prince-canuma commited on
Commit
5780e90
·
verified ·
1 Parent(s): 2d09abb

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ 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
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ inference: false
3
+ library_name: transformers
4
+ language:
5
+ - en
6
+ - fr
7
+ - de
8
+ - es
9
+ - it
10
+ - pt
11
+ - ja
12
+ - ko
13
+ - zh
14
+ - ar
15
+ - el
16
+ - fa
17
+ - pl
18
+ - id
19
+ - cs
20
+ - he
21
+ - hi
22
+ - nl
23
+ - ro
24
+ - ru
25
+ - tr
26
+ - uk
27
+ - vi
28
+ license: cc-by-nc-4.0
29
+ extra_gated_prompt: By submitting this form, you agree to the [License Agreement](https://cohere.com/c4ai-cc-by-nc-license) and
30
+ acknowledge that the information you provide will be collected, used, and shared
31
+ in accordance with Cohere’s [Privacy Policy]( https://cohere.com/privacy). You’ll
32
+ receive email updates about C4AI and Cohere research, events, products and services.
33
+ You can unsubscribe at any time.
34
+ extra_gated_fields:
35
+ Name: text
36
+ Affiliation: text
37
+ Country: country
38
+ I agree to use this model for non-commercial use ONLY: checkbox
39
+ pipeline_tag: image-text-to-text
40
+ tags:
41
+ - mlx
42
+ ---
43
+
44
+ # mlx-community/aya-vision-32b-4bit
45
+ This model was converted to MLX format from [`CohereForAI/aya-vision-32b`]() using mlx-vlm version **0.1.15**.
46
+ Refer to the [original model card](https://huggingface.co/CohereForAI/aya-vision-32b) for more details on the model.
47
+ ## Use with mlx
48
+
49
+ ```bash
50
+ pip install -U mlx-vlm
51
+ ```
52
+
53
+ ```bash
54
+ python -m mlx_vlm.generate --model mlx-community/aya-vision-32b-4bit --max-tokens 100 --temperature 0.0 --prompt "Describe this image." --image <path_to_image>
55
+ ```
config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "adapter_layer_norm_eps": 1e-06,
3
+ "alignment_activation_fn": "swiglu",
4
+ "alignment_intermediate_size": 49152,
5
+ "architectures": [
6
+ "AyaVisionForConditionalGeneration"
7
+ ],
8
+ "downsample_factor": 2,
9
+ "image_token_index": 255022,
10
+ "max_splits_per_img": 12,
11
+ "model_type": "aya_vision",
12
+ "projector_hidden_act": "gelu",
13
+ "quantization": {
14
+ "group_size": 64,
15
+ "bits": 4
16
+ },
17
+ "text_config": {
18
+ "intermediate_size": 24576,
19
+ "model_type": "cohere",
20
+ "num_key_value_heads": 8,
21
+ "rope_theta": 4000000,
22
+ "torch_dtype": "float16",
23
+ "use_qk_norm": false
24
+ },
25
+ "torch_dtype": "float16",
26
+ "transformers_version": "4.50.0.dev0",
27
+ "vision_config": {
28
+ "hidden_size": 1152,
29
+ "image_size": 364,
30
+ "intermediate_size": 4304,
31
+ "model_type": "siglip_vision_model",
32
+ "num_attention_heads": 16,
33
+ "num_hidden_layers": 27,
34
+ "patch_size": 14,
35
+ "torch_dtype": "float16",
36
+ "vision_use_head": false,
37
+ "skip_vision": true
38
+ },
39
+ "vision_feature_layer": -1,
40
+ "vision_feature_select_strategy": "full"
41
+ }
model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ad69ce7ae68af2ba0c7225b901bacc64c326fd3dc94598ea482ad998d65f43c
3
+ size 5289837470
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ef2d39cfe31fe998c115c6975cdae2fec0e1583d4ce5715b7af68f8584f6811
3
+ size 5294509427
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8db806ad6c3e5ed21260aa9eb3692be55ada0b06227ff082491bb0bc1ef8f3cd
3
+ size 5322803358
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d7199f9d0e8cbc09c2e188385542d200dc016ec14ee1fc67525ea1c5aa6e1bd
3
+ size 3326909578
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<BOS_TOKEN>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|END_OF_TURN_TOKEN|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<PAD>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dbb2974c7ff2633f0dce4490be28531dca552e3ecfafad7a2dfd0e8b212534fc
3
+ size 20124863
tokenizer_config.json ADDED
@@ -0,0 +1,356 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": false,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<PAD>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<UNK>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "<CLS>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ },
30
+ "3": {
31
+ "content": "<SEP>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "4": {
39
+ "content": "<MASK_TOKEN>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": true
45
+ },
46
+ "5": {
47
+ "content": "<BOS_TOKEN>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": false,
51
+ "single_word": false,
52
+ "special": true
53
+ },
54
+ "6": {
55
+ "content": "<EOS_TOKEN>",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": false,
59
+ "single_word": false,
60
+ "special": true
61
+ },
62
+ "7": {
63
+ "content": "<EOP_TOKEN>",
64
+ "lstrip": false,
65
+ "normalized": false,
66
+ "rstrip": false,
67
+ "single_word": false,
68
+ "special": true
69
+ },
70
+ "255000": {
71
+ "content": "<|START_OF_TURN_TOKEN|>",
72
+ "lstrip": false,
73
+ "normalized": false,
74
+ "rstrip": false,
75
+ "single_word": false,
76
+ "special": false
77
+ },
78
+ "255001": {
79
+ "content": "<|END_OF_TURN_TOKEN|>",
80
+ "lstrip": false,
81
+ "normalized": false,
82
+ "rstrip": false,
83
+ "single_word": false,
84
+ "special": true
85
+ },
86
+ "255002": {
87
+ "content": "<|YES_TOKEN|>",
88
+ "lstrip": false,
89
+ "normalized": false,
90
+ "rstrip": false,
91
+ "single_word": false,
92
+ "special": false
93
+ },
94
+ "255003": {
95
+ "content": "<|NO_TOKEN|>",
96
+ "lstrip": false,
97
+ "normalized": false,
98
+ "rstrip": false,
99
+ "single_word": false,
100
+ "special": false
101
+ },
102
+ "255004": {
103
+ "content": "<|GOOD_TOKEN|>",
104
+ "lstrip": false,
105
+ "normalized": false,
106
+ "rstrip": false,
107
+ "single_word": false,
108
+ "special": false
109
+ },
110
+ "255005": {
111
+ "content": "<|BAD_TOKEN|>",
112
+ "lstrip": false,
113
+ "normalized": false,
114
+ "rstrip": false,
115
+ "single_word": false,
116
+ "special": false
117
+ },
118
+ "255006": {
119
+ "content": "<|USER_TOKEN|>",
120
+ "lstrip": false,
121
+ "normalized": false,
122
+ "rstrip": false,
123
+ "single_word": false,
124
+ "special": false
125
+ },
126
+ "255007": {
127
+ "content": "<|CHATBOT_TOKEN|>",
128
+ "lstrip": false,
129
+ "normalized": false,
130
+ "rstrip": false,
131
+ "single_word": false,
132
+ "special": false
133
+ },
134
+ "255008": {
135
+ "content": "<|SYSTEM_TOKEN|>",
136
+ "lstrip": false,
137
+ "normalized": false,
138
+ "rstrip": false,
139
+ "single_word": false,
140
+ "special": false
141
+ },
142
+ "255009": {
143
+ "content": "<|USER_0_TOKEN|>",
144
+ "lstrip": false,
145
+ "normalized": false,
146
+ "rstrip": false,
147
+ "single_word": false,
148
+ "special": false
149
+ },
150
+ "255010": {
151
+ "content": "<|USER_1_TOKEN|>",
152
+ "lstrip": false,
153
+ "normalized": false,
154
+ "rstrip": false,
155
+ "single_word": false,
156
+ "special": false
157
+ },
158
+ "255011": {
159
+ "content": "<|USER_2_TOKEN|>",
160
+ "lstrip": false,
161
+ "normalized": false,
162
+ "rstrip": false,
163
+ "single_word": false,
164
+ "special": false
165
+ },
166
+ "255012": {
167
+ "content": "<|USER_3_TOKEN|>",
168
+ "lstrip": false,
169
+ "normalized": false,
170
+ "rstrip": false,
171
+ "single_word": false,
172
+ "special": false
173
+ },
174
+ "255013": {
175
+ "content": "<|USER_4_TOKEN|>",
176
+ "lstrip": false,
177
+ "normalized": false,
178
+ "rstrip": false,
179
+ "single_word": false,
180
+ "special": false
181
+ },
182
+ "255014": {
183
+ "content": "<|USER_5_TOKEN|>",
184
+ "lstrip": false,
185
+ "normalized": false,
186
+ "rstrip": false,
187
+ "single_word": false,
188
+ "special": false
189
+ },
190
+ "255015": {
191
+ "content": "<|USER_6_TOKEN|>",
192
+ "lstrip": false,
193
+ "normalized": false,
194
+ "rstrip": false,
195
+ "single_word": false,
196
+ "special": false
197
+ },
198
+ "255016": {
199
+ "content": "<|USER_7_TOKEN|>",
200
+ "lstrip": false,
201
+ "normalized": false,
202
+ "rstrip": false,
203
+ "single_word": false,
204
+ "special": false
205
+ },
206
+ "255017": {
207
+ "content": "<|USER_8_TOKEN|>",
208
+ "lstrip": false,
209
+ "normalized": false,
210
+ "rstrip": false,
211
+ "single_word": false,
212
+ "special": false
213
+ },
214
+ "255018": {
215
+ "content": "<|USER_9_TOKEN|>",
216
+ "lstrip": false,
217
+ "normalized": false,
218
+ "rstrip": false,
219
+ "single_word": false,
220
+ "special": false
221
+ },
222
+ "255019": {
223
+ "content": "<|START_OF_IMG|>",
224
+ "lstrip": false,
225
+ "normalized": false,
226
+ "rstrip": false,
227
+ "single_word": false,
228
+ "special": false
229
+ },
230
+ "255020": {
231
+ "content": "<|END_OF_IMG|>",
232
+ "lstrip": false,
233
+ "normalized": false,
234
+ "rstrip": false,
235
+ "single_word": false,
236
+ "special": false
237
+ },
238
+ "255021": {
239
+ "content": "<|IMG_LINE_BREAK|>",
240
+ "lstrip": false,
241
+ "normalized": false,
242
+ "rstrip": false,
243
+ "single_word": false,
244
+ "special": false
245
+ },
246
+ "255022": {
247
+ "content": "<|IMG_PATCH|>",
248
+ "lstrip": false,
249
+ "normalized": false,
250
+ "rstrip": false,
251
+ "single_word": false,
252
+ "special": false
253
+ },
254
+ "255023": {
255
+ "content": "<|EXTRA_0_TOKEN|>",
256
+ "lstrip": false,
257
+ "normalized": false,
258
+ "rstrip": false,
259
+ "single_word": false,
260
+ "special": false
261
+ },
262
+ "255024": {
263
+ "content": "<|EXTRA_1_TOKEN|>",
264
+ "lstrip": false,
265
+ "normalized": false,
266
+ "rstrip": false,
267
+ "single_word": false,
268
+ "special": false
269
+ },
270
+ "255025": {
271
+ "content": "<|EXTRA_2_TOKEN|>",
272
+ "lstrip": false,
273
+ "normalized": false,
274
+ "rstrip": false,
275
+ "single_word": false,
276
+ "special": false
277
+ },
278
+ "255026": {
279
+ "content": "<|EXTRA_3_TOKEN|>",
280
+ "lstrip": false,
281
+ "normalized": false,
282
+ "rstrip": false,
283
+ "single_word": false,
284
+ "special": false
285
+ },
286
+ "255027": {
287
+ "content": "<|EXTRA_4_TOKEN|>",
288
+ "lstrip": false,
289
+ "normalized": false,
290
+ "rstrip": false,
291
+ "single_word": false,
292
+ "special": false
293
+ },
294
+ "255028": {
295
+ "content": "<|EXTRA_5_TOKEN|>",
296
+ "lstrip": false,
297
+ "normalized": false,
298
+ "rstrip": false,
299
+ "single_word": false,
300
+ "special": false
301
+ },
302
+ "255029": {
303
+ "content": "<|EXTRA_6_TOKEN|>",
304
+ "lstrip": false,
305
+ "normalized": false,
306
+ "rstrip": false,
307
+ "single_word": false,
308
+ "special": false
309
+ },
310
+ "255030": {
311
+ "content": "<|EXTRA_7_TOKEN|>",
312
+ "lstrip": false,
313
+ "normalized": false,
314
+ "rstrip": false,
315
+ "single_word": false,
316
+ "special": false
317
+ },
318
+ "255031": {
319
+ "content": "<|EXTRA_8_TOKEN|>",
320
+ "lstrip": false,
321
+ "normalized": false,
322
+ "rstrip": false,
323
+ "single_word": false,
324
+ "special": false
325
+ },
326
+ "255032": {
327
+ "content": "<|EXTRA_9_TOKEN|>",
328
+ "lstrip": false,
329
+ "normalized": false,
330
+ "rstrip": false,
331
+ "single_word": false,
332
+ "special": false
333
+ }
334
+ },
335
+ "bos_token": "<BOS_TOKEN>",
336
+ "chat_template": [
337
+ {
338
+ "name": "default",
339
+ "template": "{{ bos_token }}<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>You are Aya Vision, a brilliant, sophisticated, AI-assistant chatbot trained to assist human users by providing thorough responses. You are a large vision language model built by the Cohere For AI. You are capable of interpreting images, including describing them, answering questions about their contents, extracting textual information, and analyzing visual context.<|END_OF_TURN_TOKEN|>\n{%- for message in messages -%}\n <|START_OF_TURN_TOKEN|>{{ message.role | replace(\"user\", \"<|USER_TOKEN|>\") | replace(\"assistant\", \"<|CHATBOT_TOKEN|><|START_RESPONSE|>\") | replace(\"system\", \"<|SYSTEM_TOKEN|>\") }}\n {%- if message.content is defined -%}\n {%- if message.content is string -%}\n{{ message.content }}\n {%- else -%}\n {%- for item in message.content | selectattr('type', 'equalto', 'image') -%}\n<image>\n {%- endfor -%}\n {%- for item in message.content | selectattr('type', 'equalto', 'text') -%}\n{{ item.text }}\n {%- endfor -%}\n {%- endif -%}\n {%- elif message.message is defined -%}\n {%- if message.message is string -%}\n{{ message.message }}\n {%- else -%}\n {%- for item in message.message | selectattr('type', 'equalto', 'image') -%}\n<image>\n {%- endfor -%}\n {%- for item in message.message | selectattr('type', 'equalto', 'text') -%}\n{{ item.text }}\n {%- endfor -%}\n {%- endif -%}\n {%- endif -%}\n {%- if message.role == \"assistant\" -%}\n<|END_RESPONSE|>\n {%- endif -%}\n<|END_OF_TURN_TOKEN|>\n{%- endfor -%}\n{%- if add_generation_prompt -%}\n<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>\n{%- endif -%}\n"
340
+ }
341
+ ],
342
+ "clean_up_tokenization_spaces": false,
343
+ "eos_token": "<|END_OF_TURN_TOKEN|>",
344
+ "extra_special_tokens": {},
345
+ "legacy": true,
346
+ "merges_file": null,
347
+ "model_max_length": 1000000000000000019884624838656,
348
+ "pad_token": "<PAD>",
349
+ "processor_class": "AyaVisionProcessor",
350
+ "sp_model_kwargs": {},
351
+ "spaces_between_special_tokens": false,
352
+ "tokenizer_class": "CohereTokenizer",
353
+ "unk_token": null,
354
+ "use_default_system_prompt": false,
355
+ "vocab_file": null
356
+ }