Hugging Face's logo

ifarhat1993
/
pruned_falcon_vlm_0.25_15_awq

Safetensors
llava_next
4-bit precision
awq
Model card Files Community
ifarhat1993 commited on
Commit
5c409b4
•
1 Parent(s): 4ab0b2f

Upload folder using huggingface_hub

Browse files
Files changed (9) hide show
  1. config.json +98 -0
  2. generation_config.json +9 -0
  3. model-00001-of-00002.safetensors +3 -0
  4. model-00002-of-00002.safetensors +3 -0
  5. model.safetensors.index.json +0 -0
  6. preprocessor_config.json +52 -0
  7. special_tokens_map.json +36 -0
  8. tokenizer.json +0 -0
  9. tokenizer_config.json +135 -0
config.json ADDED
@@ -0,0 +1,98 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "pruned_models/pruned_falcon_vlm_0.25_15_pruned",
3
+ "architectures": [
4
+ "LlavaNextForConditionalGeneration"
5
+ ],
6
+ "hidden_size": 4096,
7
+ "ignore_index": -100,
8
+ "image_grid_pinpoints": [
9
+ [
10
+ 336,
11
+ 672
12
+ ],
13
+ [
14
+ 672,
15
+ 336
16
+ ],
17
+ [
18
+ 672,
19
+ 672
20
+ ],
21
+ [
22
+ 1008,
23
+ 336
24
+ ],
25
+ [
26
+ 336,
27
+ 1008
28
+ ]
29
+ ],
30
+ "image_token_index": 65024,
31
+ "model_type": "llava_next",
32
+ "pad_token_id": 0,
33
+ "projector_hidden_act": "gelu",
34
+ "quantization_config": {
35
+ "bits": 4,
36
+ "group_size": 128,
37
+ "modules_to_not_convert": null,
38
+ "quant_method": "awq",
39
+ "version": "gemm",
40
+ "zero_point": true
41
+ },
42
+ "text_config": {
43
+ "_name_or_path": "tiiuae/falcon-11B-vlm",
44
+ "activation": "gelu",
45
+ "alibi": false,
46
+ "architectures": [
47
+ "FalconForCausalLM"
48
+ ],
49
+ "auto_map": {
50
+ "AutoConfig": "configuration_falcon.FalconConfig",
51
+ "AutoModel": "modeling_falcon.FalconModel",
52
+ "AutoModelForCausalLM": "modeling_falcon.FalconForCausalLM",
53
+ "AutoModelForQuestionAnswering": "modeling_falcon.FalconForQuestionAnswering",
54
+ "AutoModelForSequenceClassification": "modeling_falcon.FalconForSequenceClassification",
55
+ "AutoModelForTokenClassification": "modeling_falcon.FalconForTokenClassification"
56
+ },
57
+ "bias": false,
58
+ "bos_token_id": 11,
59
+ "eos_token_id": 11,
60
+ "ff_factor": 4,
61
+ "ffn_hidden_size": 12288,
62
+ "hidden_dropout": 0.0,
63
+ "hidden_size": 4096,
64
+ "layer_norm_epsilon": 1e-05,
65
+ "max_length": 4096,
66
+ "max_position_embeddings": 8192,
67
+ "model_type": "falcon",
68
+ "multi_query": true,
69
+ "new_decoder_architecture": true,
70
+ "num_attention_heads": 32,
71
+ "num_hidden_layers": 45,
72
+ "num_kv_heads": 8,
73
+ "num_ln_in_parallel_attn": 1,
74
+ "parallel_attn": true,
75
+ "rope_theta": 500042.0,
76
+ "tie_word_embeddings": false,
77
+ "torch_dtype": "bfloat16",
78
+ "vocab_size": 65024
79
+ },
80
+ "tie_word_embeddings": false,
81
+ "torch_dtype": "float16",
82
+ "transformers_version": "4.42.0",
83
+ "use_image_newline_parameter": true,
84
+ "vision_config": {
85
+ "hidden_size": 1024,
86
+ "image_size": 336,
87
+ "intermediate_size": 4096,
88
+ "model_type": "clip_vision_model",
89
+ "num_attention_heads": 16,
90
+ "num_hidden_layers": 24,
91
+ "patch_size": 14,
92
+ "projection_dim": 768,
93
+ "vocab_size": 32000
94
+ },
95
+ "vision_feature_layer": -2,
96
+ "vision_feature_select_strategy": "default",
97
+ "vocab_size": 65024
98
+ }
generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 11,
4
+ "do_sample": true,
5
+ "eos_token_id": 11,
6
+ "max_length": 4096,
7
+ "pad_token_id": 0,
8
+ "transformers_version": "4.42.0"
9
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9779aa5c993883c465ca048b519d35f8939329b2442fca63679c9834405df0a1
3
+ size 4516532200
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0812a8effb07bd7f9780d4927672071d4293404a4597369ff8489ca921761ff4
3
+ size 532676752
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
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ ">>TITLE<<",
4
+ ">>ABSTRACT<<",
5
+ ">>INTRODUCTION<<",
6
+ ">>SUMMARY<<",
7
+ ">>COMMENT<<",
8
+ ">>ANSWER<<",
9
+ ">>QUESTION<<",
10
+ ">>DOMAIN<<",
11
+ ">>PREFIX<<",
12
+ ">>SUFFIX<<",
13
+ ">>MIDDLE<<"
14
+ ],
15
+ "bos_token": {
16
+ "content": ">>",
17
+ "lstrip": false,
18
+ "normalized": false,
19
+ "rstrip": false,
20
+ "single_word": false
21
+ },
22
+ "eos_token": {
23
+ "content": "<|endoftext|>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false
28
+ },
29
+ "pad_token": {
30
+ "content": "<|endoftext|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false
35
+ }
36
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,135 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": ">>TITLE<<",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": ">>ABSTRACT<<",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": ">>INTRODUCTION<<",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": ">>SUMMARY<<",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "4": {
37
+ "content": ">>COMMENT<<",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "5": {
45
+ "content": ">>ANSWER<<",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "6": {
53
+ "content": ">>QUESTION<<",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "7": {
61
+ "content": ">>DOMAIN<<",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "8": {
69
+ "content": ">>PREFIX<<",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "9": {
77
+ "content": ">>SUFFIX<<",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "10": {
85
+ "content": ">>MIDDLE<<",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "11": {
93
+ "content": "<|endoftext|>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "500": {
101
+ "content": ">>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ }
108
+ },
109
+ "additional_special_tokens": [
110
+ ">>TITLE<<",
111
+ ">>ABSTRACT<<",
112
+ ">>INTRODUCTION<<",
113
+ ">>SUMMARY<<",
114
+ ">>COMMENT<<",
115
+ ">>ANSWER<<",
116
+ ">>QUESTION<<",
117
+ ">>DOMAIN<<",
118
+ ">>PREFIX<<",
119
+ ">>SUFFIX<<",
120
+ ">>MIDDLE<<"
121
+ ],
122
+ "bos_token": ">>",
123
+ "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ 'User: \n' + message['content'] }}\n{% elif message['role'] == 'system' %}\n{{ 'System: ' + message['content'] }}\n{% elif message['role'] == 'assistant' %}\n{{ 'Falcon:\n' + message['content']}}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ 'Falcon:' }}\n{% endif %}\n{% endfor %}",
124
+ "clean_up_tokenization_spaces": true,
125
+ "device_map": "cuda:2",
126
+ "eos_token": "<|endoftext|>",
127
+ "model_input_names": [
128
+ "input_ids",
129
+ "attention_mask"
130
+ ],
131
+ "model_max_length": 1000000000000000019884624838656,
132
+ "pad_token": "<|endoftext|>",
133
+ "padding_side": "left",
134
+ "tokenizer_class": "PreTrainedTokenizerFast"
135
+ }