Hugging Face's logo

mstyslavity
/
boulango_random

Text Generation
Transformers
Safetensors
llama
mergekit
Merge
text-generation-inference
Model card Files
xet
Community
mstyslavity commited on
Commit
5b71b5f
·
verified ·
1 Parent(s): 40bba36

Upload folder using huggingface_hub

Browse files
Files changed (7) hide show
  1. README.md +62 -0
  2. config.json +29 -0
  3. mergekit_config.yml +33 -0
  4. model.safetensors +3 -0
  5. special_tokens_map.json +77 -0
  6. tokenizer.json +0 -0
  7. tokenizer_config.json +451 -0
README.md ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model:
3
+ - PleIAs/Baguettotron
4
+ library_name: transformers
5
+ tags:
6
+ - mergekit
7
+ - merge
8
+
9
+ ---
10
+ # merge
11
+
12
+ This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
13
+
14
+ ## Merge Details
15
+ ### Merge Method
16
+
17
+ This model was merged using the Passthrough merge method using [PleIAs/Baguettotron](https://huggingface.co/PleIAs/Baguettotron) as a base.
18
+
19
+ ### Models Merged
20
+
21
+ The following models were included in the merge:
22
+
23
+
24
+ ### Configuration
25
+
26
+ The following YAML configuration was used to produce this model:
27
+
28
+ ```yaml
29
+ merge_method: passthrough
30
+ dtype: bfloat16
31
+ out_dtype: float32
32
+ base_model: PleIAs/Baguettotron
33
+ slices:
34
+ - sources:
35
+ - model: PleIAs/Baguettotron
36
+ layer_range: [0,30]
37
+ - sources:
38
+ - model: PleIAs/Baguettotron
39
+ layer_range: [20,40]
40
+ - sources:
41
+ - model: PleIAs/Baguettotron
42
+ layer_range: [30,66]
43
+ - sources:
44
+ - model: PleIAs/Baguettotron
45
+ layer_range: [40,76]
46
+ - sources:
47
+ - model: PleIAs/Baguettotron
48
+ layer_range: [50,80]
49
+ - sources:
50
+ - model: PleIAs/Baguettotron
51
+ layer_range: [10,38]
52
+ - sources:
53
+ - model: PleIAs/Baguettotron
54
+ layer_range: [0,22]
55
+ - sources:
56
+ - model: PleIAs/Baguettotron
57
+ layer_range: [14,70]
58
+ tokenizer:
59
+ source: base
60
+ parameters:
61
+ normalize: true
62
+ ```
config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "dtype": "float32",
9
+ "eos_token_id": 2,
10
+ "head_dim": 64,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 576,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 1536,
15
+ "max_position_embeddings": 4096,
16
+ "mlp_bias": false,
17
+ "model_type": "llama",
18
+ "num_attention_heads": 9,
19
+ "num_hidden_layers": 258,
20
+ "num_key_value_heads": 3,
21
+ "pretraining_tp": 1,
22
+ "rms_norm_eps": 1e-05,
23
+ "rope_scaling": null,
24
+ "rope_theta": 10000,
25
+ "tie_word_embeddings": true,
26
+ "transformers_version": "4.57.3",
27
+ "use_cache": true,
28
+ "vocab_size": 65536
29
+ }
mergekit_config.yml ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ merge_method: passthrough
2
+ dtype: bfloat16
3
+ out_dtype: float32
4
+ base_model: PleIAs/Baguettotron
5
+ slices:
6
+ - sources:
7
+ - model: PleIAs/Baguettotron
8
+ layer_range: [0,30]
9
+ - sources:
10
+ - model: PleIAs/Baguettotron
11
+ layer_range: [20,40]
12
+ - sources:
13
+ - model: PleIAs/Baguettotron
14
+ layer_range: [30,66]
15
+ - sources:
16
+ - model: PleIAs/Baguettotron
17
+ layer_range: [40,76]
18
+ - sources:
19
+ - model: PleIAs/Baguettotron
20
+ layer_range: [50,80]
21
+ - sources:
22
+ - model: PleIAs/Baguettotron
23
+ layer_range: [10,38]
24
+ - sources:
25
+ - model: PleIAs/Baguettotron
26
+ layer_range: [0,22]
27
+ - sources:
28
+ - model: PleIAs/Baguettotron
29
+ layer_range: [14,70]
30
+ tokenizer:
31
+ source: base
32
+ parameters:
33
+ normalize: true
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:408ff91106934e610b9525ff44a1fc649e216964c043607df4ee4fd7ae0f00b8
3
+ size 3804641512
special_tokens_map.json ADDED
@@ -0,0 +1,77 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end>",
5
+ "<think>",
6
+ "</think>",
7
+ "source_1",
8
+ "source_2",
9
+ "source_3",
10
+ "source_4",
11
+ "source_5",
12
+ "source_6",
13
+ "source_7",
14
+ "source_8",
15
+ "source_9",
16
+ "source_10",
17
+ "<ref",
18
+ "</ref>",
19
+ "→",
20
+ "↺",
21
+ "※",
22
+ "?maybe?",
23
+ "●",
24
+ "◐",
25
+ "○",
26
+ "⚠",
27
+ "☐",
28
+ "☑",
29
+ "✓",
30
+ "⟨H≈0.1⟩",
31
+ "⟨H≈0.2⟩",
32
+ "⟨H≈0.3⟩",
33
+ "⟨H≈0.4⟩",
34
+ "⟨H≈0.5⟩",
35
+ "⟨H≈0.6⟩",
36
+ "⟨H≈0.7⟩",
37
+ "⟨H≈0.8⟩",
38
+ "⟨H≈0.9⟩",
39
+ "⟨H≈1.0⟩",
40
+ "⟨H≈1.1⟩",
41
+ "⟨H≈1.2⟩",
42
+ "⟨H≈1.3⟩",
43
+ "⟨H≈1.4⟩",
44
+ "⟨H≈1.5⟩",
45
+ "⟨H≈1.6⟩",
46
+ "⟨H≈1.7⟩",
47
+ "⟨H≈1.8⟩"
48
+ ],
49
+ "bos_token": {
50
+ "content": "<|begin_of_text|>",
51
+ "lstrip": false,
52
+ "normalized": false,
53
+ "rstrip": false,
54
+ "single_word": false
55
+ },
56
+ "eos_token": {
57
+ "content": "<|end_of_text|>",
58
+ "lstrip": false,
59
+ "normalized": false,
60
+ "rstrip": false,
61
+ "single_word": false
62
+ },
63
+ "pad_token": {
64
+ "content": "[PAD]",
65
+ "lstrip": false,
66
+ "normalized": false,
67
+ "rstrip": false,
68
+ "single_word": false
69
+ },
70
+ "unk_token": {
71
+ "content": "[UNK]",
72
+ "lstrip": false,
73
+ "normalized": false,
74
+ "rstrip": false,
75
+ "single_word": false
76
+ }
77
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,451 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[UNK]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<|begin_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "<|end_of_text|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[PAD]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "65491": {
36
+ "content": "<|im_start|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "65492": {
44
+ "content": "<|im_end>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "65493": {
52
+ "content": "<think>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "65494": {
60
+ "content": "</think>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "65495": {
68
+ "content": "source_1",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "65496": {
76
+ "content": "source_2",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "65497": {
84
+ "content": "source_3",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "65498": {
92
+ "content": "source_4",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "65499": {
100
+ "content": "source_5",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "65500": {
108
+ "content": "source_6",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "65501": {
116
+ "content": "source_7",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "65502": {
124
+ "content": "source_8",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "65503": {
132
+ "content": "source_9",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "65504": {
140
+ "content": "source_10",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "65505": {
148
+ "content": "<ref",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "65506": {
156
+ "content": "</ref>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "65507": {
164
+ "content": "→",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "65508": {
172
+ "content": "↺",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "65509": {
180
+ "content": "※",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "65510": {
188
+ "content": "?maybe?",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "65511": {
196
+ "content": "●",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "65512": {
204
+ "content": "◐",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "65513": {
212
+ "content": "○",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "65514": {
220
+ "content": "⚠",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "65515": {
228
+ "content": "☐",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "65516": {
236
+ "content": "☑",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "65517": {
244
+ "content": "✓",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "65518": {
252
+ "content": "⟨H≈0.1⟩",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "65519": {
260
+ "content": "⟨H≈0.2⟩",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "65520": {
268
+ "content": "⟨H≈0.3⟩",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "65521": {
276
+ "content": "⟨H≈0.4⟩",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "65522": {
284
+ "content": "⟨H≈0.5⟩",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "65523": {
292
+ "content": "⟨H≈0.6⟩",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "65524": {
300
+ "content": "⟨H≈0.7⟩",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "65525": {
308
+ "content": "⟨H≈0.8⟩",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "65526": {
316
+ "content": "⟨H≈0.9⟩",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "65527": {
324
+ "content": "⟨H≈1.0⟩",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "65528": {
332
+ "content": "⟨H≈1.1⟩",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "65529": {
340
+ "content": "⟨H≈1.2⟩",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "65530": {
348
+ "content": "⟨H≈1.3⟩",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "65531": {
356
+ "content": "⟨H≈1.4⟩",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "65532": {
364
+ "content": "⟨H≈1.5⟩",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "65533": {
372
+ "content": "⟨H≈1.6⟩",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "65534": {
380
+ "content": "⟨H≈1.7⟩",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "65535": {
388
+ "content": "⟨H≈1.8⟩",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ }
395
+ },
396
+ "additional_special_tokens": [
397
+ "<|im_start|>",
398
+ "<|im_end>",
399
+ "<think>",
400
+ "</think>",
401
+ "source_1",
402
+ "source_2",
403
+ "source_3",
404
+ "source_4",
405
+ "source_5",
406
+ "source_6",
407
+ "source_7",
408
+ "source_8",
409
+ "source_9",
410
+ "source_10",
411
+ "<ref",
412
+ "</ref>",
413
+ "→",
414
+ "↺",
415
+ "※",
416
+ "?maybe?",
417
+ "●",
418
+ "◐",
419
+ "○",
420
+ "⚠",
421
+ "☐",
422
+ "☑",
423
+ "✓",
424
+ "⟨H≈0.1⟩",
425
+ "⟨H≈0.2⟩",
426
+ "⟨H≈0.3⟩",
427
+ "⟨H≈0.4⟩",
428
+ "⟨H≈0.5⟩",
429
+ "⟨H≈0.6⟩",
430
+ "⟨H≈0.7⟩",
431
+ "⟨H≈0.8⟩",
432
+ "⟨H≈0.9⟩",
433
+ "⟨H≈1.0⟩",
434
+ "⟨H≈1.1⟩",
435
+ "⟨H≈1.2⟩",
436
+ "⟨H≈1.3⟩",
437
+ "⟨H≈1.4⟩",
438
+ "⟨H≈1.5⟩",
439
+ "⟨H≈1.6⟩",
440
+ "⟨H≈1.7⟩",
441
+ "⟨H≈1.8⟩"
442
+ ],
443
+ "bos_token": "<|begin_of_text|>",
444
+ "clean_up_tokenization_spaces": true,
445
+ "eos_token": "<|end_of_text|>",
446
+ "extra_special_tokens": {},
447
+ "model_max_length": 1000000000000000019884624838656,
448
+ "pad_token": "[PAD]",
449
+ "tokenizer_class": "PreTrainedTokenizerFast",
450
+ "unk_token": "[UNK]"
451
+ }