Text Generation
GGUF
TensorBlock
GGUF
Eval Results
Inference Endpoints
morriszms commited on
Commit
229e799
1 Parent(s): 9571aa1

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -33,3 +33,15 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ bloomz-7b1-mt-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
37
+ bloomz-7b1-mt-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
38
+ bloomz-7b1-mt-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
39
+ bloomz-7b1-mt-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
40
+ bloomz-7b1-mt-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
41
+ bloomz-7b1-mt-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
42
+ bloomz-7b1-mt-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
43
+ bloomz-7b1-mt-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
44
+ bloomz-7b1-mt-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
45
+ bloomz-7b1-mt-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
46
+ bloomz-7b1-mt-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
47
+ bloomz-7b1-mt-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,724 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ datasets:
3
+ - bigscience/xP3mt
4
+ license: bigscience-bloom-rail-1.0
5
+ language:
6
+ - ak
7
+ - ar
8
+ - as
9
+ - bm
10
+ - bn
11
+ - ca
12
+ - code
13
+ - en
14
+ - es
15
+ - eu
16
+ - fon
17
+ - fr
18
+ - gu
19
+ - hi
20
+ - id
21
+ - ig
22
+ - ki
23
+ - kn
24
+ - lg
25
+ - ln
26
+ - ml
27
+ - mr
28
+ - ne
29
+ - nso
30
+ - ny
31
+ - or
32
+ - pa
33
+ - pt
34
+ - rn
35
+ - rw
36
+ - sn
37
+ - st
38
+ - sw
39
+ - ta
40
+ - te
41
+ - tn
42
+ - ts
43
+ - tum
44
+ - tw
45
+ - ur
46
+ - vi
47
+ - wo
48
+ - xh
49
+ - yo
50
+ - zh
51
+ - zu
52
+ programming_language:
53
+ - C
54
+ - C++
55
+ - C#
56
+ - Go
57
+ - Java
58
+ - JavaScript
59
+ - Lua
60
+ - PHP
61
+ - Python
62
+ - Ruby
63
+ - Rust
64
+ - Scala
65
+ - TypeScript
66
+ pipeline_tag: text-generation
67
+ widget:
68
+ - text: 一个传奇的开端,一个不灭的神话,这不仅仅是一部电影,而是作为一个走进新时代的标签,永远彪炳史册。Would you rate the previous
69
+ review as positive, neutral or negative?
70
+ example_title: zh-en sentiment
71
+ - text: 一个传奇的开端,一个不灭的神话,这不仅仅是一部电影,而是作为一个走进新时代的标签,永远彪炳史册。你认为这句话的立场是赞扬、中立还是批评?
72
+ example_title: zh-zh sentiment
73
+ - text: Suggest at least five related search terms to "Mạng neural nhân tạo".
74
+ example_title: vi-en query
75
+ - text: Proposez au moins cinq mots clés concernant «Réseau de neurones artificiels».
76
+ example_title: fr-fr query
77
+ - text: Explain in a sentence in Telugu what is backpropagation in neural networks.
78
+ example_title: te-en qa
79
+ - text: Why is the sky blue?
80
+ example_title: en-en qa
81
+ - text: 'Write a fairy tale about a troll saving a princess from a dangerous dragon.
82
+ The fairy tale is a masterpiece that has achieved praise worldwide and its moral
83
+ is "Heroes Come in All Shapes and Sizes". Story (in Spanish):'
84
+ example_title: es-en fable
85
+ - text: 'Write a fable about wood elves living in a forest that is suddenly invaded
86
+ by ogres. The fable is a masterpiece that has achieved praise worldwide and its
87
+ moral is "Violence is the last refuge of the incompetent". Fable (in Hindi):'
88
+ example_title: hi-en fable
89
+ tags:
90
+ - TensorBlock
91
+ - GGUF
92
+ base_model: bigscience/bloomz-7b1-mt
93
+ model-index:
94
+ - name: bloomz-7b1-mt
95
+ results:
96
+ - task:
97
+ type: Coreference resolution
98
+ dataset:
99
+ name: Winogrande XL (xl)
100
+ type: winogrande
101
+ config: xl
102
+ split: validation
103
+ revision: a80f460359d1e9a67c006011c94de42a8759430c
104
+ metrics:
105
+ - type: Accuracy
106
+ value: 56.51
107
+ - task:
108
+ type: Coreference resolution
109
+ dataset:
110
+ name: XWinograd (en)
111
+ type: Muennighoff/xwinograd
112
+ config: en
113
+ split: test
114
+ revision: 9dd5ea5505fad86b7bedad667955577815300cee
115
+ metrics:
116
+ - type: Accuracy
117
+ value: 65.76
118
+ - task:
119
+ type: Coreference resolution
120
+ dataset:
121
+ name: XWinograd (fr)
122
+ type: Muennighoff/xwinograd
123
+ config: fr
124
+ split: test
125
+ revision: 9dd5ea5505fad86b7bedad667955577815300cee
126
+ metrics:
127
+ - type: Accuracy
128
+ value: 57.83
129
+ - task:
130
+ type: Coreference resolution
131
+ dataset:
132
+ name: XWinograd (jp)
133
+ type: Muennighoff/xwinograd
134
+ config: jp
135
+ split: test
136
+ revision: 9dd5ea5505fad86b7bedad667955577815300cee
137
+ metrics:
138
+ - type: Accuracy
139
+ value: 51.82
140
+ - task:
141
+ type: Coreference resolution
142
+ dataset:
143
+ name: XWinograd (pt)
144
+ type: Muennighoff/xwinograd
145
+ config: pt
146
+ split: test
147
+ revision: 9dd5ea5505fad86b7bedad667955577815300cee
148
+ metrics:
149
+ - type: Accuracy
150
+ value: 57.41
151
+ - task:
152
+ type: Coreference resolution
153
+ dataset:
154
+ name: XWinograd (ru)
155
+ type: Muennighoff/xwinograd
156
+ config: ru
157
+ split: test
158
+ revision: 9dd5ea5505fad86b7bedad667955577815300cee
159
+ metrics:
160
+ - type: Accuracy
161
+ value: 55.87
162
+ - task:
163
+ type: Coreference resolution
164
+ dataset:
165
+ name: XWinograd (zh)
166
+ type: Muennighoff/xwinograd
167
+ config: zh
168
+ split: test
169
+ revision: 9dd5ea5505fad86b7bedad667955577815300cee
170
+ metrics:
171
+ - type: Accuracy
172
+ value: 62.7
173
+ - task:
174
+ type: Natural language inference
175
+ dataset:
176
+ name: ANLI (r1)
177
+ type: anli
178
+ config: r1
179
+ split: validation
180
+ revision: 9dbd830a06fea8b1c49d6e5ef2004a08d9f45094
181
+ metrics:
182
+ - type: Accuracy
183
+ value: 42.6
184
+ - task:
185
+ type: Natural language inference
186
+ dataset:
187
+ name: ANLI (r2)
188
+ type: anli
189
+ config: r2
190
+ split: validation
191
+ revision: 9dbd830a06fea8b1c49d6e5ef2004a08d9f45094
192
+ metrics:
193
+ - type: Accuracy
194
+ value: 39.4
195
+ - task:
196
+ type: Natural language inference
197
+ dataset:
198
+ name: ANLI (r3)
199
+ type: anli
200
+ config: r3
201
+ split: validation
202
+ revision: 9dbd830a06fea8b1c49d6e5ef2004a08d9f45094
203
+ metrics:
204
+ - type: Accuracy
205
+ value: 42.0
206
+ - task:
207
+ type: Natural language inference
208
+ dataset:
209
+ name: SuperGLUE (cb)
210
+ type: super_glue
211
+ config: cb
212
+ split: validation
213
+ revision: 9e12063561e7e6c79099feb6d5a493142584e9e2
214
+ metrics:
215
+ - type: Accuracy
216
+ value: 83.93
217
+ - task:
218
+ type: Natural language inference
219
+ dataset:
220
+ name: SuperGLUE (rte)
221
+ type: super_glue
222
+ config: rte
223
+ split: validation
224
+ revision: 9e12063561e7e6c79099feb6d5a493142584e9e2
225
+ metrics:
226
+ - type: Accuracy
227
+ value: 82.67
228
+ - task:
229
+ type: Natural language inference
230
+ dataset:
231
+ name: XNLI (ar)
232
+ type: xnli
233
+ config: ar
234
+ split: validation
235
+ revision: a5a45e4ff92d5d3f34de70aaf4b72c3bdf9f7f16
236
+ metrics:
237
+ - type: Accuracy
238
+ value: 55.58
239
+ - task:
240
+ type: Natural language inference
241
+ dataset:
242
+ name: XNLI (bg)
243
+ type: xnli
244
+ config: bg
245
+ split: validation
246
+ revision: a5a45e4ff92d5d3f34de70aaf4b72c3bdf9f7f16
247
+ metrics:
248
+ - type: Accuracy
249
+ value: 44.9
250
+ - task:
251
+ type: Natural language inference
252
+ dataset:
253
+ name: XNLI (de)
254
+ type: xnli
255
+ config: de
256
+ split: validation
257
+ revision: a5a45e4ff92d5d3f34de70aaf4b72c3bdf9f7f16
258
+ metrics:
259
+ - type: Accuracy
260
+ value: 48.92
261
+ - task:
262
+ type: Natural language inference
263
+ dataset:
264
+ name: XNLI (el)
265
+ type: xnli
266
+ config: el
267
+ split: validation
268
+ revision: a5a45e4ff92d5d3f34de70aaf4b72c3bdf9f7f16
269
+ metrics:
270
+ - type: Accuracy
271
+ value: 42.89
272
+ - task:
273
+ type: Natural language inference
274
+ dataset:
275
+ name: XNLI (en)
276
+ type: xnli
277
+ config: en
278
+ split: validation
279
+ revision: a5a45e4ff92d5d3f34de70aaf4b72c3bdf9f7f16
280
+ metrics:
281
+ - type: Accuracy
282
+ value: 58.92
283
+ - task:
284
+ type: Natural language inference
285
+ dataset:
286
+ name: XNLI (es)
287
+ type: xnli
288
+ config: es
289
+ split: validation
290
+ revision: a5a45e4ff92d5d3f34de70aaf4b72c3bdf9f7f16
291
+ metrics:
292
+ - type: Accuracy
293
+ value: 57.35
294
+ - task:
295
+ type: Natural language inference
296
+ dataset:
297
+ name: XNLI (fr)
298
+ type: xnli
299
+ config: fr
300
+ split: validation
301
+ revision: a5a45e4ff92d5d3f34de70aaf4b72c3bdf9f7f16
302
+ metrics:
303
+ - type: Accuracy
304
+ value: 56.67
305
+ - task:
306
+ type: Natural language inference
307
+ dataset:
308
+ name: XNLI (hi)
309
+ type: xnli
310
+ config: hi
311
+ split: validation
312
+ revision: a5a45e4ff92d5d3f34de70aaf4b72c3bdf9f7f16
313
+ metrics:
314
+ - type: Accuracy
315
+ value: 53.45
316
+ - task:
317
+ type: Natural language inference
318
+ dataset:
319
+ name: XNLI (ru)
320
+ type: xnli
321
+ config: ru
322
+ split: validation
323
+ revision: a5a45e4ff92d5d3f34de70aaf4b72c3bdf9f7f16
324
+ metrics:
325
+ - type: Accuracy
326
+ value: 50.24
327
+ - task:
328
+ type: Natural language inference
329
+ dataset:
330
+ name: XNLI (sw)
331
+ type: xnli
332
+ config: sw
333
+ split: validation
334
+ revision: a5a45e4ff92d5d3f34de70aaf4b72c3bdf9f7f16
335
+ metrics:
336
+ - type: Accuracy
337
+ value: 48.27
338
+ - task:
339
+ type: Natural language inference
340
+ dataset:
341
+ name: XNLI (th)
342
+ type: xnli
343
+ config: th
344
+ split: validation
345
+ revision: a5a45e4ff92d5d3f34de70aaf4b72c3bdf9f7f16
346
+ metrics:
347
+ - type: Accuracy
348
+ value: 41.08
349
+ - task:
350
+ type: Natural language inference
351
+ dataset:
352
+ name: XNLI (tr)
353
+ type: xnli
354
+ config: tr
355
+ split: validation
356
+ revision: a5a45e4ff92d5d3f34de70aaf4b72c3bdf9f7f16
357
+ metrics:
358
+ - type: Accuracy
359
+ value: 38.71
360
+ - task:
361
+ type: Natural language inference
362
+ dataset:
363
+ name: XNLI (ur)
364
+ type: xnli
365
+ config: ur
366
+ split: validation
367
+ revision: a5a45e4ff92d5d3f34de70aaf4b72c3bdf9f7f16
368
+ metrics:
369
+ - type: Accuracy
370
+ value: 49.48
371
+ - task:
372
+ type: Natural language inference
373
+ dataset:
374
+ name: XNLI (vi)
375
+ type: xnli
376
+ config: vi
377
+ split: validation
378
+ revision: a5a45e4ff92d5d3f34de70aaf4b72c3bdf9f7f16
379
+ metrics:
380
+ - type: Accuracy
381
+ value: 54.5
382
+ - task:
383
+ type: Natural language inference
384
+ dataset:
385
+ name: XNLI (zh)
386
+ type: xnli
387
+ config: zh
388
+ split: validation
389
+ revision: a5a45e4ff92d5d3f34de70aaf4b72c3bdf9f7f16
390
+ metrics:
391
+ - type: Accuracy
392
+ value: 54.3
393
+ - task:
394
+ type: Program synthesis
395
+ dataset:
396
+ name: HumanEval
397
+ type: openai_humaneval
398
+ config: None
399
+ split: test
400
+ revision: e8dc562f5de170c54b5481011dd9f4fa04845771
401
+ metrics:
402
+ - type: Pass@1
403
+ value: 7.23
404
+ - type: Pass@10
405
+ value: 14.46
406
+ - type: Pass@100
407
+ value: 25.86
408
+ - task:
409
+ type: Sentence completion
410
+ dataset:
411
+ name: StoryCloze (2016)
412
+ type: story_cloze
413
+ config: '2016'
414
+ split: validation
415
+ revision: e724c6f8cdf7c7a2fb229d862226e15b023ee4db
416
+ metrics:
417
+ - type: Accuracy
418
+ value: 89.58
419
+ - task:
420
+ type: Sentence completion
421
+ dataset:
422
+ name: SuperGLUE (copa)
423
+ type: super_glue
424
+ config: copa
425
+ split: validation
426
+ revision: 9e12063561e7e6c79099feb6d5a493142584e9e2
427
+ metrics:
428
+ - type: Accuracy
429
+ value: 84.0
430
+ - task:
431
+ type: Sentence completion
432
+ dataset:
433
+ name: XCOPA (et)
434
+ type: xcopa
435
+ config: et
436
+ split: validation
437
+ revision: 37f73c60fb123111fa5af5f9b705d0b3747fd187
438
+ metrics:
439
+ - type: Accuracy
440
+ value: 52.0
441
+ - task:
442
+ type: Sentence completion
443
+ dataset:
444
+ name: XCOPA (ht)
445
+ type: xcopa
446
+ config: ht
447
+ split: validation
448
+ revision: 37f73c60fb123111fa5af5f9b705d0b3747fd187
449
+ metrics:
450
+ - type: Accuracy
451
+ value: 54.0
452
+ - task:
453
+ type: Sentence completion
454
+ dataset:
455
+ name: XCOPA (id)
456
+ type: xcopa
457
+ config: id
458
+ split: validation
459
+ revision: 37f73c60fb123111fa5af5f9b705d0b3747fd187
460
+ metrics:
461
+ - type: Accuracy
462
+ value: 73.0
463
+ - task:
464
+ type: Sentence completion
465
+ dataset:
466
+ name: XCOPA (it)
467
+ type: xcopa
468
+ config: it
469
+ split: validation
470
+ revision: 37f73c60fb123111fa5af5f9b705d0b3747fd187
471
+ metrics:
472
+ - type: Accuracy
473
+ value: 62.0
474
+ - task:
475
+ type: Sentence completion
476
+ dataset:
477
+ name: XCOPA (qu)
478
+ type: xcopa
479
+ config: qu
480
+ split: validation
481
+ revision: 37f73c60fb123111fa5af5f9b705d0b3747fd187
482
+ metrics:
483
+ - type: Accuracy
484
+ value: 61.0
485
+ - task:
486
+ type: Sentence completion
487
+ dataset:
488
+ name: XCOPA (sw)
489
+ type: xcopa
490
+ config: sw
491
+ split: validation
492
+ revision: 37f73c60fb123111fa5af5f9b705d0b3747fd187
493
+ metrics:
494
+ - type: Accuracy
495
+ value: 61.0
496
+ - task:
497
+ type: Sentence completion
498
+ dataset:
499
+ name: XCOPA (ta)
500
+ type: xcopa
501
+ config: ta
502
+ split: validation
503
+ revision: 37f73c60fb123111fa5af5f9b705d0b3747fd187
504
+ metrics:
505
+ - type: Accuracy
506
+ value: 62.0
507
+ - task:
508
+ type: Sentence completion
509
+ dataset:
510
+ name: XCOPA (th)
511
+ type: xcopa
512
+ config: th
513
+ split: validation
514
+ revision: 37f73c60fb123111fa5af5f9b705d0b3747fd187
515
+ metrics:
516
+ - type: Accuracy
517
+ value: 61.0
518
+ - task:
519
+ type: Sentence completion
520
+ dataset:
521
+ name: XCOPA (tr)
522
+ type: xcopa
523
+ config: tr
524
+ split: validation
525
+ revision: 37f73c60fb123111fa5af5f9b705d0b3747fd187
526
+ metrics:
527
+ - type: Accuracy
528
+ value: 56.0
529
+ - task:
530
+ type: Sentence completion
531
+ dataset:
532
+ name: XCOPA (vi)
533
+ type: xcopa
534
+ config: vi
535
+ split: validation
536
+ revision: 37f73c60fb123111fa5af5f9b705d0b3747fd187
537
+ metrics:
538
+ - type: Accuracy
539
+ value: 77.0
540
+ - task:
541
+ type: Sentence completion
542
+ dataset:
543
+ name: XCOPA (zh)
544
+ type: xcopa
545
+ config: zh
546
+ split: validation
547
+ revision: 37f73c60fb123111fa5af5f9b705d0b3747fd187
548
+ metrics:
549
+ - type: Accuracy
550
+ value: 80.0
551
+ - task:
552
+ type: Sentence completion
553
+ dataset:
554
+ name: XStoryCloze (ar)
555
+ type: Muennighoff/xstory_cloze
556
+ config: ar
557
+ split: validation
558
+ revision: 8bb76e594b68147f1a430e86829d07189622b90d
559
+ metrics:
560
+ - type: Accuracy
561
+ value: 83.85
562
+ - task:
563
+ type: Sentence completion
564
+ dataset:
565
+ name: XStoryCloze (es)
566
+ type: Muennighoff/xstory_cloze
567
+ config: es
568
+ split: validation
569
+ revision: 8bb76e594b68147f1a430e86829d07189622b90d
570
+ metrics:
571
+ - type: Accuracy
572
+ value: 88.82
573
+ - task:
574
+ type: Sentence completion
575
+ dataset:
576
+ name: XStoryCloze (eu)
577
+ type: Muennighoff/xstory_cloze
578
+ config: eu
579
+ split: validation
580
+ revision: 8bb76e594b68147f1a430e86829d07189622b90d
581
+ metrics:
582
+ - type: Accuracy
583
+ value: 73.26
584
+ - task:
585
+ type: Sentence completion
586
+ dataset:
587
+ name: XStoryCloze (hi)
588
+ type: Muennighoff/xstory_cloze
589
+ config: hi
590
+ split: validation
591
+ revision: 8bb76e594b68147f1a430e86829d07189622b90d
592
+ metrics:
593
+ - type: Accuracy
594
+ value: 80.41
595
+ - task:
596
+ type: Sentence completion
597
+ dataset:
598
+ name: XStoryCloze (id)
599
+ type: Muennighoff/xstory_cloze
600
+ config: id
601
+ split: validation
602
+ revision: 8bb76e594b68147f1a430e86829d07189622b90d
603
+ metrics:
604
+ - type: Accuracy
605
+ value: 84.58
606
+ - task:
607
+ type: Sentence completion
608
+ dataset:
609
+ name: XStoryCloze (my)
610
+ type: Muennighoff/xstory_cloze
611
+ config: my
612
+ split: validation
613
+ revision: 8bb76e594b68147f1a430e86829d07189622b90d
614
+ metrics:
615
+ - type: Accuracy
616
+ value: 51.56
617
+ - task:
618
+ type: Sentence completion
619
+ dataset:
620
+ name: XStoryCloze (ru)
621
+ type: Muennighoff/xstory_cloze
622
+ config: ru
623
+ split: validation
624
+ revision: 8bb76e594b68147f1a430e86829d07189622b90d
625
+ metrics:
626
+ - type: Accuracy
627
+ value: 64.26
628
+ - task:
629
+ type: Sentence completion
630
+ dataset:
631
+ name: XStoryCloze (sw)
632
+ type: Muennighoff/xstory_cloze
633
+ config: sw
634
+ split: validation
635
+ revision: 8bb76e594b68147f1a430e86829d07189622b90d
636
+ metrics:
637
+ - type: Accuracy
638
+ value: 71.01
639
+ - task:
640
+ type: Sentence completion
641
+ dataset:
642
+ name: XStoryCloze (te)
643
+ type: Muennighoff/xstory_cloze
644
+ config: te
645
+ split: validation
646
+ revision: 8bb76e594b68147f1a430e86829d07189622b90d
647
+ metrics:
648
+ - type: Accuracy
649
+ value: 73.06
650
+ - task:
651
+ type: Sentence completion
652
+ dataset:
653
+ name: XStoryCloze (zh)
654
+ type: Muennighoff/xstory_cloze
655
+ config: zh
656
+ split: validation
657
+ revision: 8bb76e594b68147f1a430e86829d07189622b90d
658
+ metrics:
659
+ - type: Accuracy
660
+ value: 85.9
661
+ ---
662
+
663
+ <div style="width: auto; margin-left: auto; margin-right: auto">
664
+ <img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
665
+ </div>
666
+ <div style="display: flex; justify-content: space-between; width: 100%;">
667
+ <div style="display: flex; flex-direction: column; align-items: flex-start;">
668
+ <p style="margin-top: 0.5em; margin-bottom: 0em;">
669
+ Feedback and support: TensorBlock's <a href="https://x.com/tensorblock_aoi">Twitter/X</a>, <a href="https://t.me/TensorBlock">Telegram Group</a> and <a href="https://x.com/tensorblock_aoi">Discord server</a>
670
+ </p>
671
+ </div>
672
+ </div>
673
+
674
+ ## bigscience/bloomz-7b1-mt - GGUF
675
+
676
+ This repo contains GGUF format model files for [bigscience/bloomz-7b1-mt](https://huggingface.co/bigscience/bloomz-7b1-mt).
677
+
678
+ The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b4011](https://github.com/ggerganov/llama.cpp/commit/a6744e43e80f4be6398fc7733a01642c846dce1d).
679
+
680
+ ## Prompt template
681
+
682
+ ```
683
+
684
+ ```
685
+
686
+ ## Model file specification
687
+
688
+ | Filename | Quant type | File Size | Description |
689
+ | -------- | ---------- | --------- | ----------- |
690
+ | [bloomz-7b1-mt-Q2_K.gguf](https://huggingface.co/tensorblock/bloomz-7b1-mt-GGUF/tree/main/bloomz-7b1-mt-Q2_K.gguf) | Q2_K | 3.201 GB | smallest, significant quality loss - not recommended for most purposes |
691
+ | [bloomz-7b1-mt-Q3_K_S.gguf](https://huggingface.co/tensorblock/bloomz-7b1-mt-GGUF/tree/main/bloomz-7b1-mt-Q3_K_S.gguf) | Q3_K_S | 3.631 GB | very small, high quality loss |
692
+ | [bloomz-7b1-mt-Q3_K_M.gguf](https://huggingface.co/tensorblock/bloomz-7b1-mt-GGUF/tree/main/bloomz-7b1-mt-Q3_K_M.gguf) | Q3_K_M | 4.137 GB | very small, high quality loss |
693
+ | [bloomz-7b1-mt-Q3_K_L.gguf](https://huggingface.co/tensorblock/bloomz-7b1-mt-GGUF/tree/main/bloomz-7b1-mt-Q3_K_L.gguf) | Q3_K_L | 4.422 GB | small, substantial quality loss |
694
+ | [bloomz-7b1-mt-Q4_0.gguf](https://huggingface.co/tensorblock/bloomz-7b1-mt-GGUF/tree/main/bloomz-7b1-mt-Q4_0.gguf) | Q4_0 | 4.505 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
695
+ | [bloomz-7b1-mt-Q4_K_S.gguf](https://huggingface.co/tensorblock/bloomz-7b1-mt-GGUF/tree/main/bloomz-7b1-mt-Q4_K_S.gguf) | Q4_K_S | 4.529 GB | small, greater quality loss |
696
+ | [bloomz-7b1-mt-Q4_K_M.gguf](https://huggingface.co/tensorblock/bloomz-7b1-mt-GGUF/tree/main/bloomz-7b1-mt-Q4_K_M.gguf) | Q4_K_M | 4.907 GB | medium, balanced quality - recommended |
697
+ | [bloomz-7b1-mt-Q5_0.gguf](https://huggingface.co/tensorblock/bloomz-7b1-mt-GGUF/tree/main/bloomz-7b1-mt-Q5_0.gguf) | Q5_0 | 5.328 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
698
+ | [bloomz-7b1-mt-Q5_K_S.gguf](https://huggingface.co/tensorblock/bloomz-7b1-mt-GGUF/tree/main/bloomz-7b1-mt-Q5_K_S.gguf) | Q5_K_S | 5.328 GB | large, low quality loss - recommended |
699
+ | [bloomz-7b1-mt-Q5_K_M.gguf](https://huggingface.co/tensorblock/bloomz-7b1-mt-GGUF/tree/main/bloomz-7b1-mt-Q5_K_M.gguf) | Q5_K_M | 5.631 GB | large, very low quality loss - recommended |
700
+ | [bloomz-7b1-mt-Q6_K.gguf](https://huggingface.co/tensorblock/bloomz-7b1-mt-GGUF/tree/main/bloomz-7b1-mt-Q6_K.gguf) | Q6_K | 6.202 GB | very large, extremely low quality loss |
701
+ | [bloomz-7b1-mt-Q8_0.gguf](https://huggingface.co/tensorblock/bloomz-7b1-mt-GGUF/tree/main/bloomz-7b1-mt-Q8_0.gguf) | Q8_0 | 8.028 GB | very large, extremely low quality loss - not recommended |
702
+
703
+
704
+ ## Downloading instruction
705
+
706
+ ### Command line
707
+
708
+ Firstly, install Huggingface Client
709
+
710
+ ```shell
711
+ pip install -U "huggingface_hub[cli]"
712
+ ```
713
+
714
+ Then, downoad the individual model file the a local directory
715
+
716
+ ```shell
717
+ huggingface-cli download tensorblock/bloomz-7b1-mt-GGUF --include "bloomz-7b1-mt-Q2_K.gguf" --local-dir MY_LOCAL_DIR
718
+ ```
719
+
720
+ If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
721
+
722
+ ```shell
723
+ huggingface-cli download tensorblock/bloomz-7b1-mt-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
724
+ ```
bloomz-7b1-mt-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3364f5eb3f4c6e2620b01202f70873877ac6b0ca69cafb45b77d08c8ba8f6e82
3
+ size 3436620704
bloomz-7b1-mt-Q3_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e48e735ba2686fbe9e5ea2d7c0db70026344b54de9a8a7048c906a1f036b3d59
3
+ size 4748159904
bloomz-7b1-mt-Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49bf32d213cf8d323c2f7ab26464195e8e540a282ad54bc04ffc23164b3e1b12
3
+ size 4441975712
bloomz-7b1-mt-Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f18ed94e639079432be38c85aa25c67fb3737af9eae904b0234aec419506553
3
+ size 3898813344
bloomz-7b1-mt-Q4_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17a482720ac59642e09e80aa27c0cfa2c58cd03344498dfc9b66697f8b171f4e
3
+ size 4837452704
bloomz-7b1-mt-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5ad9e2230a819fc15020c6d8d50c6f498734a4cbd7dc35547370f802525e08d
3
+ size 5268417440
bloomz-7b1-mt-Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12f11b3698eb56004819fbc136bf0211df02e615d2eddf95bd906c90048dbe1b
3
+ size 4862618528
bloomz-7b1-mt-Q5_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b98e88c2167ab4d99b7ca6569b2f7ec25e5607370a36ab230aa075fac3d6bf0
3
+ size 5720877984
bloomz-7b1-mt-Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d134feed07afb1bd812169e08d0fe1c0671e880a6aeb3210dba0ff7faeda0e36
3
+ size 6046198688
bloomz-7b1-mt-Q5_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ad007fc2d3c716cb7cfdf7f4c0824620b3c7e7f2468704aa7ae9f3dfc6fe273
3
+ size 5720877984
bloomz-7b1-mt-Q6_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4a31d12750721ffddffe5c0a6bb8bdc8ae58b96712afba7222ac4e8b345ec74
3
+ size 6659517344
bloomz-7b1-mt-Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ca96b98600c7e6498a4b5b2c589372ec61932b3130280e258033512c405855d
3
+ size 8620026784