Hugging Face's logo

Ba2han
/
mistral_augment-fixed-FP8

Safetensors
mistral3
compressed-tensors
Model card Files
xet
 Community
Ba2han commited on
Commit
029b9d1
·
verified ·
1 Parent(s): ebb1b76

Upload fixed FP8 model (multimodal layers removed)

Browse files
Files changed (11) hide show
  1. .gitattributes +2 -0
  2. chat_template.jinja +2 -0
  3. config.json +278 -0
  4. generation_config.json +9 -0
  5. model.safetensors +3 -0
  6. params.json +47 -0
  7. processor_config.json +42 -0
  8. recipe.yaml +7 -0
  9. tekken.json +3 -0
  10. tokenizer.json +3 -0
  11. tokenizer_config.json +1010 -0
.gitattributes CHANGED
@@ -33,3 +33,5 @@ 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
+ tekken.json filter=lfs diff=lfs merge=lfs -text
37
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
chat_template.jinja ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ {{ bos_token }}{% for message in messages %}{% if message['role'] == 'user' %}{{ '[INST]' + message['content'] }}{% if loop.index0 == 1 and messages[0]['role'] == 'system' %}{{ '
2
+ ' + messages[0]['content'] }}{% endif %}{{ '[/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token }}{% endif %}{% endfor %}
config.json ADDED
@@ -0,0 +1,278 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Mistral3ForConditionalGeneration"
4
+ ],
5
+ "dtype": "bfloat16",
6
+ "image_token_index": 10,
7
+ "model_type": "mistral3",
8
+ "multimodal_projector_bias": false,
9
+ "projector_hidden_act": "gelu",
10
+ "tie_word_embeddings": false,
11
+ "quantization_config": {
12
+ "config_groups": {
13
+ "group_0": {
14
+ "format": "float-quantized",
15
+ "input_activations": {
16
+ "actorder": null,
17
+ "block_structure": null,
18
+ "dynamic": true,
19
+ "group_size": null,
20
+ "num_bits": 8,
21
+ "observer": null,
22
+ "observer_kwargs": {},
23
+ "strategy": "token",
24
+ "symmetric": true,
25
+ "type": "float"
26
+ },
27
+ "output_activations": null,
28
+ "targets": [
29
+ "Linear"
30
+ ],
31
+ "weights": {
32
+ "actorder": null,
33
+ "block_structure": null,
34
+ "dynamic": false,
35
+ "group_size": null,
36
+ "num_bits": 8,
37
+ "observer": "minmax",
38
+ "observer_kwargs": {},
39
+ "strategy": "channel",
40
+ "symmetric": true,
41
+ "type": "float"
42
+ }
43
+ }
44
+ },
45
+ "format": "float-quantized",
46
+ "global_compression_ratio": null,
47
+ "ignore": [
48
+ "model.vision_tower.transformer.layers.0.feed_forward.gate_proj",
49
+ "model.vision_tower.transformer.layers.0.feed_forward.up_proj",
50
+ "model.vision_tower.transformer.layers.0.feed_forward.down_proj",
51
+ "model.vision_tower.transformer.layers.0.attention.k_proj",
52
+ "model.vision_tower.transformer.layers.0.attention.v_proj",
53
+ "model.vision_tower.transformer.layers.0.attention.q_proj",
54
+ "model.vision_tower.transformer.layers.0.attention.o_proj",
55
+ "model.vision_tower.transformer.layers.1.feed_forward.gate_proj",
56
+ "model.vision_tower.transformer.layers.1.feed_forward.up_proj",
57
+ "model.vision_tower.transformer.layers.1.feed_forward.down_proj",
58
+ "model.vision_tower.transformer.layers.1.attention.k_proj",
59
+ "model.vision_tower.transformer.layers.1.attention.v_proj",
60
+ "model.vision_tower.transformer.layers.1.attention.q_proj",
61
+ "model.vision_tower.transformer.layers.1.attention.o_proj",
62
+ "model.vision_tower.transformer.layers.2.feed_forward.gate_proj",
63
+ "model.vision_tower.transformer.layers.2.feed_forward.up_proj",
64
+ "model.vision_tower.transformer.layers.2.feed_forward.down_proj",
65
+ "model.vision_tower.transformer.layers.2.attention.k_proj",
66
+ "model.vision_tower.transformer.layers.2.attention.v_proj",
67
+ "model.vision_tower.transformer.layers.2.attention.q_proj",
68
+ "model.vision_tower.transformer.layers.2.attention.o_proj",
69
+ "model.vision_tower.transformer.layers.3.feed_forward.gate_proj",
70
+ "model.vision_tower.transformer.layers.3.feed_forward.up_proj",
71
+ "model.vision_tower.transformer.layers.3.feed_forward.down_proj",
72
+ "model.vision_tower.transformer.layers.3.attention.k_proj",
73
+ "model.vision_tower.transformer.layers.3.attention.v_proj",
74
+ "model.vision_tower.transformer.layers.3.attention.q_proj",
75
+ "model.vision_tower.transformer.layers.3.attention.o_proj",
76
+ "model.vision_tower.transformer.layers.4.feed_forward.gate_proj",
77
+ "model.vision_tower.transformer.layers.4.feed_forward.up_proj",
78
+ "model.vision_tower.transformer.layers.4.feed_forward.down_proj",
79
+ "model.vision_tower.transformer.layers.4.attention.k_proj",
80
+ "model.vision_tower.transformer.layers.4.attention.v_proj",
81
+ "model.vision_tower.transformer.layers.4.attention.q_proj",
82
+ "model.vision_tower.transformer.layers.4.attention.o_proj",
83
+ "model.vision_tower.transformer.layers.5.feed_forward.gate_proj",
84
+ "model.vision_tower.transformer.layers.5.feed_forward.up_proj",
85
+ "model.vision_tower.transformer.layers.5.feed_forward.down_proj",
86
+ "model.vision_tower.transformer.layers.5.attention.k_proj",
87
+ "model.vision_tower.transformer.layers.5.attention.v_proj",
88
+ "model.vision_tower.transformer.layers.5.attention.q_proj",
89
+ "model.vision_tower.transformer.layers.5.attention.o_proj",
90
+ "model.vision_tower.transformer.layers.6.feed_forward.gate_proj",
91
+ "model.vision_tower.transformer.layers.6.feed_forward.up_proj",
92
+ "model.vision_tower.transformer.layers.6.feed_forward.down_proj",
93
+ "model.vision_tower.transformer.layers.6.attention.k_proj",
94
+ "model.vision_tower.transformer.layers.6.attention.v_proj",
95
+ "model.vision_tower.transformer.layers.6.attention.q_proj",
96
+ "model.vision_tower.transformer.layers.6.attention.o_proj",
97
+ "model.vision_tower.transformer.layers.7.feed_forward.gate_proj",
98
+ "model.vision_tower.transformer.layers.7.feed_forward.up_proj",
99
+ "model.vision_tower.transformer.layers.7.feed_forward.down_proj",
100
+ "model.vision_tower.transformer.layers.7.attention.k_proj",
101
+ "model.vision_tower.transformer.layers.7.attention.v_proj",
102
+ "model.vision_tower.transformer.layers.7.attention.q_proj",
103
+ "model.vision_tower.transformer.layers.7.attention.o_proj",
104
+ "model.vision_tower.transformer.layers.8.feed_forward.gate_proj",
105
+ "model.vision_tower.transformer.layers.8.feed_forward.up_proj",
106
+ "model.vision_tower.transformer.layers.8.feed_forward.down_proj",
107
+ "model.vision_tower.transformer.layers.8.attention.k_proj",
108
+ "model.vision_tower.transformer.layers.8.attention.v_proj",
109
+ "model.vision_tower.transformer.layers.8.attention.q_proj",
110
+ "model.vision_tower.transformer.layers.8.attention.o_proj",
111
+ "model.vision_tower.transformer.layers.9.feed_forward.gate_proj",
112
+ "model.vision_tower.transformer.layers.9.feed_forward.up_proj",
113
+ "model.vision_tower.transformer.layers.9.feed_forward.down_proj",
114
+ "model.vision_tower.transformer.layers.9.attention.k_proj",
115
+ "model.vision_tower.transformer.layers.9.attention.v_proj",
116
+ "model.vision_tower.transformer.layers.9.attention.q_proj",
117
+ "model.vision_tower.transformer.layers.9.attention.o_proj",
118
+ "model.vision_tower.transformer.layers.10.feed_forward.gate_proj",
119
+ "model.vision_tower.transformer.layers.10.feed_forward.up_proj",
120
+ "model.vision_tower.transformer.layers.10.feed_forward.down_proj",
121
+ "model.vision_tower.transformer.layers.10.attention.k_proj",
122
+ "model.vision_tower.transformer.layers.10.attention.v_proj",
123
+ "model.vision_tower.transformer.layers.10.attention.q_proj",
124
+ "model.vision_tower.transformer.layers.10.attention.o_proj",
125
+ "model.vision_tower.transformer.layers.11.feed_forward.gate_proj",
126
+ "model.vision_tower.transformer.layers.11.feed_forward.up_proj",
127
+ "model.vision_tower.transformer.layers.11.feed_forward.down_proj",
128
+ "model.vision_tower.transformer.layers.11.attention.k_proj",
129
+ "model.vision_tower.transformer.layers.11.attention.v_proj",
130
+ "model.vision_tower.transformer.layers.11.attention.q_proj",
131
+ "model.vision_tower.transformer.layers.11.attention.o_proj",
132
+ "model.vision_tower.transformer.layers.12.feed_forward.gate_proj",
133
+ "model.vision_tower.transformer.layers.12.feed_forward.up_proj",
134
+ "model.vision_tower.transformer.layers.12.feed_forward.down_proj",
135
+ "model.vision_tower.transformer.layers.12.attention.k_proj",
136
+ "model.vision_tower.transformer.layers.12.attention.v_proj",
137
+ "model.vision_tower.transformer.layers.12.attention.q_proj",
138
+ "model.vision_tower.transformer.layers.12.attention.o_proj",
139
+ "model.vision_tower.transformer.layers.13.feed_forward.gate_proj",
140
+ "model.vision_tower.transformer.layers.13.feed_forward.up_proj",
141
+ "model.vision_tower.transformer.layers.13.feed_forward.down_proj",
142
+ "model.vision_tower.transformer.layers.13.attention.k_proj",
143
+ "model.vision_tower.transformer.layers.13.attention.v_proj",
144
+ "model.vision_tower.transformer.layers.13.attention.q_proj",
145
+ "model.vision_tower.transformer.layers.13.attention.o_proj",
146
+ "model.vision_tower.transformer.layers.14.feed_forward.gate_proj",
147
+ "model.vision_tower.transformer.layers.14.feed_forward.up_proj",
148
+ "model.vision_tower.transformer.layers.14.feed_forward.down_proj",
149
+ "model.vision_tower.transformer.layers.14.attention.k_proj",
150
+ "model.vision_tower.transformer.layers.14.attention.v_proj",
151
+ "model.vision_tower.transformer.layers.14.attention.q_proj",
152
+ "model.vision_tower.transformer.layers.14.attention.o_proj",
153
+ "model.vision_tower.transformer.layers.15.feed_forward.gate_proj",
154
+ "model.vision_tower.transformer.layers.15.feed_forward.up_proj",
155
+ "model.vision_tower.transformer.layers.15.feed_forward.down_proj",
156
+ "model.vision_tower.transformer.layers.15.attention.k_proj",
157
+ "model.vision_tower.transformer.layers.15.attention.v_proj",
158
+ "model.vision_tower.transformer.layers.15.attention.q_proj",
159
+ "model.vision_tower.transformer.layers.15.attention.o_proj",
160
+ "model.vision_tower.transformer.layers.16.feed_forward.gate_proj",
161
+ "model.vision_tower.transformer.layers.16.feed_forward.up_proj",
162
+ "model.vision_tower.transformer.layers.16.feed_forward.down_proj",
163
+ "model.vision_tower.transformer.layers.16.attention.k_proj",
164
+ "model.vision_tower.transformer.layers.16.attention.v_proj",
165
+ "model.vision_tower.transformer.layers.16.attention.q_proj",
166
+ "model.vision_tower.transformer.layers.16.attention.o_proj",
167
+ "model.vision_tower.transformer.layers.17.feed_forward.gate_proj",
168
+ "model.vision_tower.transformer.layers.17.feed_forward.up_proj",
169
+ "model.vision_tower.transformer.layers.17.feed_forward.down_proj",
170
+ "model.vision_tower.transformer.layers.17.attention.k_proj",
171
+ "model.vision_tower.transformer.layers.17.attention.v_proj",
172
+ "model.vision_tower.transformer.layers.17.attention.q_proj",
173
+ "model.vision_tower.transformer.layers.17.attention.o_proj",
174
+ "model.vision_tower.transformer.layers.18.feed_forward.gate_proj",
175
+ "model.vision_tower.transformer.layers.18.feed_forward.up_proj",
176
+ "model.vision_tower.transformer.layers.18.feed_forward.down_proj",
177
+ "model.vision_tower.transformer.layers.18.attention.k_proj",
178
+ "model.vision_tower.transformer.layers.18.attention.v_proj",
179
+ "model.vision_tower.transformer.layers.18.attention.q_proj",
180
+ "model.vision_tower.transformer.layers.18.attention.o_proj",
181
+ "model.vision_tower.transformer.layers.19.feed_forward.gate_proj",
182
+ "model.vision_tower.transformer.layers.19.feed_forward.up_proj",
183
+ "model.vision_tower.transformer.layers.19.feed_forward.down_proj",
184
+ "model.vision_tower.transformer.layers.19.attention.k_proj",
185
+ "model.vision_tower.transformer.layers.19.attention.v_proj",
186
+ "model.vision_tower.transformer.layers.19.attention.q_proj",
187
+ "model.vision_tower.transformer.layers.19.attention.o_proj",
188
+ "model.vision_tower.transformer.layers.20.feed_forward.gate_proj",
189
+ "model.vision_tower.transformer.layers.20.feed_forward.up_proj",
190
+ "model.vision_tower.transformer.layers.20.feed_forward.down_proj",
191
+ "model.vision_tower.transformer.layers.20.attention.k_proj",
192
+ "model.vision_tower.transformer.layers.20.attention.v_proj",
193
+ "model.vision_tower.transformer.layers.20.attention.q_proj",
194
+ "model.vision_tower.transformer.layers.20.attention.o_proj",
195
+ "model.vision_tower.transformer.layers.21.feed_forward.gate_proj",
196
+ "model.vision_tower.transformer.layers.21.feed_forward.up_proj",
197
+ "model.vision_tower.transformer.layers.21.feed_forward.down_proj",
198
+ "model.vision_tower.transformer.layers.21.attention.k_proj",
199
+ "model.vision_tower.transformer.layers.21.attention.v_proj",
200
+ "model.vision_tower.transformer.layers.21.attention.q_proj",
201
+ "model.vision_tower.transformer.layers.21.attention.o_proj",
202
+ "model.vision_tower.transformer.layers.22.feed_forward.gate_proj",
203
+ "model.vision_tower.transformer.layers.22.feed_forward.up_proj",
204
+ "model.vision_tower.transformer.layers.22.feed_forward.down_proj",
205
+ "model.vision_tower.transformer.layers.22.attention.k_proj",
206
+ "model.vision_tower.transformer.layers.22.attention.v_proj",
207
+ "model.vision_tower.transformer.layers.22.attention.q_proj",
208
+ "model.vision_tower.transformer.layers.22.attention.o_proj",
209
+ "model.vision_tower.transformer.layers.23.feed_forward.gate_proj",
210
+ "model.vision_tower.transformer.layers.23.feed_forward.up_proj",
211
+ "model.vision_tower.transformer.layers.23.feed_forward.down_proj",
212
+ "model.vision_tower.transformer.layers.23.attention.k_proj",
213
+ "model.vision_tower.transformer.layers.23.attention.v_proj",
214
+ "model.vision_tower.transformer.layers.23.attention.q_proj",
215
+ "model.vision_tower.transformer.layers.23.attention.o_proj",
216
+ "model.multi_modal_projector.patch_merger.merging_layer",
217
+ "model.multi_modal_projector.linear_1",
218
+ "model.multi_modal_projector.linear_2",
219
+ "lm_head"
220
+ ],
221
+ "kv_cache_scheme": null,
222
+ "quant_method": "compressed-tensors",
223
+ "quantization_status": "compressed",
224
+ "sparsity_config": {},
225
+ "transform_config": {},
226
+ "version": "0.13.0"
227
+ },
228
+ "spatial_merge_size": 2,
229
+ "text_config": {
230
+ "attention_dropout": 0.0,
231
+ "head_dim": 128,
232
+ "hidden_act": "silu",
233
+ "hidden_size": 4096,
234
+ "initializer_range": 0.02,
235
+ "intermediate_size": 14336,
236
+ "max_position_embeddings": 262144,
237
+ "model_type": "ministral3",
238
+ "num_attention_heads": 32,
239
+ "num_hidden_layers": 34,
240
+ "num_key_value_heads": 8,
241
+ "rms_norm_eps": 1e-05,
242
+ "rope_parameters": {
243
+ "beta_fast": 32.0,
244
+ "beta_slow": 1.0,
245
+ "factor": 16.0,
246
+ "llama_4_scaling_beta": 0.1,
247
+ "mscale": 1.0,
248
+ "mscale_all_dim": 1.0,
249
+ "original_max_position_embeddings": 16384,
250
+ "rope_theta": 1000000.0,
251
+ "rope_type": "yarn",
252
+ "type": "yarn"
253
+ },
254
+ "sliding_window": null,
255
+ "use_cache": true,
256
+ "vocab_size": 131072
257
+ },
258
+ "transformers_version": "5.0.0.dev0",
259
+ "vision_config": {
260
+ "attention_dropout": 0.0,
261
+ "head_dim": 64,
262
+ "hidden_act": "silu",
263
+ "hidden_size": 1024,
264
+ "image_size": 1540,
265
+ "initializer_range": 0.02,
266
+ "intermediate_size": 4096,
267
+ "model_type": "pixtral",
268
+ "num_attention_heads": 16,
269
+ "num_channels": 3,
270
+ "num_hidden_layers": 24,
271
+ "patch_size": 14,
272
+ "rope_parameters": {
273
+ "rope_theta": 10000.0,
274
+ "rope_type": "default"
275
+ }
276
+ },
277
+ "vision_feature_layer": -1
278
+ }
generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 1,
3
+ "eos_token_id": [
4
+ 2
5
+ ],
6
+ "max_length": 262144,
7
+ "pad_token_id": 11,
8
+ "transformers_version": "5.0.0rc1"
9
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:452bea725cdd91823d4e914e76a17151e2a82ca9da1e8dd2244bdf715543ad1d
3
+ size 9566567984
params.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dim": 4096,
3
+ "n_layers": 34,
4
+ "head_dim": 128,
5
+ "hidden_dim": 14336,
6
+ "n_heads": 32,
7
+ "n_kv_heads": 8,
8
+ "rope_theta": 1000000.0,
9
+ "norm_eps": 1e-05,
10
+ "vocab_size": 131072,
11
+ "tied_embeddings": false,
12
+ "max_position_embeddings": 262144,
13
+ "llama_4_scaling": {
14
+ "original_max_position_embeddings": 16384,
15
+ "beta": 0.1
16
+ },
17
+ "q_lora_rank": null,
18
+ "qk_rope_head_dim": null,
19
+ "qk_nope_head_dim": null,
20
+ "kv_lora_rank": null,
21
+ "v_head_dim": null,
22
+ "yarn": {
23
+ "original_max_position_embeddings": 16384,
24
+ "factor": 16,
25
+ "apply_scale": false,
26
+ "beta": 32,
27
+ "alpha": 1
28
+ },
29
+ "vision_encoder": {
30
+ "image_token_id": 10,
31
+ "image_break_token_id": 12,
32
+ "image_end_token_id": 13,
33
+ "intermediate_size": 4096,
34
+ "num_hidden_layers": 24,
35
+ "num_attention_heads": 16,
36
+ "mm_projector_id": "patch_merge",
37
+ "spatial_merge_size": 2,
38
+ "hidden_size": 1024,
39
+ "num_channels": 3,
40
+ "image_size": 1540,
41
+ "max_image_size": 1540,
42
+ "patch_size": 14,
43
+ "rope_theta": 10000.0,
44
+ "add_pre_mm_projector_layer_norm": true,
45
+ "adapter_bias": false
46
+ }
47
+ }
processor_config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "image_break_token": "[IMG_BREAK]",
3
+ "image_end_token": "[IMG_END]",
4
+ "image_processor": {
5
+ "crop_size": null,
6
+ "data_format": "channels_first",
7
+ "device": null,
8
+ "disable_grouping": null,
9
+ "do_center_crop": null,
10
+ "do_convert_rgb": true,
11
+ "do_normalize": true,
12
+ "do_pad": null,
13
+ "do_rescale": true,
14
+ "do_resize": true,
15
+ "image_mean": [
16
+ 0.48145466,
17
+ 0.4578275,
18
+ 0.40821073
19
+ ],
20
+ "image_processor_type": "PixtralImageProcessorFast",
21
+ "image_seq_length": null,
22
+ "image_std": [
23
+ 0.26862954,
24
+ 0.26130258,
25
+ 0.27577711
26
+ ],
27
+ "input_data_format": null,
28
+ "pad_size": null,
29
+ "patch_size": 14,
30
+ "processor_class": "PixtralProcessor",
31
+ "resample": 3,
32
+ "rescale_factor": 0.00392156862745098,
33
+ "return_tensors": null,
34
+ "size": {
35
+ "longest_edge": 1540
36
+ }
37
+ },
38
+ "image_token": "[IMG]",
39
+ "patch_size": 14,
40
+ "processor_class": "PixtralProcessor",
41
+ "spatial_merge_size": 2
42
+ }
recipe.yaml ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ default_stage:
2
+ default_modifiers:
3
+ QuantizationModifier:
4
+ targets: [Linear]
5
+ ignore: [lm_head, 're:.*vision_tower.*', 're:.*multi_modal_projector.*', 're:.*merger.*',
6
+ 're:.*embed_tokens.*']
7
+ scheme: FP8_DYNAMIC
tekken.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e29d19ea32eb7e26e6c0572d57cb7f9eca0f4420e0e0fe6ae1cf3be94da1c0d6
3
+ size 16753777
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5aa98f5a90c72d9c2348c26e16c50779e9d4cc7810fb781bc5d8734a5b97902f
3
+ size 17077880
tokenizer_config.json ADDED
@@ -0,0 +1,1010 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": null,
3
+ "backend": "tokenizers",
4
+ "extra_special_tokens": [
5
+ "<unk>",
6
+ "<s>",
7
+ "</s>",
8
+ "[INST]",
9
+ "[/INST]",
10
+ "[AVAILABLE_TOOLS]",
11
+ "[/AVAILABLE_TOOLS]",
12
+ "[TOOL_RESULTS]",
13
+ "[/TOOL_RESULTS]",
14
+ "[TOOL_CALLS]",
15
+ "[IMG]",
16
+ "<pad>",
17
+ "[IMG_BREAK]",
18
+ "[IMG_END]",
19
+ "[PREFIX]",
20
+ "[MIDDLE]",
21
+ "[SUFFIX]",
22
+ "[SYSTEM_PROMPT]",
23
+ "[/SYSTEM_PROMPT]",
24
+ "[TOOL_CONTENT]",
25
+ "<SPECIAL_20>",
26
+ "<SPECIAL_21>",
27
+ "<SPECIAL_22>",
28
+ "<SPECIAL_23>",
29
+ "[AUDIO]",
30
+ "[BEGIN_AUDIO]",
31
+ "<SPECIAL_26>",
32
+ "<SPECIAL_27>",
33
+ "<SPECIAL_28>",
34
+ "<SPECIAL_29>",
35
+ "<SPECIAL_30>",
36
+ "<SPECIAL_31>",
37
+ "[ARGS]",
38
+ "[CALL_ID]",
39
+ "[THINK]",
40
+ "[/THINK]",
41
+ "<SPECIAL_36>",
42
+ "<SPECIAL_37>",
43
+ "<SPECIAL_38>",
44
+ "<SPECIAL_39>",
45
+ "<SPECIAL_40>",
46
+ "<SPECIAL_41>",
47
+ "<SPECIAL_42>",
48
+ "<SPECIAL_43>",
49
+ "<SPECIAL_44>",
50
+ "<SPECIAL_45>",
51
+ "<SPECIAL_46>",
52
+ "<SPECIAL_47>",
53
+ "<SPECIAL_48>",
54
+ "<SPECIAL_49>",
55
+ "<SPECIAL_50>",
56
+ "<SPECIAL_51>",
57
+ "<SPECIAL_52>",
58
+ "<SPECIAL_53>",
59
+ "<SPECIAL_54>",
60
+ "<SPECIAL_55>",
61
+ "<SPECIAL_56>",
62
+ "<SPECIAL_57>",
63
+ "<SPECIAL_58>",
64
+ "<SPECIAL_59>",
65
+ "<SPECIAL_60>",
66
+ "<SPECIAL_61>",
67
+ "<SPECIAL_62>",
68
+ "<SPECIAL_63>",
69
+ "<SPECIAL_64>",
70
+ "<SPECIAL_65>",
71
+ "<SPECIAL_66>",
72
+ "<SPECIAL_67>",
73
+ "<SPECIAL_68>",
74
+ "<SPECIAL_69>",
75
+ "<SPECIAL_70>",
76
+ "<SPECIAL_71>",
77
+ "<SPECIAL_72>",
78
+ "<SPECIAL_73>",
79
+ "<SPECIAL_74>",
80
+ "<SPECIAL_75>",
81
+ "<SPECIAL_76>",
82
+ "<SPECIAL_77>",
83
+ "<SPECIAL_78>",
84
+ "<SPECIAL_79>",
85
+ "<SPECIAL_80>",
86
+ "<SPECIAL_81>",
87
+ "<SPECIAL_82>",
88
+ "<SPECIAL_83>",
89
+ "<SPECIAL_84>",
90
+ "<SPECIAL_85>",
91
+ "<SPECIAL_86>",
92
+ "<SPECIAL_87>",
93
+ "<SPECIAL_88>",
94
+ "<SPECIAL_89>",
95
+ "<SPECIAL_90>",
96
+ "<SPECIAL_91>",
97
+ "<SPECIAL_92>",
98
+ "<SPECIAL_93>",
99
+ "<SPECIAL_94>",
100
+ "<SPECIAL_95>",
101
+ "<SPECIAL_96>",
102
+ "<SPECIAL_97>",
103
+ "<SPECIAL_98>",
104
+ "<SPECIAL_99>",
105
+ "<SPECIAL_100>",
106
+ "<SPECIAL_101>",
107
+ "<SPECIAL_102>",
108
+ "<SPECIAL_103>",
109
+ "<SPECIAL_104>",
110
+ "<SPECIAL_105>",
111
+ "<SPECIAL_106>",
112
+ "<SPECIAL_107>",
113
+ "<SPECIAL_108>",
114
+ "<SPECIAL_109>",
115
+ "<SPECIAL_110>",
116
+ "<SPECIAL_111>",
117
+ "<SPECIAL_112>",
118
+ "<SPECIAL_113>",
119
+ "<SPECIAL_114>",
120
+ "<SPECIAL_115>",
121
+ "<SPECIAL_116>",
122
+ "<SPECIAL_117>",
123
+ "<SPECIAL_118>",
124
+ "<SPECIAL_119>",
125
+ "<SPECIAL_120>",
126
+ "<SPECIAL_121>",
127
+ "<SPECIAL_122>",
128
+ "<SPECIAL_123>",
129
+ "<SPECIAL_124>",
130
+ "<SPECIAL_125>",
131
+ "<SPECIAL_126>",
132
+ "<SPECIAL_127>",
133
+ "<SPECIAL_128>",
134
+ "<SPECIAL_129>",
135
+ "<SPECIAL_130>",
136
+ "<SPECIAL_131>",
137
+ "<SPECIAL_132>",
138
+ "<SPECIAL_133>",
139
+ "<SPECIAL_134>",
140
+ "<SPECIAL_135>",
141
+ "<SPECIAL_136>",
142
+ "<SPECIAL_137>",
143
+ "<SPECIAL_138>",
144
+ "<SPECIAL_139>",
145
+ "<SPECIAL_140>",
146
+ "<SPECIAL_141>",
147
+ "<SPECIAL_142>",
148
+ "<SPECIAL_143>",
149
+ "<SPECIAL_144>",
150
+ "<SPECIAL_145>",
151
+ "<SPECIAL_146>",
152
+ "<SPECIAL_147>",
153
+ "<SPECIAL_148>",
154
+ "<SPECIAL_149>",
155
+ "<SPECIAL_150>",
156
+ "<SPECIAL_151>",
157
+ "<SPECIAL_152>",
158
+ "<SPECIAL_153>",
159
+ "<SPECIAL_154>",
160
+ "<SPECIAL_155>",
161
+ "<SPECIAL_156>",
162
+ "<SPECIAL_157>",
163
+ "<SPECIAL_158>",
164
+ "<SPECIAL_159>",
165
+ "<SPECIAL_160>",
166
+ "<SPECIAL_161>",
167
+ "<SPECIAL_162>",
168
+ "<SPECIAL_163>",
169
+ "<SPECIAL_164>",
170
+ "<SPECIAL_165>",
171
+ "<SPECIAL_166>",
172
+ "<SPECIAL_167>",
173
+ "<SPECIAL_168>",
174
+ "<SPECIAL_169>",
175
+ "<SPECIAL_170>",
176
+ "<SPECIAL_171>",
177
+ "<SPECIAL_172>",
178
+ "<SPECIAL_173>",
179
+ "<SPECIAL_174>",
180
+ "<SPECIAL_175>",
181
+ "<SPECIAL_176>",
182
+ "<SPECIAL_177>",
183
+ "<SPECIAL_178>",
184
+ "<SPECIAL_179>",
185
+ "<SPECIAL_180>",
186
+ "<SPECIAL_181>",
187
+ "<SPECIAL_182>",
188
+ "<SPECIAL_183>",
189
+ "<SPECIAL_184>",
190
+ "<SPECIAL_185>",
191
+ "<SPECIAL_186>",
192
+ "<SPECIAL_187>",
193
+ "<SPECIAL_188>",
194
+ "<SPECIAL_189>",
195
+ "<SPECIAL_190>",
196
+ "<SPECIAL_191>",
197
+ "<SPECIAL_192>",
198
+ "<SPECIAL_193>",
199
+ "<SPECIAL_194>",
200
+ "<SPECIAL_195>",
201
+ "<SPECIAL_196>",
202
+ "<SPECIAL_197>",
203
+ "<SPECIAL_198>",
204
+ "<SPECIAL_199>",
205
+ "<SPECIAL_200>",
206
+ "<SPECIAL_201>",
207
+ "<SPECIAL_202>",
208
+ "<SPECIAL_203>",
209
+ "<SPECIAL_204>",
210
+ "<SPECIAL_205>",
211
+ "<SPECIAL_206>",
212
+ "<SPECIAL_207>",
213
+ "<SPECIAL_208>",
214
+ "<SPECIAL_209>",
215
+ "<SPECIAL_210>",
216
+ "<SPECIAL_211>",
217
+ "<SPECIAL_212>",
218
+ "<SPECIAL_213>",
219
+ "<SPECIAL_214>",
220
+ "<SPECIAL_215>",
221
+ "<SPECIAL_216>",
222
+ "<SPECIAL_217>",
223
+ "<SPECIAL_218>",
224
+ "<SPECIAL_219>",
225
+ "<SPECIAL_220>",
226
+ "<SPECIAL_221>",
227
+ "<SPECIAL_222>",
228
+ "<SPECIAL_223>",
229
+ "<SPECIAL_224>",
230
+ "<SPECIAL_225>",
231
+ "<SPECIAL_226>",
232
+ "<SPECIAL_227>",
233
+ "<SPECIAL_228>",
234
+ "<SPECIAL_229>",
235
+ "<SPECIAL_230>",
236
+ "<SPECIAL_231>",
237
+ "<SPECIAL_232>",
238
+ "<SPECIAL_233>",
239
+ "<SPECIAL_234>",
240
+ "<SPECIAL_235>",
241
+ "<SPECIAL_236>",
242
+ "<SPECIAL_237>",
243
+ "<SPECIAL_238>",
244
+ "<SPECIAL_239>",
245
+ "<SPECIAL_240>",
246
+ "<SPECIAL_241>",
247
+ "<SPECIAL_242>",
248
+ "<SPECIAL_243>",
249
+ "<SPECIAL_244>",
250
+ "<SPECIAL_245>",
251
+ "<SPECIAL_246>",
252
+ "<SPECIAL_247>",
253
+ "<SPECIAL_248>",
254
+ "<SPECIAL_249>",
255
+ "<SPECIAL_250>",
256
+ "<SPECIAL_251>",
257
+ "<SPECIAL_252>",
258
+ "<SPECIAL_253>",
259
+ "<SPECIAL_254>",
260
+ "<SPECIAL_255>",
261
+ "<SPECIAL_256>",
262
+ "<SPECIAL_257>",
263
+ "<SPECIAL_258>",
264
+ "<SPECIAL_259>",
265
+ "<SPECIAL_260>",
266
+ "<SPECIAL_261>",
267
+ "<SPECIAL_262>",
268
+ "<SPECIAL_263>",
269
+ "<SPECIAL_264>",
270
+ "<SPECIAL_265>",
271
+ "<SPECIAL_266>",
272
+ "<SPECIAL_267>",
273
+ "<SPECIAL_268>",
274
+ "<SPECIAL_269>",
275
+ "<SPECIAL_270>",
276
+ "<SPECIAL_271>",
277
+ "<SPECIAL_272>",
278
+ "<SPECIAL_273>",
279
+ "<SPECIAL_274>",
280
+ "<SPECIAL_275>",
281
+ "<SPECIAL_276>",
282
+ "<SPECIAL_277>",
283
+ "<SPECIAL_278>",
284
+ "<SPECIAL_279>",
285
+ "<SPECIAL_280>",
286
+ "<SPECIAL_281>",
287
+ "<SPECIAL_282>",
288
+ "<SPECIAL_283>",
289
+ "<SPECIAL_284>",
290
+ "<SPECIAL_285>",
291
+ "<SPECIAL_286>",
292
+ "<SPECIAL_287>",
293
+ "<SPECIAL_288>",
294
+ "<SPECIAL_289>",
295
+ "<SPECIAL_290>",
296
+ "<SPECIAL_291>",
297
+ "<SPECIAL_292>",
298
+ "<SPECIAL_293>",
299
+ "<SPECIAL_294>",
300
+ "<SPECIAL_295>",
301
+ "<SPECIAL_296>",
302
+ "<SPECIAL_297>",
303
+ "<SPECIAL_298>",
304
+ "<SPECIAL_299>",
305
+ "<SPECIAL_300>",
306
+ "<SPECIAL_301>",
307
+ "<SPECIAL_302>",
308
+ "<SPECIAL_303>",
309
+ "<SPECIAL_304>",
310
+ "<SPECIAL_305>",
311
+ "<SPECIAL_306>",
312
+ "<SPECIAL_307>",
313
+ "<SPECIAL_308>",
314
+ "<SPECIAL_309>",
315
+ "<SPECIAL_310>",
316
+ "<SPECIAL_311>",
317
+ "<SPECIAL_312>",
318
+ "<SPECIAL_313>",
319
+ "<SPECIAL_314>",
320
+ "<SPECIAL_315>",
321
+ "<SPECIAL_316>",
322
+ "<SPECIAL_317>",
323
+ "<SPECIAL_318>",
324
+ "<SPECIAL_319>",
325
+ "<SPECIAL_320>",
326
+ "<SPECIAL_321>",
327
+ "<SPECIAL_322>",
328
+ "<SPECIAL_323>",
329
+ "<SPECIAL_324>",
330
+ "<SPECIAL_325>",
331
+ "<SPECIAL_326>",
332
+ "<SPECIAL_327>",
333
+ "<SPECIAL_328>",
334
+ "<SPECIAL_329>",
335
+ "<SPECIAL_330>",
336
+ "<SPECIAL_331>",
337
+ "<SPECIAL_332>",
338
+ "<SPECIAL_333>",
339
+ "<SPECIAL_334>",
340
+ "<SPECIAL_335>",
341
+ "<SPECIAL_336>",
342
+ "<SPECIAL_337>",
343
+ "<SPECIAL_338>",
344
+ "<SPECIAL_339>",
345
+ "<SPECIAL_340>",
346
+ "<SPECIAL_341>",
347
+ "<SPECIAL_342>",
348
+ "<SPECIAL_343>",
349
+ "<SPECIAL_344>",
350
+ "<SPECIAL_345>",
351
+ "<SPECIAL_346>",
352
+ "<SPECIAL_347>",
353
+ "<SPECIAL_348>",
354
+ "<SPECIAL_349>",
355
+ "<SPECIAL_350>",
356
+ "<SPECIAL_351>",
357
+ "<SPECIAL_352>",
358
+ "<SPECIAL_353>",
359
+ "<SPECIAL_354>",
360
+ "<SPECIAL_355>",
361
+ "<SPECIAL_356>",
362
+ "<SPECIAL_357>",
363
+ "<SPECIAL_358>",
364
+ "<SPECIAL_359>",
365
+ "<SPECIAL_360>",
366
+ "<SPECIAL_361>",
367
+ "<SPECIAL_362>",
368
+ "<SPECIAL_363>",
369
+ "<SPECIAL_364>",
370
+ "<SPECIAL_365>",
371
+ "<SPECIAL_366>",
372
+ "<SPECIAL_367>",
373
+ "<SPECIAL_368>",
374
+ "<SPECIAL_369>",
375
+ "<SPECIAL_370>",
376
+ "<SPECIAL_371>",
377
+ "<SPECIAL_372>",
378
+ "<SPECIAL_373>",
379
+ "<SPECIAL_374>",
380
+ "<SPECIAL_375>",
381
+ "<SPECIAL_376>",
382
+ "<SPECIAL_377>",
383
+ "<SPECIAL_378>",
384
+ "<SPECIAL_379>",
385
+ "<SPECIAL_380>",
386
+ "<SPECIAL_381>",
387
+ "<SPECIAL_382>",
388
+ "<SPECIAL_383>",
389
+ "<SPECIAL_384>",
390
+ "<SPECIAL_385>",
391
+ "<SPECIAL_386>",
392
+ "<SPECIAL_387>",
393
+ "<SPECIAL_388>",
394
+ "<SPECIAL_389>",
395
+ "<SPECIAL_390>",
396
+ "<SPECIAL_391>",
397
+ "<SPECIAL_392>",
398
+ "<SPECIAL_393>",
399
+ "<SPECIAL_394>",
400
+ "<SPECIAL_395>",
401
+ "<SPECIAL_396>",
402
+ "<SPECIAL_397>",
403
+ "<SPECIAL_398>",
404
+ "<SPECIAL_399>",
405
+ "<SPECIAL_400>",
406
+ "<SPECIAL_401>",
407
+ "<SPECIAL_402>",
408
+ "<SPECIAL_403>",
409
+ "<SPECIAL_404>",
410
+ "<SPECIAL_405>",
411
+ "<SPECIAL_406>",
412
+ "<SPECIAL_407>",
413
+ "<SPECIAL_408>",
414
+ "<SPECIAL_409>",
415
+ "<SPECIAL_410>",
416
+ "<SPECIAL_411>",
417
+ "<SPECIAL_412>",
418
+ "<SPECIAL_413>",
419
+ "<SPECIAL_414>",
420
+ "<SPECIAL_415>",
421
+ "<SPECIAL_416>",
422
+ "<SPECIAL_417>",
423
+ "<SPECIAL_418>",
424
+ "<SPECIAL_419>",
425
+ "<SPECIAL_420>",
426
+ "<SPECIAL_421>",
427
+ "<SPECIAL_422>",
428
+ "<SPECIAL_423>",
429
+ "<SPECIAL_424>",
430
+ "<SPECIAL_425>",
431
+ "<SPECIAL_426>",
432
+ "<SPECIAL_427>",
433
+ "<SPECIAL_428>",
434
+ "<SPECIAL_429>",
435
+ "<SPECIAL_430>",
436
+ "<SPECIAL_431>",
437
+ "<SPECIAL_432>",
438
+ "<SPECIAL_433>",
439
+ "<SPECIAL_434>",
440
+ "<SPECIAL_435>",
441
+ "<SPECIAL_436>",
442
+ "<SPECIAL_437>",
443
+ "<SPECIAL_438>",
444
+ "<SPECIAL_439>",
445
+ "<SPECIAL_440>",
446
+ "<SPECIAL_441>",
447
+ "<SPECIAL_442>",
448
+ "<SPECIAL_443>",
449
+ "<SPECIAL_444>",
450
+ "<SPECIAL_445>",
451
+ "<SPECIAL_446>",
452
+ "<SPECIAL_447>",
453
+ "<SPECIAL_448>",
454
+ "<SPECIAL_449>",
455
+ "<SPECIAL_450>",
456
+ "<SPECIAL_451>",
457
+ "<SPECIAL_452>",
458
+ "<SPECIAL_453>",
459
+ "<SPECIAL_454>",
460
+ "<SPECIAL_455>",
461
+ "<SPECIAL_456>",
462
+ "<SPECIAL_457>",
463
+ "<SPECIAL_458>",
464
+ "<SPECIAL_459>",
465
+ "<SPECIAL_460>",
466
+ "<SPECIAL_461>",
467
+ "<SPECIAL_462>",
468
+ "<SPECIAL_463>",
469
+ "<SPECIAL_464>",
470
+ "<SPECIAL_465>",
471
+ "<SPECIAL_466>",
472
+ "<SPECIAL_467>",
473
+ "<SPECIAL_468>",
474
+ "<SPECIAL_469>",
475
+ "<SPECIAL_470>",
476
+ "<SPECIAL_471>",
477
+ "<SPECIAL_472>",
478
+ "<SPECIAL_473>",
479
+ "<SPECIAL_474>",
480
+ "<SPECIAL_475>",
481
+ "<SPECIAL_476>",
482
+ "<SPECIAL_477>",
483
+ "<SPECIAL_478>",
484
+ "<SPECIAL_479>",
485
+ "<SPECIAL_480>",
486
+ "<SPECIAL_481>",
487
+ "<SPECIAL_482>",
488
+ "<SPECIAL_483>",
489
+ "<SPECIAL_484>",
490
+ "<SPECIAL_485>",
491
+ "<SPECIAL_486>",
492
+ "<SPECIAL_487>",
493
+ "<SPECIAL_488>",
494
+ "<SPECIAL_489>",
495
+ "<SPECIAL_490>",
496
+ "<SPECIAL_491>",
497
+ "<SPECIAL_492>",
498
+ "<SPECIAL_493>",
499
+ "<SPECIAL_494>",
500
+ "<SPECIAL_495>",
501
+ "<SPECIAL_496>",
502
+ "<SPECIAL_497>",
503
+ "<SPECIAL_498>",
504
+ "<SPECIAL_499>",
505
+ "<SPECIAL_500>",
506
+ "<SPECIAL_501>",
507
+ "<SPECIAL_502>",
508
+ "<SPECIAL_503>",
509
+ "<SPECIAL_504>",
510
+ "<SPECIAL_505>",
511
+ "<SPECIAL_506>",
512
+ "<SPECIAL_507>",
513
+ "<SPECIAL_508>",
514
+ "<SPECIAL_509>",
515
+ "<SPECIAL_510>",
516
+ "<SPECIAL_511>",
517
+ "<SPECIAL_512>",
518
+ "<SPECIAL_513>",
519
+ "<SPECIAL_514>",
520
+ "<SPECIAL_515>",
521
+ "<SPECIAL_516>",
522
+ "<SPECIAL_517>",
523
+ "<SPECIAL_518>",
524
+ "<SPECIAL_519>",
525
+ "<SPECIAL_520>",
526
+ "<SPECIAL_521>",
527
+ "<SPECIAL_522>",
528
+ "<SPECIAL_523>",
529
+ "<SPECIAL_524>",
530
+ "<SPECIAL_525>",
531
+ "<SPECIAL_526>",
532
+ "<SPECIAL_527>",
533
+ "<SPECIAL_528>",
534
+ "<SPECIAL_529>",
535
+ "<SPECIAL_530>",
536
+ "<SPECIAL_531>",
537
+ "<SPECIAL_532>",
538
+ "<SPECIAL_533>",
539
+ "<SPECIAL_534>",
540
+ "<SPECIAL_535>",
541
+ "<SPECIAL_536>",
542
+ "<SPECIAL_537>",
543
+ "<SPECIAL_538>",
544
+ "<SPECIAL_539>",
545
+ "<SPECIAL_540>",
546
+ "<SPECIAL_541>",
547
+ "<SPECIAL_542>",
548
+ "<SPECIAL_543>",
549
+ "<SPECIAL_544>",
550
+ "<SPECIAL_545>",
551
+ "<SPECIAL_546>",
552
+ "<SPECIAL_547>",
553
+ "<SPECIAL_548>",
554
+ "<SPECIAL_549>",
555
+ "<SPECIAL_550>",
556
+ "<SPECIAL_551>",
557
+ "<SPECIAL_552>",
558
+ "<SPECIAL_553>",
559
+ "<SPECIAL_554>",
560
+ "<SPECIAL_555>",
561
+ "<SPECIAL_556>",
562
+ "<SPECIAL_557>",
563
+ "<SPECIAL_558>",
564
+ "<SPECIAL_559>",
565
+ "<SPECIAL_560>",
566
+ "<SPECIAL_561>",
567
+ "<SPECIAL_562>",
568
+ "<SPECIAL_563>",
569
+ "<SPECIAL_564>",
570
+ "<SPECIAL_565>",
571
+ "<SPECIAL_566>",
572
+ "<SPECIAL_567>",
573
+ "<SPECIAL_568>",
574
+ "<SPECIAL_569>",
575
+ "<SPECIAL_570>",
576
+ "<SPECIAL_571>",
577
+ "<SPECIAL_572>",
578
+ "<SPECIAL_573>",
579
+ "<SPECIAL_574>",
580
+ "<SPECIAL_575>",
581
+ "<SPECIAL_576>",
582
+ "<SPECIAL_577>",
583
+ "<SPECIAL_578>",
584
+ "<SPECIAL_579>",
585
+ "<SPECIAL_580>",
586
+ "<SPECIAL_581>",
587
+ "<SPECIAL_582>",
588
+ "<SPECIAL_583>",
589
+ "<SPECIAL_584>",
590
+ "<SPECIAL_585>",
591
+ "<SPECIAL_586>",
592
+ "<SPECIAL_587>",
593
+ "<SPECIAL_588>",
594
+ "<SPECIAL_589>",
595
+ "<SPECIAL_590>",
596
+ "<SPECIAL_591>",
597
+ "<SPECIAL_592>",
598
+ "<SPECIAL_593>",
599
+ "<SPECIAL_594>",
600
+ "<SPECIAL_595>",
601
+ "<SPECIAL_596>",
602
+ "<SPECIAL_597>",
603
+ "<SPECIAL_598>",
604
+ "<SPECIAL_599>",
605
+ "<SPECIAL_600>",
606
+ "<SPECIAL_601>",
607
+ "<SPECIAL_602>",
608
+ "<SPECIAL_603>",
609
+ "<SPECIAL_604>",
610
+ "<SPECIAL_605>",
611
+ "<SPECIAL_606>",
612
+ "<SPECIAL_607>",
613
+ "<SPECIAL_608>",
614
+ "<SPECIAL_609>",
615
+ "<SPECIAL_610>",
616
+ "<SPECIAL_611>",
617
+ "<SPECIAL_612>",
618
+ "<SPECIAL_613>",
619
+ "<SPECIAL_614>",
620
+ "<SPECIAL_615>",
621
+ "<SPECIAL_616>",
622
+ "<SPECIAL_617>",
623
+ "<SPECIAL_618>",
624
+ "<SPECIAL_619>",
625
+ "<SPECIAL_620>",
626
+ "<SPECIAL_621>",
627
+ "<SPECIAL_622>",
628
+ "<SPECIAL_623>",
629
+ "<SPECIAL_624>",
630
+ "<SPECIAL_625>",
631
+ "<SPECIAL_626>",
632
+ "<SPECIAL_627>",
633
+ "<SPECIAL_628>",
634
+ "<SPECIAL_629>",
635
+ "<SPECIAL_630>",
636
+ "<SPECIAL_631>",
637
+ "<SPECIAL_632>",
638
+ "<SPECIAL_633>",
639
+ "<SPECIAL_634>",
640
+ "<SPECIAL_635>",
641
+ "<SPECIAL_636>",
642
+ "<SPECIAL_637>",
643
+ "<SPECIAL_638>",
644
+ "<SPECIAL_639>",
645
+ "<SPECIAL_640>",
646
+ "<SPECIAL_641>",
647
+ "<SPECIAL_642>",
648
+ "<SPECIAL_643>",
649
+ "<SPECIAL_644>",
650
+ "<SPECIAL_645>",
651
+ "<SPECIAL_646>",
652
+ "<SPECIAL_647>",
653
+ "<SPECIAL_648>",
654
+ "<SPECIAL_649>",
655
+ "<SPECIAL_650>",
656
+ "<SPECIAL_651>",
657
+ "<SPECIAL_652>",
658
+ "<SPECIAL_653>",
659
+ "<SPECIAL_654>",
660
+ "<SPECIAL_655>",
661
+ "<SPECIAL_656>",
662
+ "<SPECIAL_657>",
663
+ "<SPECIAL_658>",
664
+ "<SPECIAL_659>",
665
+ "<SPECIAL_660>",
666
+ "<SPECIAL_661>",
667
+ "<SPECIAL_662>",
668
+ "<SPECIAL_663>",
669
+ "<SPECIAL_664>",
670
+ "<SPECIAL_665>",
671
+ "<SPECIAL_666>",
672
+ "<SPECIAL_667>",
673
+ "<SPECIAL_668>",
674
+ "<SPECIAL_669>",
675
+ "<SPECIAL_670>",
676
+ "<SPECIAL_671>",
677
+ "<SPECIAL_672>",
678
+ "<SPECIAL_673>",
679
+ "<SPECIAL_674>",
680
+ "<SPECIAL_675>",
681
+ "<SPECIAL_676>",
682
+ "<SPECIAL_677>",
683
+ "<SPECIAL_678>",
684
+ "<SPECIAL_679>",
685
+ "<SPECIAL_680>",
686
+ "<SPECIAL_681>",
687
+ "<SPECIAL_682>",
688
+ "<SPECIAL_683>",
689
+ "<SPECIAL_684>",
690
+ "<SPECIAL_685>",
691
+ "<SPECIAL_686>",
692
+ "<SPECIAL_687>",
693
+ "<SPECIAL_688>",
694
+ "<SPECIAL_689>",
695
+ "<SPECIAL_690>",
696
+ "<SPECIAL_691>",
697
+ "<SPECIAL_692>",
698
+ "<SPECIAL_693>",
699
+ "<SPECIAL_694>",
700
+ "<SPECIAL_695>",
701
+ "<SPECIAL_696>",
702
+ "<SPECIAL_697>",
703
+ "<SPECIAL_698>",
704
+ "<SPECIAL_699>",
705
+ "<SPECIAL_700>",
706
+ "<SPECIAL_701>",
707
+ "<SPECIAL_702>",
708
+ "<SPECIAL_703>",
709
+ "<SPECIAL_704>",
710
+ "<SPECIAL_705>",
711
+ "<SPECIAL_706>",
712
+ "<SPECIAL_707>",
713
+ "<SPECIAL_708>",
714
+ "<SPECIAL_709>",
715
+ "<SPECIAL_710>",
716
+ "<SPECIAL_711>",
717
+ "<SPECIAL_712>",
718
+ "<SPECIAL_713>",
719
+ "<SPECIAL_714>",
720
+ "<SPECIAL_715>",
721
+ "<SPECIAL_716>",
722
+ "<SPECIAL_717>",
723
+ "<SPECIAL_718>",
724
+ "<SPECIAL_719>",
725
+ "<SPECIAL_720>",
726
+ "<SPECIAL_721>",
727
+ "<SPECIAL_722>",
728
+ "<SPECIAL_723>",
729
+ "<SPECIAL_724>",
730
+ "<SPECIAL_725>",
731
+ "<SPECIAL_726>",
732
+ "<SPECIAL_727>",
733
+ "<SPECIAL_728>",
734
+ "<SPECIAL_729>",
735
+ "<SPECIAL_730>",
736
+ "<SPECIAL_731>",
737
+ "<SPECIAL_732>",
738
+ "<SPECIAL_733>",
739
+ "<SPECIAL_734>",
740
+ "<SPECIAL_735>",
741
+ "<SPECIAL_736>",
742
+ "<SPECIAL_737>",
743
+ "<SPECIAL_738>",
744
+ "<SPECIAL_739>",
745
+ "<SPECIAL_740>",
746
+ "<SPECIAL_741>",
747
+ "<SPECIAL_742>",
748
+ "<SPECIAL_743>",
749
+ "<SPECIAL_744>",
750
+ "<SPECIAL_745>",
751
+ "<SPECIAL_746>",
752
+ "<SPECIAL_747>",
753
+ "<SPECIAL_748>",
754
+ "<SPECIAL_749>",
755
+ "<SPECIAL_750>",
756
+ "<SPECIAL_751>",
757
+ "<SPECIAL_752>",
758
+ "<SPECIAL_753>",
759
+ "<SPECIAL_754>",
760
+ "<SPECIAL_755>",
761
+ "<SPECIAL_756>",
762
+ "<SPECIAL_757>",
763
+ "<SPECIAL_758>",
764
+ "<SPECIAL_759>",
765
+ "<SPECIAL_760>",
766
+ "<SPECIAL_761>",
767
+ "<SPECIAL_762>",
768
+ "<SPECIAL_763>",
769
+ "<SPECIAL_764>",
770
+ "<SPECIAL_765>",
771
+ "<SPECIAL_766>",
772
+ "<SPECIAL_767>",
773
+ "<SPECIAL_768>",
774
+ "<SPECIAL_769>",
775
+ "<SPECIAL_770>",
776
+ "<SPECIAL_771>",
777
+ "<SPECIAL_772>",
778
+ "<SPECIAL_773>",
779
+ "<SPECIAL_774>",
780
+ "<SPECIAL_775>",
781
+ "<SPECIAL_776>",
782
+ "<SPECIAL_777>",
783
+ "<SPECIAL_778>",
784
+ "<SPECIAL_779>",
785
+ "<SPECIAL_780>",
786
+ "<SPECIAL_781>",
787
+ "<SPECIAL_782>",
788
+ "<SPECIAL_783>",
789
+ "<SPECIAL_784>",
790
+ "<SPECIAL_785>",
791
+ "<SPECIAL_786>",
792
+ "<SPECIAL_787>",
793
+ "<SPECIAL_788>",
794
+ "<SPECIAL_789>",
795
+ "<SPECIAL_790>",
796
+ "<SPECIAL_791>",
797
+ "<SPECIAL_792>",
798
+ "<SPECIAL_793>",
799
+ "<SPECIAL_794>",
800
+ "<SPECIAL_795>",
801
+ "<SPECIAL_796>",
802
+ "<SPECIAL_797>",
803
+ "<SPECIAL_798>",
804
+ "<SPECIAL_799>",
805
+ "<SPECIAL_800>",
806
+ "<SPECIAL_801>",
807
+ "<SPECIAL_802>",
808
+ "<SPECIAL_803>",
809
+ "<SPECIAL_804>",
810
+ "<SPECIAL_805>",
811
+ "<SPECIAL_806>",
812
+ "<SPECIAL_807>",
813
+ "<SPECIAL_808>",
814
+ "<SPECIAL_809>",
815
+ "<SPECIAL_810>",
816
+ "<SPECIAL_811>",
817
+ "<SPECIAL_812>",
818
+ "<SPECIAL_813>",
819
+ "<SPECIAL_814>",
820
+ "<SPECIAL_815>",
821
+ "<SPECIAL_816>",
822
+ "<SPECIAL_817>",
823
+ "<SPECIAL_818>",
824
+ "<SPECIAL_819>",
825
+ "<SPECIAL_820>",
826
+ "<SPECIAL_821>",
827
+ "<SPECIAL_822>",
828
+ "<SPECIAL_823>",
829
+ "<SPECIAL_824>",
830
+ "<SPECIAL_825>",
831
+ "<SPECIAL_826>",
832
+ "<SPECIAL_827>",
833
+ "<SPECIAL_828>",
834
+ "<SPECIAL_829>",
835
+ "<SPECIAL_830>",
836
+ "<SPECIAL_831>",
837
+ "<SPECIAL_832>",
838
+ "<SPECIAL_833>",
839
+ "<SPECIAL_834>",
840
+ "<SPECIAL_835>",
841
+ "<SPECIAL_836>",
842
+ "<SPECIAL_837>",
843
+ "<SPECIAL_838>",
844
+ "<SPECIAL_839>",
845
+ "<SPECIAL_840>",
846
+ "<SPECIAL_841>",
847
+ "<SPECIAL_842>",
848
+ "<SPECIAL_843>",
849
+ "<SPECIAL_844>",
850
+ "<SPECIAL_845>",
851
+ "<SPECIAL_846>",
852
+ "<SPECIAL_847>",
853
+ "<SPECIAL_848>",
854
+ "<SPECIAL_849>",
855
+ "<SPECIAL_850>",
856
+ "<SPECIAL_851>",
857
+ "<SPECIAL_852>",
858
+ "<SPECIAL_853>",
859
+ "<SPECIAL_854>",
860
+ "<SPECIAL_855>",
861
+ "<SPECIAL_856>",
862
+ "<SPECIAL_857>",
863
+ "<SPECIAL_858>",
864
+ "<SPECIAL_859>",
865
+ "<SPECIAL_860>",
866
+ "<SPECIAL_861>",
867
+ "<SPECIAL_862>",
868
+ "<SPECIAL_863>",
869
+ "<SPECIAL_864>",
870
+ "<SPECIAL_865>",
871
+ "<SPECIAL_866>",
872
+ "<SPECIAL_867>",
873
+ "<SPECIAL_868>",
874
+ "<SPECIAL_869>",
875
+ "<SPECIAL_870>",
876
+ "<SPECIAL_871>",
877
+ "<SPECIAL_872>",
878
+ "<SPECIAL_873>",
879
+ "<SPECIAL_874>",
880
+ "<SPECIAL_875>",
881
+ "<SPECIAL_876>",
882
+ "<SPECIAL_877>",
883
+ "<SPECIAL_878>",
884
+ "<SPECIAL_879>",
885
+ "<SPECIAL_880>",
886
+ "<SPECIAL_881>",
887
+ "<SPECIAL_882>",
888
+ "<SPECIAL_883>",
889
+ "<SPECIAL_884>",
890
+ "<SPECIAL_885>",
891
+ "<SPECIAL_886>",
892
+ "<SPECIAL_887>",
893
+ "<SPECIAL_888>",
894
+ "<SPECIAL_889>",
895
+ "<SPECIAL_890>",
896
+ "<SPECIAL_891>",
897
+ "<SPECIAL_892>",
898
+ "<SPECIAL_893>",
899
+ "<SPECIAL_894>",
900
+ "<SPECIAL_895>",
901
+ "<SPECIAL_896>",
902
+ "<SPECIAL_897>",
903
+ "<SPECIAL_898>",
904
+ "<SPECIAL_899>",
905
+ "<SPECIAL_900>",
906
+ "<SPECIAL_901>",
907
+ "<SPECIAL_902>",
908
+ "<SPECIAL_903>",
909
+ "<SPECIAL_904>",
910
+ "<SPECIAL_905>",
911
+ "<SPECIAL_906>",
912
+ "<SPECIAL_907>",
913
+ "<SPECIAL_908>",
914
+ "<SPECIAL_909>",
915
+ "<SPECIAL_910>",
916
+ "<SPECIAL_911>",
917
+ "<SPECIAL_912>",
918
+ "<SPECIAL_913>",
919
+ "<SPECIAL_914>",
920
+ "<SPECIAL_915>",
921
+ "<SPECIAL_916>",
922
+ "<SPECIAL_917>",
923
+ "<SPECIAL_918>",
924
+ "<SPECIAL_919>",
925
+ "<SPECIAL_920>",
926
+ "<SPECIAL_921>",
927
+ "<SPECIAL_922>",
928
+ "<SPECIAL_923>",
929
+ "<SPECIAL_924>",
930
+ "<SPECIAL_925>",
931
+ "<SPECIAL_926>",
932
+ "<SPECIAL_927>",
933
+ "<SPECIAL_928>",
934
+ "<SPECIAL_929>",
935
+ "<SPECIAL_930>",
936
+ "<SPECIAL_931>",
937
+ "<SPECIAL_932>",
938
+ "<SPECIAL_933>",
939
+ "<SPECIAL_934>",
940
+ "<SPECIAL_935>",
941
+ "<SPECIAL_936>",
942
+ "<SPECIAL_937>",
943
+ "<SPECIAL_938>",
944
+ "<SPECIAL_939>",
945
+ "<SPECIAL_940>",
946
+ "<SPECIAL_941>",
947
+ "<SPECIAL_942>",
948
+ "<SPECIAL_943>",
949
+ "<SPECIAL_944>",
950
+ "<SPECIAL_945>",
951
+ "<SPECIAL_946>",
952
+ "<SPECIAL_947>",
953
+ "<SPECIAL_948>",
954
+ "<SPECIAL_949>",
955
+ "<SPECIAL_950>",
956
+ "<SPECIAL_951>",
957
+ "<SPECIAL_952>",
958
+ "<SPECIAL_953>",
959
+ "<SPECIAL_954>",
960
+ "<SPECIAL_955>",
961
+ "<SPECIAL_956>",
962
+ "<SPECIAL_957>",
963
+ "<SPECIAL_958>",
964
+ "<SPECIAL_959>",
965
+ "<SPECIAL_960>",
966
+ "<SPECIAL_961>",
967
+ "<SPECIAL_962>",
968
+ "<SPECIAL_963>",
969
+ "<SPECIAL_964>",
970
+ "<SPECIAL_965>",
971
+ "<SPECIAL_966>",
972
+ "<SPECIAL_967>",
973
+ "<SPECIAL_968>",
974
+ "<SPECIAL_969>",
975
+ "<SPECIAL_970>",
976
+ "<SPECIAL_971>",
977
+ "<SPECIAL_972>",
978
+ "<SPECIAL_973>",
979
+ "<SPECIAL_974>",
980
+ "<SPECIAL_975>",
981
+ "<SPECIAL_976>",
982
+ "<SPECIAL_977>",
983
+ "<SPECIAL_978>",
984
+ "<SPECIAL_979>",
985
+ "<SPECIAL_980>",
986
+ "<SPECIAL_981>",
987
+ "<SPECIAL_982>",
988
+ "<SPECIAL_983>",
989
+ "<SPECIAL_984>",
990
+ "<SPECIAL_985>",
991
+ "<SPECIAL_986>",
992
+ "<SPECIAL_987>",
993
+ "<SPECIAL_988>",
994
+ "<SPECIAL_989>",
995
+ "<SPECIAL_990>",
996
+ "<SPECIAL_991>",
997
+ "<SPECIAL_992>",
998
+ "<SPECIAL_993>",
999
+ "<SPECIAL_994>",
1000
+ "<SPECIAL_995>",
1001
+ "<SPECIAL_996>",
1002
+ "<SPECIAL_997>",
1003
+ "<SPECIAL_998>",
1004
+ "<SPECIAL_999>"
1005
+ ],
1006
+ "model_max_length": 1000000000000000019884624838656,
1007
+ "pad_token": "<pad>",
1008
+ "processor_class": "PixtralProcessor",
1009
+ "tokenizer_class": "TokenizersBackend"
1010
+ }