Hugging Face's logo

OPEA
/
llava-v1.5-7b-int4-sym-inc

Safetensors
llava_llama
4-bit precision
intel/auto-round
Model card Files Community
weiweiz1 commited on
Commit
3d08a1c
·
1 Parent(s): 9683dcf

convert lfs json files

Browse files
Files changed (6) hide show
  1. .gitattributes +0 -6
  2. config.json +105 -3
  3. generation_config.json +7 -3
  4. quantization_config.json +59 -3
  5. special_tokens_map.json +30 -3
  6. tokenizer_config.json +43 -3
.gitattributes CHANGED
@@ -33,9 +33,3 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
- tokenizer_config.json filter=lfs diff=lfs merge=lfs -text
37
- config.json filter=lfs diff=lfs merge=lfs -text
38
- generation_config.json filter=lfs diff=lfs merge=lfs -text
39
- quantize_config.json filter=lfs diff=lfs merge=lfs -text
40
- special_tokens_map.json filter=lfs diff=lfs merge=lfs -text
41
- quantization_config.json filter=lfs diff=lfs merge=lfs -text
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
config.json CHANGED
@@ -1,3 +1,105 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:bbe0517125c66fa20887dfc7d599b7dc0fc96acbc0d9f6752f7fb833e47d6c51
3
- size 2807
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/models//llava-v1.5-7b",
3
+ "architectures": [
4
+ "LlavaLlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
+ "freeze_mm_mlp_adapter": false,
11
+ "freeze_mm_vision_resampler": false,
12
+ "hidden_act": "silu",
13
+ "hidden_size": 4096,
14
+ "image_aspect_ratio": "pad",
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 11008,
17
+ "max_length": 4096,
18
+ "max_position_embeddings": 4096,
19
+ "mlp_bias": false,
20
+ "mm_hidden_size": 1024,
21
+ "mm_projector_type": "mlp2x_gelu",
22
+ "mm_resampler_type": null,
23
+ "mm_use_im_patch_token": false,
24
+ "mm_use_im_start_end": false,
25
+ "mm_vision_select_feature": "patch",
26
+ "mm_vision_select_layer": -2,
27
+ "mm_vision_tower": "openai/clip-vit-large-patch14-336",
28
+ "model_type": "llava_llama",
29
+ "num_attention_heads": 32,
30
+ "num_hidden_layers": 32,
31
+ "num_key_value_heads": 32,
32
+ "pad_token_id": 0,
33
+ "pretraining_tp": 1,
34
+ "quantization_config": {
35
+ "amp": true,
36
+ "autoround_version": "0.4.0.dev",
37
+ "backend": "auto_round:gptq:exllamav2",
38
+ "batch_size": 1,
39
+ "bits": 4,
40
+ "data_type": "int",
41
+ "dataset": "liuhaotian/llava_conv_58k",
42
+ "enable_minmax_tuning": true,
43
+ "enable_norm_bias_tuning": false,
44
+ "enable_quanted_input": true,
45
+ "gradient_accumulate_steps": 4,
46
+ "group_size": 128,
47
+ "iters": 1000,
48
+ "low_gpu_mem_usage": false,
49
+ "lr": 0.001,
50
+ "minmax_lr": 0.001,
51
+ "nsamples": 512,
52
+ "quant_method": "intel/auto-round",
53
+ "scale_dtype": "torch.float16",
54
+ "seqlen": 512,
55
+ "sym": true,
56
+ "to_quant_block_names": [
57
+ [
58
+ "model.layers.0",
59
+ "model.layers.1",
60
+ "model.layers.2",
61
+ "model.layers.3",
62
+ "model.layers.4",
63
+ "model.layers.5",
64
+ "model.layers.6",
65
+ "model.layers.7",
66
+ "model.layers.8",
67
+ "model.layers.9",
68
+ "model.layers.10",
69
+ "model.layers.11",
70
+ "model.layers.12",
71
+ "model.layers.13",
72
+ "model.layers.14",
73
+ "model.layers.15",
74
+ "model.layers.16",
75
+ "model.layers.17",
76
+ "model.layers.18",
77
+ "model.layers.19",
78
+ "model.layers.20",
79
+ "model.layers.21",
80
+ "model.layers.22",
81
+ "model.layers.23",
82
+ "model.layers.24",
83
+ "model.layers.25",
84
+ "model.layers.26",
85
+ "model.layers.27",
86
+ "model.layers.28",
87
+ "model.layers.29",
88
+ "model.layers.30",
89
+ "model.layers.31"
90
+ ]
91
+ ]
92
+ },
93
+ "rms_norm_eps": 1e-05,
94
+ "rope_scaling": null,
95
+ "rope_theta": 10000.0,
96
+ "tie_word_embeddings": false,
97
+ "torch_dtype": "float16",
98
+ "transformers_version": "4.44.1",
99
+ "tune_mm_mlp_adapter": false,
100
+ "tune_mm_vision_resampler": false,
101
+ "unfreeze_mm_vision_tower": false,
102
+ "use_cache": true,
103
+ "use_mm_proj": true,
104
+ "vocab_size": 32000
105
+ }
generation_config.json CHANGED
@@ -1,3 +1,7 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:e2cd8d5eeb0db609b05bea501ab215d3c9280558f6538dc5c7e283e5fad62f63
3
- size 124
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 1,
3
+ "eos_token_id": 2,
4
+ "max_length": 4096,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.44.1"
7
+ }
quantization_config.json CHANGED
@@ -1,3 +1,59 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:1440501220e7a3e3bfec2216990a9645cd669af51309c6aa609332154daea73f
3
- size 1387
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bits": 4,
3
+ "group_size": 128,
4
+ "sym": true,
5
+ "data_type": "int",
6
+ "enable_quanted_input": true,
7
+ "enable_minmax_tuning": true,
8
+ "seqlen": 512,
9
+ "batch_size": 1,
10
+ "scale_dtype": "torch.float16",
11
+ "lr": 0.001,
12
+ "minmax_lr": 0.001,
13
+ "gradient_accumulate_steps": 4,
14
+ "iters": 1000,
15
+ "amp": true,
16
+ "nsamples": 512,
17
+ "low_gpu_mem_usage": false,
18
+ "to_quant_block_names": [
19
+ [
20
+ "model.layers.0",
21
+ "model.layers.1",
22
+ "model.layers.2",
23
+ "model.layers.3",
24
+ "model.layers.4",
25
+ "model.layers.5",
26
+ "model.layers.6",
27
+ "model.layers.7",
28
+ "model.layers.8",
29
+ "model.layers.9",
30
+ "model.layers.10",
31
+ "model.layers.11",
32
+ "model.layers.12",
33
+ "model.layers.13",
34
+ "model.layers.14",
35
+ "model.layers.15",
36
+ "model.layers.16",
37
+ "model.layers.17",
38
+ "model.layers.18",
39
+ "model.layers.19",
40
+ "model.layers.20",
41
+ "model.layers.21",
42
+ "model.layers.22",
43
+ "model.layers.23",
44
+ "model.layers.24",
45
+ "model.layers.25",
46
+ "model.layers.26",
47
+ "model.layers.27",
48
+ "model.layers.28",
49
+ "model.layers.29",
50
+ "model.layers.30",
51
+ "model.layers.31"
52
+ ]
53
+ ],
54
+ "enable_norm_bias_tuning": false,
55
+ "dataset": "liuhaotian/llava_conv_58k",
56
+ "autoround_version": "0.4.0.dev",
57
+ "quant_method": "intel/auto-round",
58
+ "backend": "auto_round:gptq:exllamav2"
59
+ }
special_tokens_map.json CHANGED
@@ -1,3 +1,30 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:4859e5dbde90e059988a0a2136d8df3f2773d4d2fc4c4543690028f0b2166e7f
3
- size 552
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_config.json CHANGED
@@ -1,3 +1,43 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:aac5eb0917505d23bdfcd63f0623aa39308b0f9ccc8766520015a41ad25f1ede
3
- size 964
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ },
31
+ "bos_token": "<s>",
32
+ "clean_up_tokenization_spaces": false,
33
+ "eos_token": "</s>",
34
+ "legacy": false,
35
+ "model_max_length": 2048,
36
+ "pad_token": "<unk>",
37
+ "padding_side": "right",
38
+ "sp_model_kwargs": {},
39
+ "spaces_between_special_tokens": false,
40
+ "tokenizer_class": "LlamaTokenizer",
41
+ "unk_token": "<unk>",
42
+ "use_default_system_prompt": false
43
+ }