lurker18 commited on
Commit
c591056
·
verified ·
1 Parent(s): 71ec859

Upload 13 files

Browse files
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<image>": 32000
3
+ }
chat_template.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "chat_template": "{% for message in messages %}{% if message['role'] != 'system' %}{{ message['role'].upper() + ': '}}{% endif %}{# Render all images first #}{% for content in message['content'] | selectattr('type', 'equalto', 'image') %}{{ '<image>\n' }}{% endfor %}{# Render all text next #}{% if message['role'] != 'assistant' %}{% for content in message['content'] | selectattr('type', 'equalto', 'text') %}{{ content['text'] + ' '}}{% endfor %}{% else %}{% for content in message['content'] | selectattr('type', 'equalto', 'text') %}{% generation %}{{ content['text'] + ' '}}{% endgeneration %}{% endfor %}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ 'ASSISTANT:' }}{% endif %}"
3
+ }
config.json ADDED
@@ -0,0 +1,77 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/mnt/nvme01/huggingface/models/Llava-HF/llava-v1.6-vicuna-13b-hf",
3
+ "architectures": [
4
+ "LlavaNextForConditionalGeneration"
5
+ ],
6
+ "ignore_index": -100,
7
+ "image_grid_pinpoints": [
8
+ [
9
+ 336,
10
+ 672
11
+ ],
12
+ [
13
+ 672,
14
+ 336
15
+ ],
16
+ [
17
+ 672,
18
+ 672
19
+ ],
20
+ [
21
+ 1008,
22
+ 336
23
+ ],
24
+ [
25
+ 336,
26
+ 1008
27
+ ]
28
+ ],
29
+ "image_seq_length": 576,
30
+ "image_token_index": 32000,
31
+ "model_type": "llava_next",
32
+ "projector_hidden_act": "gelu",
33
+ "quantization_config": {
34
+ "bits": 4,
35
+ "group_size": 128,
36
+ "modules_to_not_convert": null,
37
+ "quant_method": "awq",
38
+ "version": "gemm",
39
+ "zero_point": true
40
+ },
41
+ "text_config": {
42
+ "_name_or_path": "lmsys/vicuna-13b-v1.5",
43
+ "architectures": [
44
+ "LlamaForCausalLM"
45
+ ],
46
+ "hidden_size": 5120,
47
+ "intermediate_size": 13824,
48
+ "max_length": 4096,
49
+ "max_position_embeddings": 4096,
50
+ "model_type": "llama",
51
+ "num_attention_heads": 40,
52
+ "num_hidden_layers": 40,
53
+ "num_key_value_heads": 40,
54
+ "pad_token_id": 0,
55
+ "rms_norm_eps": 1e-05,
56
+ "torch_dtype": "float16",
57
+ "vocab_size": 32064
58
+ },
59
+ "tie_word_embeddings": false,
60
+ "torch_dtype": "float16",
61
+ "transformers_version": "4.45.2",
62
+ "use_image_newline_parameter": true,
63
+ "vision_config": {
64
+ "hidden_size": 1024,
65
+ "image_size": 336,
66
+ "intermediate_size": 4096,
67
+ "model_type": "clip_vision_model",
68
+ "num_attention_heads": 16,
69
+ "num_hidden_layers": 24,
70
+ "patch_size": 14,
71
+ "projection_dim": 768,
72
+ "vocab_size": 32000
73
+ },
74
+ "vision_feature_layer": -2,
75
+ "vision_feature_select_strategy": "default",
76
+ "vocab_size": 32064
77
+ }
generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "do_sample": true,
5
+ "eos_token_id": 2,
6
+ "max_length": 4096,
7
+ "pad_token_id": 0,
8
+ "transformers_version": "4.45.2"
9
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea9684d45849ded8fd11cb03e7eab503799cd6cbea5d173651536b1755d052c1
3
+ size 4994786744
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f2c3b29d9294041912278d7b741a9b2578e1da017d0732b3096fce8708d0a1a
3
+ size 2924539288
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
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
+ }
processor_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "image_token": "<image>",
3
+ "patch_size": 14,
4
+ "processor_class": "LlavaNextProcessor",
5
+ "vision_feature_select_strategy": "default"
6
+ }
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": "<unk>",
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 sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": true,
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
+ },
39
+ "bos_token": "<s>",
40
+ "clean_up_tokenization_spaces": false,
41
+ "eos_token": "</s>",
42
+ "extra_special_tokens": {
43
+ "image_token": "<image>"
44
+ },
45
+ "image_token": "<image>",
46
+ "legacy": false,
47
+ "model_max_length": 4096,
48
+ "pad_token": "<unk>",
49
+ "padding_side": "right",
50
+ "processor_class": "LlavaNextProcessor",
51
+ "sp_model_kwargs": {},
52
+ "spaces_between_special_tokens": false,
53
+ "tokenizer_class": "LlamaTokenizer",
54
+ "unk_token": "<unk>",
55
+ "use_default_system_prompt": false
56
+ }