Hugging Face's logo

Queenarya
/
First-model

Safetensors
qwen2_vl
4-bit precision
bitsandbytes
Model card Files
xet
 Community
Queenarya commited on
Commit
dace4b2
·
verified ·
1 Parent(s): 3de09ac

Upload config.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. config.json +108 -0
config.json ADDED
@@ -0,0 +1,108 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2VLForConditionalGeneration"
4
+ ],
5
+ "dtype": "bfloat16",
6
+ "image_token_id": 151655,
7
+ "model_type": "qwen2_vl",
8
+ "quantization_config": {
9
+ "_load_in_4bit": true,
10
+ "_load_in_8bit": false,
11
+ "bnb_4bit_compute_dtype": "bfloat16",
12
+ "bnb_4bit_quant_storage": "uint8",
13
+ "bnb_4bit_quant_type": "nf4",
14
+ "bnb_4bit_use_double_quant": true,
15
+ "llm_int8_enable_fp32_cpu_offload": false,
16
+ "llm_int8_has_fp16_weight": false,
17
+ "llm_int8_skip_modules": null,
18
+ "llm_int8_threshold": 6.0,
19
+ "load_in_4bit": true,
20
+ "load_in_8bit": false,
21
+ "quant_method": "bitsandbytes"
22
+ },
23
+ "text_config": {
24
+ "attention_dropout": 0.0,
25
+ "bos_token_id": 151643,
26
+ "dtype": "bfloat16",
27
+ "eos_token_id": 151645,
28
+ "hidden_act": "silu",
29
+ "hidden_size": 3584,
30
+ "initializer_range": 0.02,
31
+ "intermediate_size": 18944,
32
+ "layer_types": [
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention",
42
+ "full_attention",
43
+ "full_attention",
44
+ "full_attention",
45
+ "full_attention",
46
+ "full_attention",
47
+ "full_attention",
48
+ "full_attention",
49
+ "full_attention",
50
+ "full_attention",
51
+ "full_attention",
52
+ "full_attention",
53
+ "full_attention",
54
+ "full_attention",
55
+ "full_attention",
56
+ "full_attention",
57
+ "full_attention",
58
+ "full_attention",
59
+ "full_attention",
60
+ "full_attention"
61
+ ],
62
+ "max_position_embeddings": 32768,
63
+ "max_window_layers": 28,
64
+ "model_type": "qwen2_vl_text",
65
+ "num_attention_heads": 28,
66
+ "num_hidden_layers": 28,
67
+ "num_key_value_heads": 4,
68
+ "pad_token_id": 151654,
69
+ "rms_norm_eps": 1e-06,
70
+ "rope_parameters": {
71
+ "mrope_section": [
72
+ 16,
73
+ 24,
74
+ 24
75
+ ],
76
+ "rope_theta": 1000000.0,
77
+ "rope_type": "default",
78
+ "type": "default"
79
+ },
80
+ "sliding_window": null,
81
+ "use_cache": true,
82
+ "use_sliding_window": false,
83
+ "vocab_size": 152064
84
+ },
85
+ "tie_word_embeddings": false,
86
+ "transformers_version": "5.5.1",
87
+ "unsloth_fixed": true,
88
+ "video_token_id": 151656,
89
+ "vision_config": {
90
+ "depth": 32,
91
+ "embed_dim": 1280,
92
+ "hidden_act": "quick_gelu",
93
+ "hidden_size": 3584,
94
+ "in_channels": 3,
95
+ "in_chans": 3,
96
+ "initializer_range": 0.02,
97
+ "mlp_ratio": 4,
98
+ "model_type": "qwen2_vl",
99
+ "num_heads": 16,
100
+ "patch_size": 14,
101
+ "spatial_merge_size": 2,
102
+ "spatial_patch_size": 14,
103
+ "temporal_patch_size": 2
104
+ },
105
+ "vision_end_token_id": 151653,
106
+ "vision_start_token_id": 151652,
107
+ "vision_token_id": 151654
108
+ }