Hugging Face's logo

krishnateja95
/
Deepseek-VL2-Tiny-4bit-AWQ

Safetensors
deepseek_vl_v2
4-bit precision
intel/auto-round
Model card Files
xet
Community
1
krishnateja95 commited on
Commit
5775d04
·
verified ·
1 Parent(s): cd5975c

Tokenizer and Quant config

Browse files
Files changed (5) hide show
  1. processor_config.json +116 -0
  2. quantization_config.json +24 -0
  3. special_tokens_map.json +39 -0
  4. tokenizer.json +0 -0
  5. tokenizer_config.json +0 -0
processor_config.json ADDED
@@ -0,0 +1,116 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_special_token": false,
3
+ "candidate_resolutions": [
4
+ [
5
+ 384,
6
+ 384
7
+ ],
8
+ [
9
+ 384,
10
+ 768
11
+ ],
12
+ [
13
+ 768,
14
+ 384
15
+ ],
16
+ [
17
+ 384,
18
+ 1152
19
+ ],
20
+ [
21
+ 1152,
22
+ 384
23
+ ],
24
+ [
25
+ 384,
26
+ 1536
27
+ ],
28
+ [
29
+ 1536,
30
+ 384
31
+ ],
32
+ [
33
+ 768,
34
+ 768
35
+ ],
36
+ [
37
+ 384,
38
+ 1920
39
+ ],
40
+ [
41
+ 1920,
42
+ 384
43
+ ],
44
+ [
45
+ 384,
46
+ 2304
47
+ ],
48
+ [
49
+ 2304,
50
+ 384
51
+ ],
52
+ [
53
+ 768,
54
+ 1152
55
+ ],
56
+ [
57
+ 1152,
58
+ 768
59
+ ],
60
+ [
61
+ 384,
62
+ 2688
63
+ ],
64
+ [
65
+ 2688,
66
+ 384
67
+ ],
68
+ [
69
+ 384,
70
+ 3072
71
+ ],
72
+ [
73
+ 3072,
74
+ 384
75
+ ],
76
+ [
77
+ 768,
78
+ 1536
79
+ ],
80
+ [
81
+ 1536,
82
+ 768
83
+ ],
84
+ [
85
+ 384,
86
+ 3456
87
+ ],
88
+ [
89
+ 3456,
90
+ 384
91
+ ],
92
+ [
93
+ 1152,
94
+ 1152
95
+ ]
96
+ ],
97
+ "downsample_ratio": 2,
98
+ "ignore_id": -100,
99
+ "image_mean": [
100
+ 0.5,
101
+ 0.5,
102
+ 0.5
103
+ ],
104
+ "image_std": [
105
+ 0.5,
106
+ 0.5,
107
+ 0.5
108
+ ],
109
+ "image_token": "<image>",
110
+ "mask_prompt": false,
111
+ "normalize": true,
112
+ "pad_token": "<\uff5c\u2581pad\u2581\uff5c>",
113
+ "patch_size": 14,
114
+ "processor_class": "DeepseekVLV2Processor",
115
+ "sft_format": "deepseek"
116
+ }
quantization_config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bits": 4,
3
+ "group_size": 64,
4
+ "sym": true,
5
+ "data_type": "int",
6
+ "enable_quanted_input": true,
7
+ "enable_minmax_tuning": true,
8
+ "seqlen": 2048,
9
+ "batch_size": 8,
10
+ "scale_dtype": "torch.float16",
11
+ "lr": 0.5,
12
+ "minmax_lr": 0.5,
13
+ "gradient_accumulate_steps": 1,
14
+ "iters": 2,
15
+ "amp": true,
16
+ "nsamples": 8,
17
+ "low_gpu_mem_usage": false,
18
+ "to_quant_block_names": "language.model.layers",
19
+ "enable_norm_bias_tuning": false,
20
+ "dataset": "NeelNanda/pile-10k",
21
+ "autoround_version": "0.4.6",
22
+ "quant_method": "intel/auto-round",
23
+ "backend": "auto_round:gptq:exllamav2"
24
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<|User|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "<|Assistant|>",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ }
17
+ ],
18
+ "bos_token": {
19
+ "content": "<｜begin▁of▁sentence｜>",
20
+ "lstrip": false,
21
+ "normalized": false,
22
+ "rstrip": false,
23
+ "single_word": false
24
+ },
25
+ "eos_token": {
26
+ "content": "<｜end▁of▁sentence｜>",
27
+ "lstrip": false,
28
+ "normalized": false,
29
+ "rstrip": false,
30
+ "single_word": false
31
+ },
32
+ "pad_token": {
33
+ "content": "<｜▁pad▁｜>",
34
+ "lstrip": false,
35
+ "normalized": false,
36
+ "rstrip": false,
37
+ "single_word": false
38
+ }
39
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff