-
396
- [More Information Needed]
397
-
398
- #### Summary
399
-
400
-
401
-
402
- ## Model Examination [optional]
403
-
404
- <!-- Relevant interpretability work for the model goes here -->
405
-
406
- [More Information Needed]
407
-
408
- ## Environmental Impact
409
-
410
- <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
411
-
412
- 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).
413
-
414
- - **Hardware Type:** [More Information Needed]
415
- - **Hours used:** [More Information Needed]
416
- - **Cloud Provider:** [More Information Needed]
417
- - **Compute Region:** [More Information Needed]
418
- - **Carbon Emitted:** [More Information Needed]
419
-
420
- ## Technical Specifications [optional]
421
-
422
- ### Model Architecture and Objective
423
-
424
- [More Information Needed]
425
-
426
- ### Compute Infrastructure
427
-
428
- [More Information Needed]
429
-
430
- #### Hardware
431
-
432
- [More Information Needed]
433
-
434
- #### Software
435
-
436
- [More Information Needed]
437
-
438
- ## Citation [optional]
439
-
440
- <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
441
-
442
- **BibTeX:**
443
-
444
- [More Information Needed]
445
-
446
- **APA:**
447
-
448
- [More Information Needed]
449
-
450
- ## Glossary [optional]
451
-
452
- <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
453
-
454
- [More Information Needed]
455
-
456
- ## More Information [optional]
457
-
458
- [More Information Needed]
459
-
460
- ## Model Card Authors [optional]
461
-
462
- [More Information Needed]
463
-
464
- ## Model Card Contact
465
-
466
- [More Information Needed]
 
1
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2
  model-index:
3
  - name: StarCoder
4
  results:
5
  - task:
6
  type: text-generation
7
  dataset:
8
+ split: test
 
 
 
 
 
 
 
 
 
 
 
 
 
9
  type: openai_humaneval
10
+ name: HumanEval (Prompted)
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
11
  metrics:
12
+ - type: pass@1
13
+ name: aaaa
14
+ value: 0.408
15
  verified: false
16
+ ---