Wajdii98 commited on
Commit
b824b5d
·
verified ·
1 Parent(s): 0aa53b1

Upload folder using huggingface_hub

Browse files
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "<image>": 32000,
3
+ "<pad>": 32001
4
+ }
chat_template.jinja ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ {% for message in messages %}{% if message['role'] == 'user' %}{{ '[INST] ' }}{# Render all images first #}{% for content in message['content'] | selectattr('type', 'equalto', 'image') %}{{ '<image>
2
+ ' }}{% 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 %}
config.json ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlavaForConditionalGeneration"
4
+ ],
5
+ "ignore_index": -100,
6
+ "image_seq_length": 576,
7
+ "image_token_index": 32000,
8
+ "model_type": "llava",
9
+ "multimodal_projector_bias": true,
10
+ "pad_token_id": 32001,
11
+ "projector_hidden_act": "gelu",
12
+ "quantization_config": {
13
+ "_load_in_4bit": true,
14
+ "_load_in_8bit": false,
15
+ "bnb_4bit_compute_dtype": "float16",
16
+ "bnb_4bit_quant_storage": "uint8",
17
+ "bnb_4bit_quant_type": "nf4",
18
+ "bnb_4bit_use_double_quant": true,
19
+ "llm_int8_enable_fp32_cpu_offload": false,
20
+ "llm_int8_has_fp16_weight": false,
21
+ "llm_int8_skip_modules": null,
22
+ "llm_int8_threshold": 6.0,
23
+ "load_in_4bit": true,
24
+ "load_in_8bit": false,
25
+ "quant_method": "bitsandbytes"
26
+ },
27
+ "text_config": {
28
+ "_name_or_path": "mistralai/Mistral-7B-v0.1",
29
+ "architectures": [
30
+ "MistralForCausalLM"
31
+ ],
32
+ "attention_dropout": 0.0,
33
+ "head_dim": null,
34
+ "hidden_act": "silu",
35
+ "hidden_size": 4096,
36
+ "initializer_range": 0.02,
37
+ "intermediate_size": 14336,
38
+ "max_position_embeddings": 32768,
39
+ "model_type": "mistral",
40
+ "num_attention_heads": 32,
41
+ "num_hidden_layers": 32,
42
+ "num_key_value_heads": 8,
43
+ "rms_norm_eps": 1e-05,
44
+ "rope_theta": 10000.0,
45
+ "sliding_window": 4096,
46
+ "torch_dtype": "float16",
47
+ "use_cache": true,
48
+ "vocab_size": 32064
49
+ },
50
+ "torch_dtype": "float16",
51
+ "transformers_version": "4.52.0.dev0",
52
+ "vision_config": {
53
+ "attention_dropout": 0.0,
54
+ "hidden_act": "quick_gelu",
55
+ "hidden_size": 1024,
56
+ "image_size": 336,
57
+ "initializer_factor": 1.0,
58
+ "initializer_range": 0.02,
59
+ "intermediate_size": 4096,
60
+ "layer_norm_eps": 1e-05,
61
+ "model_type": "clip_vision_model",
62
+ "num_attention_heads": 16,
63
+ "num_channels": 3,
64
+ "num_hidden_layers": 24,
65
+ "patch_size": 14,
66
+ "projection_dim": 768,
67
+ "torch_dtype": "float16",
68
+ "vocab_size": 32000
69
+ },
70
+ "vision_feature_layer": -2,
71
+ "vision_feature_select_strategy": "default",
72
+ "vocab_size": 32064
73
+ }
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": 32001,
6
+ "transformers_version": "4.52.0.dev0"
7
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b044ad395d3072d171ebed09c27345d126210237686f7c014205674d28da32e5
3
+ size 4296759289
preprocessor_config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": {
3
+ "height": 336,
4
+ "width": 336
5
+ },
6
+ "do_center_crop": true,
7
+ "do_convert_rgb": true,
8
+ "do_normalize": true,
9
+ "do_rescale": true,
10
+ "do_resize": true,
11
+ "image_mean": [
12
+ 0.48145466,
13
+ 0.4578275,
14
+ 0.40821073
15
+ ],
16
+ "image_processor_type": "CLIPImageProcessor",
17
+ "image_std": [
18
+ 0.26862954,
19
+ 0.26130258,
20
+ 0.27577711
21
+ ],
22
+ "processor_class": "LlavaProcessor",
23
+ "resample": 3,
24
+ "rescale_factor": 0.00392156862745098,
25
+ "size": {
26
+ "shortest_edge": 336
27
+ }
28
+ }
processor_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "image_token": "<image>",
3
+ "num_additional_image_tokens": 1,
4
+ "patch_size": 14,
5
+ "processor_class": "LlavaProcessor",
6
+ "vision_feature_select_strategy": "default"
7
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "image_token": "<image>",
17
+ "pad_token": {
18
+ "content": "<pad>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "unk_token": {
25
+ "content": "<unk>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
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 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "clean_up_tokenization_spaces": false,
50
+ "eos_token": "</s>",
51
+ "extra_special_tokens": {
52
+ "image_token": "<image>"
53
+ },
54
+ "image_token": "<image>",
55
+ "legacy": true,
56
+ "model_max_length": 1000000000000000019884624838656,
57
+ "pad_token": "<pad>",
58
+ "padding_side": "left",
59
+ "processor_class": "LlavaProcessor",
60
+ "sp_model_kwargs": {},
61
+ "spaces_between_special_tokens": false,
62
+ "tokenizer_class": "LlamaTokenizer",
63
+ "trust_remote_code": false,
64
+ "unk_token": "<unk>",
65
+ "use_default_system_prompt": true
66
+ }