Hugging Face's logo

looppayments
/
llava-7b-adapters

Image-Text-to-Text
Transformers
TensorBoard
Safetensors
llava_next
conversational
text-generation-inference
Inference Endpoints
Model card Files Metrics Community
evanrichards commited on
Commit
3855a7d
•
1 Parent(s): 7326db8

Training in progress, step 50

Browse files
Files changed (12) hide show
  1. adapter_config.json +254 -0
  2. adapter_model.safetensors +3 -0
  3. added_tokens.json +4 -0
  4. chat_template.json +3 -0
  5. preprocessor_config.json +52 -0
  6. runs/Aug16_17-40-29_0e88b13d5842/events.out.tfevents.1723830034.0e88b13d5842.2184.0 +3 -0
  7. runs/Aug16_17-41-35_0e88b13d5842/events.out.tfevents.1723830100.0e88b13d5842.2184.1 +3 -0
  8. special_tokens_map.json +30 -0
  9. tokenizer.json +0 -0
  10. tokenizer.model +3 -0
  11. tokenizer_config.json +65 -0
  12. training_args.bin +3 -0
adapter_config.json ADDED
@@ -0,0 +1,254 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": {
4
+ "base_model_class": "LlavaNextForConditionalGeneration",
5
+ "parent_library": "transformers.models.llava_next.modeling_llava_next"
6
+ },
7
+ "base_model_name_or_path": "llava-hf/llava-v1.6-mistral-7b-hf",
8
+ "bias": "none",
9
+ "fan_in_fan_out": false,
10
+ "inference_mode": true,
11
+ "init_lora_weights": "gaussian",
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 128,
17
+ "lora_dropout": 0.1,
18
+ "megatron_config": null,
19
+ "megatron_core": "megatron.core",
20
+ "modules_to_save": null,
21
+ "peft_type": "LORA",
22
+ "r": 64,
23
+ "rank_pattern": {},
24
+ "revision": null,
25
+ "target_modules": [
26
+ "language_model.model.layers.24.self_attn.k_proj",
27
+ "language_model.model.layers.13.self_attn.o_proj",
28
+ "language_model.model.layers.11.mlp.gate_proj",
29
+ "language_model.model.layers.30.self_attn.v_proj",
30
+ "language_model.model.layers.9.self_attn.o_proj",
31
+ "language_model.model.layers.1.mlp.gate_proj",
32
+ "language_model.model.layers.25.mlp.up_proj",
33
+ "language_model.model.layers.19.self_attn.v_proj",
34
+ "language_model.model.layers.31.mlp.up_proj",
35
+ "language_model.model.layers.12.self_attn.v_proj",
36
+ "language_model.model.layers.15.mlp.down_proj",
37
+ "language_model.model.layers.20.self_attn.k_proj",
38
+ "language_model.model.layers.18.self_attn.k_proj",
39
+ "language_model.model.layers.4.mlp.up_proj",
40
+ "language_model.model.layers.27.self_attn.v_proj",
41
+ "language_model.model.layers.7.self_attn.k_proj",
42
+ "language_model.model.layers.9.self_attn.k_proj",
43
+ "language_model.model.layers.31.self_attn.v_proj",
44
+ "language_model.model.layers.22.mlp.down_proj",
45
+ "language_model.model.layers.19.self_attn.k_proj",
46
+ "language_model.model.layers.4.self_attn.v_proj",
47
+ "language_model.model.layers.20.self_attn.v_proj",
48
+ "language_model.model.layers.2.self_attn.k_proj",
49
+ "language_model.model.layers.17.mlp.up_proj",
50
+ "language_model.model.layers.25.mlp.down_proj",
51
+ "language_model.model.layers.13.self_attn.v_proj",
52
+ "language_model.model.layers.24.self_attn.o_proj",
53
+ "language_model.model.layers.8.self_attn.v_proj",
54
+ "language_model.model.layers.3.self_attn.k_proj",
55
+ "language_model.model.layers.19.mlp.up_proj",
56
+ "language_model.model.layers.0.self_attn.q_proj",
57
+ "language_model.model.layers.8.self_attn.o_proj",
58
+ "language_model.model.layers.11.self_attn.k_proj",
59
+ "language_model.model.layers.20.mlp.down_proj",
60
+ "language_model.model.layers.4.self_attn.k_proj",
61
+ "language_model.model.layers.22.self_attn.v_proj",
62
+ "language_model.model.layers.18.self_attn.q_proj",
63
+ "language_model.model.layers.24.self_attn.v_proj",
64
+ "language_model.model.layers.29.mlp.up_proj",
65
+ "language_model.model.layers.15.mlp.up_proj",
66
+ "language_model.model.layers.18.self_attn.v_proj",
67
+ "language_model.model.layers.3.mlp.up_proj",
68
+ "language_model.model.layers.15.mlp.gate_proj",
69
+ "language_model.model.layers.21.mlp.up_proj",
70
+ "language_model.model.layers.26.self_attn.q_proj",
71
+ "language_model.model.layers.26.self_attn.v_proj",
72
+ "language_model.model.layers.5.self_attn.o_proj",
73
+ "language_model.model.layers.25.self_attn.k_proj",
74
+ "language_model.model.layers.5.self_attn.q_proj",
75
+ "language_model.model.layers.27.self_attn.k_proj",
76
+ "language_model.model.layers.29.mlp.gate_proj",
77
+ "language_model.model.layers.27.mlp.down_proj",
78
+ "language_model.model.layers.29.self_attn.v_proj",
79
+ "language_model.model.layers.14.mlp.gate_proj",
80
+ "language_model.model.layers.20.mlp.up_proj",
81
+ "language_model.model.layers.20.self_attn.q_proj",
82
+ "language_model.model.layers.14.self_attn.v_proj",
83
+ "language_model.model.layers.18.mlp.gate_proj",
84
+ "language_model.model.layers.21.self_attn.q_proj",
85
+ "language_model.model.layers.7.mlp.up_proj",
86
+ "language_model.model.layers.10.mlp.down_proj",
87
+ "language_model.model.layers.23.mlp.gate_proj",
88
+ "language_model.model.layers.2.mlp.up_proj",
89
+ "language_model.model.layers.24.mlp.up_proj",
90
+ "language_model.model.layers.2.self_attn.v_proj",
91
+ "language_model.model.layers.10.self_attn.k_proj",
92
+ "language_model.model.layers.8.self_attn.q_proj",
93
+ "language_model.model.layers.11.self_attn.v_proj",
94
+ "language_model.model.layers.22.mlp.up_proj",
95
+ "language_model.model.layers.29.self_attn.q_proj",
96
+ "language_model.model.layers.3.self_attn.q_proj",
97
+ "language_model.model.layers.17.self_attn.v_proj",
98
+ "language_model.model.layers.1.mlp.down_proj",
99
+ "language_model.model.layers.4.mlp.gate_proj",
100
+ "language_model.model.layers.12.self_attn.k_proj",
101
+ "language_model.model.layers.30.self_attn.q_proj",
102
+ "language_model.model.layers.12.self_attn.o_proj",
103
+ "language_model.model.layers.4.mlp.down_proj",
104
+ "language_model.model.layers.7.self_attn.o_proj",
105
+ "language_model.model.layers.29.self_attn.o_proj",
106
+ "language_model.model.layers.13.self_attn.q_proj",
107
+ "language_model.model.layers.10.self_attn.q_proj",
108
+ "language_model.model.layers.26.mlp.down_proj",
109
+ "language_model.model.layers.17.mlp.gate_proj",
110
+ "language_model.model.layers.28.self_attn.k_proj",
111
+ "language_model.model.layers.28.mlp.up_proj",
112
+ "language_model.model.layers.6.mlp.down_proj",
113
+ "language_model.model.layers.3.self_attn.o_proj",
114
+ "language_model.model.layers.6.self_attn.k_proj",
115
+ "language_model.model.layers.19.self_attn.q_proj",
116
+ "language_model.model.layers.0.mlp.down_proj",
117
+ "language_model.model.layers.9.mlp.gate_proj",
118
+ "language_model.model.layers.14.self_attn.q_proj",
119
+ "language_model.model.layers.30.mlp.up_proj",
120
+ "language_model.model.layers.31.self_attn.q_proj",
121
+ "language_model.model.layers.31.mlp.down_proj",
122
+ "language_model.model.layers.12.mlp.gate_proj",
123
+ "language_model.model.layers.0.self_attn.k_proj",
124
+ "language_model.model.layers.1.self_attn.k_proj",
125
+ "language_model.model.layers.1.self_attn.o_proj",
126
+ "language_model.model.layers.14.self_attn.k_proj",
127
+ "language_model.model.layers.5.self_attn.v_proj",
128
+ "language_model.model.layers.11.self_attn.o_proj",
129
+ "language_model.model.layers.21.self_attn.o_proj",
130
+ "language_model.model.layers.16.mlp.up_proj",
131
+ "language_model.model.layers.7.self_attn.v_proj",
132
+ "language_model.model.layers.10.self_attn.v_proj",
133
+ "language_model.model.layers.6.mlp.gate_proj",
134
+ "language_model.model.layers.16.self_attn.q_proj",
135
+ "language_model.model.layers.19.mlp.gate_proj",
136
+ "language_model.model.layers.26.mlp.up_proj",
137
+ "language_model.model.layers.23.self_attn.q_proj",
138
+ "language_model.model.layers.30.mlp.gate_proj",
139
+ "language_model.model.layers.11.mlp.up_proj",
140
+ "language_model.model.layers.14.self_attn.o_proj",
141
+ "language_model.model.layers.25.self_attn.v_proj",
142
+ "language_model.model.layers.24.self_attn.q_proj",
143
+ "language_model.model.layers.0.mlp.up_proj",
144
+ "language_model.model.layers.0.self_attn.o_proj",
145
+ "language_model.model.layers.16.self_attn.v_proj",
146
+ "language_model.model.layers.0.self_attn.v_proj",
147
+ "language_model.model.layers.28.self_attn.v_proj",
148
+ "language_model.model.layers.13.mlp.gate_proj",
149
+ "language_model.model.layers.27.self_attn.o_proj",
150
+ "language_model.model.layers.29.mlp.down_proj",
151
+ "language_model.model.layers.17.self_attn.o_proj",
152
+ "language_model.model.layers.17.mlp.down_proj",
153
+ "language_model.model.layers.18.mlp.up_proj",
154
+ "language_model.model.layers.3.mlp.down_proj",
155
+ "language_model.model.layers.16.mlp.gate_proj",
156
+ "language_model.model.layers.17.self_attn.q_proj",
157
+ "language_model.model.layers.6.self_attn.v_proj",
158
+ "language_model.model.layers.2.self_attn.o_proj",
159
+ "language_model.model.layers.9.mlp.up_proj",
160
+ "language_model.model.layers.16.mlp.down_proj",
161
+ "language_model.model.layers.25.mlp.gate_proj",
162
+ "language_model.model.layers.19.self_attn.o_proj",
163
+ "language_model.model.layers.3.self_attn.v_proj",
164
+ "language_model.model.layers.1.mlp.up_proj",
165
+ "language_model.model.layers.28.self_attn.q_proj",
166
+ "language_model.model.layers.15.self_attn.k_proj",
167
+ "language_model.model.layers.0.mlp.gate_proj",
168
+ "language_model.model.layers.20.mlp.gate_proj",
169
+ "language_model.model.layers.5.self_attn.k_proj",
170
+ "language_model.model.layers.9.self_attn.q_proj",
171
+ "language_model.model.layers.10.self_attn.o_proj",
172
+ "language_model.model.layers.17.self_attn.k_proj",
173
+ "language_model.model.layers.23.mlp.down_proj",
174
+ "language_model.model.layers.27.self_attn.q_proj",
175
+ "language_model.model.layers.30.self_attn.k_proj",
176
+ "language_model.model.layers.15.self_attn.q_proj",
177
+ "language_model.model.layers.9.self_attn.v_proj",
178
+ "language_model.model.layers.22.self_attn.q_proj",
179
+ "language_model.model.layers.11.mlp.down_proj",
180
+ "language_model.model.layers.18.mlp.down_proj",
181
+ "language_model.model.layers.9.mlp.down_proj",
182
+ "language_model.model.layers.24.mlp.down_proj",
183
+ "language_model.model.layers.27.mlp.gate_proj",
184
+ "language_model.model.layers.29.self_attn.k_proj",
185
+ "language_model.model.layers.13.mlp.down_proj",
186
+ "language_model.model.layers.2.self_attn.q_proj",
187
+ "language_model.model.layers.13.mlp.up_proj",
188
+ "language_model.model.layers.28.mlp.down_proj",
189
+ "language_model.model.layers.2.mlp.gate_proj",
190
+ "language_model.model.layers.15.self_attn.v_proj",
191
+ "language_model.model.layers.30.self_attn.o_proj",
192
+ "language_model.model.layers.7.mlp.down_proj",
193
+ "language_model.model.layers.30.mlp.down_proj",
194
+ "language_model.model.layers.10.mlp.gate_proj",
195
+ "language_model.model.layers.6.self_attn.q_proj",
196
+ "language_model.model.layers.5.mlp.gate_proj",
197
+ "language_model.model.layers.12.mlp.up_proj",
198
+ "language_model.model.layers.18.self_attn.o_proj",
199
+ "language_model.model.layers.21.self_attn.k_proj",
200
+ "language_model.model.layers.16.self_attn.k_proj",
201
+ "language_model.model.layers.22.mlp.gate_proj",
202
+ "language_model.model.layers.7.self_attn.q_proj",
203
+ "language_model.model.layers.23.self_attn.k_proj",
204
+ "language_model.model.layers.23.self_attn.v_proj",
205
+ "language_model.model.layers.24.mlp.gate_proj",
206
+ "language_model.model.layers.22.self_attn.k_proj",
207
+ "language_model.model.layers.22.self_attn.o_proj",
208
+ "language_model.model.layers.25.self_attn.q_proj",
209
+ "language_model.model.layers.8.mlp.up_proj",
210
+ "language_model.model.layers.28.self_attn.o_proj",
211
+ "language_model.model.layers.1.self_attn.q_proj",
212
+ "language_model.model.layers.5.mlp.up_proj",
213
+ "language_model.model.layers.2.mlp.down_proj",
214
+ "language_model.model.layers.31.self_attn.k_proj",
215
+ "language_model.model.layers.21.self_attn.v_proj",
216
+ "language_model.model.layers.7.mlp.gate_proj",
217
+ "language_model.model.layers.28.mlp.gate_proj",
218
+ "language_model.model.layers.14.mlp.up_proj",
219
+ "language_model.model.layers.15.self_attn.o_proj",
220
+ "language_model.model.layers.23.self_attn.o_proj",
221
+ "language_model.model.layers.26.mlp.gate_proj",
222
+ "language_model.model.layers.26.self_attn.o_proj",
223
+ "language_model.model.layers.8.mlp.gate_proj",
224
+ "language_model.model.layers.4.self_attn.o_proj",
225
+ "language_model.model.layers.21.mlp.gate_proj",
226
+ "language_model.model.layers.14.mlp.down_proj",
227
+ "language_model.model.layers.1.self_attn.v_proj",
228
+ "language_model.model.layers.6.self_attn.o_proj",
229
+ "language_model.model.layers.11.self_attn.q_proj",
230
+ "language_model.model.layers.26.self_attn.k_proj",
231
+ "language_model.model.layers.3.mlp.gate_proj",
232
+ "language_model.model.layers.12.self_attn.q_proj",
233
+ "language_model.model.layers.8.mlp.down_proj",
234
+ "language_model.model.layers.31.self_attn.o_proj",
235
+ "language_model.model.layers.20.self_attn.o_proj",
236
+ "language_model.model.layers.4.self_attn.q_proj",
237
+ "language_model.model.layers.8.self_attn.k_proj",
238
+ "language_model.model.layers.31.mlp.gate_proj",
239
+ "language_model.model.layers.23.mlp.up_proj",
240
+ "language_model.model.layers.19.mlp.down_proj",
241
+ "language_model.model.layers.27.mlp.up_proj",
242
+ "language_model.model.layers.21.mlp.down_proj",
243
+ "language_model.model.layers.13.self_attn.k_proj",
244
+ "language_model.model.layers.5.mlp.down_proj",
245
+ "language_model.model.layers.12.mlp.down_proj",
246
+ "language_model.model.layers.16.self_attn.o_proj",
247
+ "language_model.model.layers.25.self_attn.o_proj",
248
+ "language_model.model.layers.6.mlp.up_proj",
249
+ "language_model.model.layers.10.mlp.up_proj"
250
+ ],
251
+ "task_type": null,
252
+ "use_dora": false,
253
+ "use_rslora": false
254
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19b1fb0b9633c175e29aaad59a249b18d9ddbfa3eff0249c36f61abb4e689f6d
3
+ size 671155888
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "<image>": 32000,
3
+ "<pad>": 32001
4
+ }
chat_template.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "chat_template": "{% for message in messages %}{% if message['role'] == 'user' %}{{ '[INST] ' }}{# Render all images first #}{% for content in message['content'] | selectattr('type', 'equalto', 'image') %}{{ '<image>\n' }}{% endfor %}{# Render all text next #}{% for content in message['content'] | selectattr('type', 'equalto', 'text') %}{{ content['text'] }}{% endfor %}{{' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' ' + message['content'][0]['text'] + '<\\s> '}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}"
3
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "aspect_ratio_setting": "anyres",
3
+ "crop_size": {
4
+ "height": 336,
5
+ "width": 336
6
+ },
7
+ "do_center_crop": true,
8
+ "do_convert_rgb": true,
9
+ "do_normalize": true,
10
+ "do_pad": true,
11
+ "do_rescale": true,
12
+ "do_resize": true,
13
+ "image_grid_pinpoints": [
14
+ [
15
+ 336,
16
+ 672
17
+ ],
18
+ [
19
+ 672,
20
+ 336
21
+ ],
22
+ [
23
+ 672,
24
+ 672
25
+ ],
26
+ [
27
+ 1008,
28
+ 336
29
+ ],
30
+ [
31
+ 336,
32
+ 1008
33
+ ]
34
+ ],
35
+ "image_mean": [
36
+ 0.48145466,
37
+ 0.4578275,
38
+ 0.40821073
39
+ ],
40
+ "image_processor_type": "LlavaNextImageProcessor",
41
+ "image_std": [
42
+ 0.26862954,
43
+ 0.26130258,
44
+ 0.27577711
45
+ ],
46
+ "processor_class": "LlavaNextProcessor",
47
+ "resample": 3,
48
+ "rescale_factor": 0.00392156862745098,
49
+ "size": {
50
+ "shortest_edge": 336
51
+ }
52
+ }
runs/Aug16_17-40-29_0e88b13d5842/events.out.tfevents.1723830034.0e88b13d5842.2184.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5638dd752e0c7bb00b841031612b46a0743b29a300d57c92f0fff23dc830fd2
3
+ size 6143
runs/Aug16_17-41-35_0e88b13d5842/events.out.tfevents.1723830100.0e88b13d5842.2184.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58e783807f95ef61d4e961ad6f30a31435aeea3e1db7d9ca332caa7f2b99b045
3
+ size 6407
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
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
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
tokenizer_config.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ },
30
+ "32000": {
31
+ "content": "<image>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "32001": {
39
+ "content": "<pad>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": true
45
+ }
46
+ },
47
+ "additional_special_tokens": [],
48
+ "bos_token": "<s>",
49
+ "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
50
+ "clean_up_tokenization_spaces": false,
51
+ "eos_token": "</s>",
52
+ "legacy": true,
53
+ "max_length": null,
54
+ "model_max_length": 1000000000000000019884624838656,
55
+ "pad_to_multiple_of": null,
56
+ "pad_token": "<pad>",
57
+ "pad_token_type_id": 0,
58
+ "padding_side": "right",
59
+ "processor_class": "LlavaNextProcessor",
60
+ "sp_model_kwargs": {},
61
+ "spaces_between_special_tokens": false,
62
+ "tokenizer_class": "LlamaTokenizer",
63
+ "unk_token": "<unk>",
64
+ "use_default_system_prompt": false
65
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae673b3d3e98c8e758204c9af6d4d269cc45fb48b319b18cf2328697f130f9d4
3
+ size 5176