Upload folder using huggingface_hub

#1
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<image>": 32000
3
+ }
config.json ADDED
@@ -0,0 +1,78 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "llava-hf/llava-v1.6-vicuna-7b-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_token_index": 32000,
30
+ "model_type": "llava_next",
31
+ "projector_hidden_act": "gelu",
32
+ "quantization_config": {
33
+ "_load_in_4bit": true,
34
+ "_load_in_8bit": false,
35
+ "bnb_4bit_compute_dtype": "bfloat16",
36
+ "bnb_4bit_quant_storage": "uint8",
37
+ "bnb_4bit_quant_type": "fp4",
38
+ "bnb_4bit_use_double_quant": true,
39
+ "llm_int8_enable_fp32_cpu_offload": false,
40
+ "llm_int8_has_fp16_weight": false,
41
+ "llm_int8_skip_modules": [
42
+ "lm_head"
43
+ ],
44
+ "llm_int8_threshold": 6.0,
45
+ "load_in_4bit": true,
46
+ "load_in_8bit": false,
47
+ "quant_method": "bitsandbytes"
48
+ },
49
+ "text_config": {
50
+ "_name_or_path": "lmsys/vicuna-7b-v1.5",
51
+ "architectures": [
52
+ "LlamaForCausalLM"
53
+ ],
54
+ "max_position_embeddings": 4096,
55
+ "model_type": "llama",
56
+ "pad_token_id": 0,
57
+ "rms_norm_eps": 1e-05,
58
+ "torch_dtype": "float16",
59
+ "vocab_size": 32064
60
+ },
61
+ "torch_dtype": "bfloat16",
62
+ "transformers_version": "4.39.2",
63
+ "use_image_newline_parameter": true,
64
+ "vision_config": {
65
+ "hidden_size": 1024,
66
+ "image_size": 336,
67
+ "intermediate_size": 4096,
68
+ "model_type": "clip_vision_model",
69
+ "num_attention_heads": 16,
70
+ "num_hidden_layers": 24,
71
+ "patch_size": 14,
72
+ "projection_dim": 768,
73
+ "vocab_size": 32000
74
+ },
75
+ "vision_feature_layer": -2,
76
+ "vision_feature_select_strategy": "default",
77
+ "vocab_size": 32064
78
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.39.2"
7
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d85d72e307cd18a5049174063b32b252053b0c0d4c9a21b120d3a9323b442335
3
+ size 4037122735
preprocessor_config.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_rescale": true,
11
+ "do_resize": true,
12
+ "image_grid_pinpoints": [
13
+ [
14
+ 336,
15
+ 672
16
+ ],
17
+ [
18
+ 672,
19
+ 336
20
+ ],
21
+ [
22
+ 672,
23
+ 672
24
+ ],
25
+ [
26
+ 1008,
27
+ 336
28
+ ],
29
+ [
30
+ 336,
31
+ 1008
32
+ ]
33
+ ],
34
+ "image_mean": [
35
+ 0.48145466,
36
+ 0.4578275,
37
+ 0.40821073
38
+ ],
39
+ "image_processor_type": "LlavaNextImageProcessor",
40
+ "image_std": [
41
+ 0.26862954,
42
+ 0.26130258,
43
+ 0.27577711
44
+ ],
45
+ "processor_class": "LlavaNextProcessor",
46
+ "resample": 3,
47
+ "rescale_factor": 0.00392156862745098,
48
+ "size": {
49
+ "shortest_edge": 336
50
+ }
51
+ }
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 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "legacy": false,
43
+ "model_max_length": 4096,
44
+ "pad_token": "<unk>",
45
+ "padding_side": "right",
46
+ "processor_class": "LlavaNextProcessor",
47
+ "sp_model_kwargs": {},
48
+ "spaces_between_special_tokens": false,
49
+ "tokenizer_class": "LlamaTokenizer",
50
+ "unk_token": "<unk>",
51
+ "use_default_system_prompt": false
52
+ }