Hugging Face's logo

chitb
/
portrayer_6k_dev

Safetensors
llava_qwen
Model card Files Community
chitb commited on
Commit
f888656
·
verified ·
1 Parent(s): ff399c8

Upload folder using huggingface_hub

Browse files
Files changed (9) hide show
  1. added_tokens.json +6 -0
  2. config.json +209 -0
  3. generation_config.json +14 -0
  4. merges.txt +0 -0
  5. model.safetensors +3 -0
  6. special_tokens_map.json +20 -0
  7. tokenizer.json +0 -0
  8. tokenizer_config.json +53 -0
  9. vocab.json +0 -0
added_tokens.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "<image>": 151646,
3
+ "<|endoftext|>": 151643,
4
+ "<|im_end|>": 151645,
5
+ "<|im_start|>": 151644
6
+ }
config.json ADDED
@@ -0,0 +1,209 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "../checkpoint_spp/llava-onevision-qwen2-0.5b-si",
3
+ "add_faster_video": false,
4
+ "add_time_instruction": false,
5
+ "architectures": [
6
+ "LlavaQwenForCausalLM"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "bos_token_id": 151643,
10
+ "eos_token_id": 151645,
11
+ "faster_token_stride": 10,
12
+ "force_sample": false,
13
+ "freeze_mm_mlp_adapter": false,
14
+ "hidden_act": "silu",
15
+ "hidden_size": 896,
16
+ "image_aspect_ratio": "anyres_max_9",
17
+ "image_crop_resolution": null,
18
+ "image_grid_pinpoints": [
19
+ [
20
+ 384,
21
+ 384
22
+ ],
23
+ [
24
+ 384,
25
+ 768
26
+ ],
27
+ [
28
+ 384,
29
+ 1152
30
+ ],
31
+ [
32
+ 384,
33
+ 1536
34
+ ],
35
+ [
36
+ 384,
37
+ 1920
38
+ ],
39
+ [
40
+ 384,
41
+ 2304
42
+ ],
43
+ [
44
+ 768,
45
+ 384
46
+ ],
47
+ [
48
+ 768,
49
+ 768
50
+ ],
51
+ [
52
+ 768,
53
+ 1152
54
+ ],
55
+ [
56
+ 768,
57
+ 1536
58
+ ],
59
+ [
60
+ 768,
61
+ 1920
62
+ ],
63
+ [
64
+ 768,
65
+ 2304
66
+ ],
67
+ [
68
+ 1152,
69
+ 384
70
+ ],
71
+ [
72
+ 1152,
73
+ 768
74
+ ],
75
+ [
76
+ 1152,
77
+ 1152
78
+ ],
79
+ [
80
+ 1152,
81
+ 1536
82
+ ],
83
+ [
84
+ 1152,
85
+ 1920
86
+ ],
87
+ [
88
+ 1152,
89
+ 2304
90
+ ],
91
+ [
92
+ 1536,
93
+ 384
94
+ ],
95
+ [
96
+ 1536,
97
+ 768
98
+ ],
99
+ [
100
+ 1536,
101
+ 1152
102
+ ],
103
+ [
104
+ 1536,
105
+ 1536
106
+ ],
107
+ [
108
+ 1536,
109
+ 1920
110
+ ],
111
+ [
112
+ 1536,
113
+ 2304
114
+ ],
115
+ [
116
+ 1920,
117
+ 384
118
+ ],
119
+ [
120
+ 1920,
121
+ 768
122
+ ],
123
+ [
124
+ 1920,
125
+ 1152
126
+ ],
127
+ [
128
+ 1920,
129
+ 1536
130
+ ],
131
+ [
132
+ 1920,
133
+ 1920
134
+ ],
135
+ [
136
+ 1920,
137
+ 2304
138
+ ],
139
+ [
140
+ 2304,
141
+ 384
142
+ ],
143
+ [
144
+ 2304,
145
+ 768
146
+ ],
147
+ [
148
+ 2304,
149
+ 1152
150
+ ],
151
+ [
152
+ 2304,
153
+ 1536
154
+ ],
155
+ [
156
+ 2304,
157
+ 1920
158
+ ],
159
+ [
160
+ 2304,
161
+ 2304
162
+ ]
163
+ ],
164
+ "image_split_resolution": null,
165
+ "image_token_index": 151646,
166
+ "initializer_range": 0.02,
167
+ "intermediate_size": 4864,
168
+ "max_position_embeddings": 32768,
169
+ "max_window_layers": 24,
170
+ "mm_hidden_size": 1152,
171
+ "mm_newline_position": "grid",
172
+ "mm_patch_merge_type": "spatial_unpad",
173
+ "mm_projector_lr": 1e-05,
174
+ "mm_projector_type": "mlp2x_gelu",
175
+ "mm_resampler_type": null,
176
+ "mm_spatial_pool_mode": "bilinear",
177
+ "mm_spatial_pool_stride": null,
178
+ "mm_tunable_parts": "mm_vision_tower,mm_mlp_adapter,mm_language_model",
179
+ "mm_use_im_patch_token": false,
180
+ "mm_use_im_start_end": false,
181
+ "mm_vision_select_feature": "patch",
182
+ "mm_vision_select_layer": -2,
183
+ "mm_vision_tower": "../checkpoint_spp/siglip-so400m-patch14-384/",
184
+ "mm_vision_tower_lr": 2e-06,
185
+ "model_type": "llava_qwen",
186
+ "num_attention_heads": 14,
187
+ "num_hidden_layers": 24,
188
+ "num_key_value_heads": 2,
189
+ "pos_skipping_range": 4096,
190
+ "rms_norm_eps": 1e-06,
191
+ "rope_scaling": null,
192
+ "rope_theta": 1000000.0,
193
+ "sliding_window": null,
194
+ "tie_word_embeddings": true,
195
+ "tokenizer_model_max_length": 8192,
196
+ "tokenizer_padding_side": "right",
197
+ "torch_dtype": "float16",
198
+ "transformers_version": "4.43.0",
199
+ "tune_mm_mlp_adapter": false,
200
+ "unfreeze_vision_tower": false,
201
+ "use_cache": true,
202
+ "use_mm_proj": true,
203
+ "use_pos_skipping": false,
204
+ "use_resampler": false,
205
+ "use_s2": false,
206
+ "use_sliding_window": false,
207
+ "vision_tower_pretrained": "",
208
+ "vocab_size": 151647
209
+ }
generation_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "repetition_penalty": 1.1,
10
+ "temperature": 0.7,
11
+ "top_k": 20,
12
+ "top_p": 0.8,
13
+ "transformers_version": "4.43.0"
14
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:751bb13d1eb90121821eb44908def03eb5581d6d27ae0296bc2db64ed6003944
3
+ size 1786816728
special_tokens_map.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>"
5
+ ],
6
+ "eos_token": {
7
+ "content": "<|im_end|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "pad_token": {
14
+ "content": "<|endoftext|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ }
20
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "151643": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "151644": {
13
+ "content": "<|im_start|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "151645": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "151646": {
29
+ "content": "<image>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ }
36
+ },
37
+ "additional_special_tokens": [
38
+ "<|im_start|>",
39
+ "<|im_end|>"
40
+ ],
41
+ "bos_token": null,
42
+ "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
43
+ "clean_up_tokenization_spaces": false,
44
+ "eos_token": "<|im_end|>",
45
+ "errors": "replace",
46
+ "model_max_length": 32768,
47
+ "pad_token": "<|endoftext|>",
48
+ "padding_side": "right",
49
+ "processor_class": "LlavaProcessor",
50
+ "split_special_tokens": false,
51
+ "tokenizer_class": "Qwen2Tokenizer",
52
+ "unk_token": null
53
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff