ashishscapsitech123 commited on
Commit
6dfc4ee
·
verified ·
1 Parent(s): 527f054

Upload model trained with Unsloth

Browse files

Upload model trained with Unsloth 2x faster

config.json ADDED
@@ -0,0 +1,160 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2VLForConditionalGeneration"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 151643,
7
+ "eos_token_id": 151645,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 3584,
10
+ "image_token_id": 151655,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 18944,
13
+ "max_position_embeddings": 32768,
14
+ "max_window_layers": 28,
15
+ "model_type": "qwen2_vl",
16
+ "num_attention_heads": 28,
17
+ "num_hidden_layers": 28,
18
+ "num_key_value_heads": 4,
19
+ "pad_token_id": 151654,
20
+ "quantization_config": {
21
+ "bnb_4bit_compute_dtype": "bfloat16",
22
+ "bnb_4bit_quant_type": "nf4",
23
+ "bnb_4bit_use_double_quant": true,
24
+ "llm_int8_enable_fp32_cpu_offload": false,
25
+ "llm_int8_has_fp16_weight": false,
26
+ "llm_int8_skip_modules": null,
27
+ "llm_int8_threshold": 6.0,
28
+ "load_in_4bit": true,
29
+ "load_in_8bit": false,
30
+ "quant_method": "bitsandbytes"
31
+ },
32
+ "rms_norm_eps": 1e-06,
33
+ "rope_scaling": {
34
+ "mrope_section": [
35
+ 16,
36
+ 24,
37
+ 24
38
+ ],
39
+ "rope_type": "default",
40
+ "type": "default"
41
+ },
42
+ "rope_theta": 1000000.0,
43
+ "sliding_window": 32768,
44
+ "text_config": {
45
+ "_name_or_path": "Qwen/Qwen2-VL-7B-Instruct",
46
+ "architectures": [
47
+ "Qwen2VLForConditionalGeneration"
48
+ ],
49
+ "attention_dropout": 0.0,
50
+ "bos_token_id": 151643,
51
+ "eos_token_id": 151645,
52
+ "hidden_act": "silu",
53
+ "hidden_size": 3584,
54
+ "image_token_id": null,
55
+ "initializer_range": 0.02,
56
+ "intermediate_size": 18944,
57
+ "layer_types": [
58
+ "full_attention",
59
+ "full_attention",
60
+ "full_attention",
61
+ "full_attention",
62
+ "full_attention",
63
+ "full_attention",
64
+ "full_attention",
65
+ "full_attention",
66
+ "full_attention",
67
+ "full_attention",
68
+ "full_attention",
69
+ "full_attention",
70
+ "full_attention",
71
+ "full_attention",
72
+ "full_attention",
73
+ "full_attention",
74
+ "full_attention",
75
+ "full_attention",
76
+ "full_attention",
77
+ "full_attention",
78
+ "full_attention",
79
+ "full_attention",
80
+ "full_attention",
81
+ "full_attention",
82
+ "full_attention",
83
+ "full_attention",
84
+ "full_attention",
85
+ "full_attention"
86
+ ],
87
+ "max_position_embeddings": 32768,
88
+ "max_window_layers": 28,
89
+ "model_type": "qwen2_vl_text",
90
+ "num_attention_heads": 28,
91
+ "num_hidden_layers": 28,
92
+ "num_key_value_heads": 4,
93
+ "pad_token_id": 151654,
94
+ "quantization_config": {
95
+ "_load_in_4bit": true,
96
+ "_load_in_8bit": false,
97
+ "bnb_4bit_compute_dtype": "bfloat16",
98
+ "bnb_4bit_quant_storage": "uint8",
99
+ "bnb_4bit_quant_type": "nf4",
100
+ "bnb_4bit_use_double_quant": true,
101
+ "llm_int8_enable_fp32_cpu_offload": false,
102
+ "llm_int8_has_fp16_weight": false,
103
+ "llm_int8_skip_modules": null,
104
+ "llm_int8_threshold": 6.0,
105
+ "load_in_4bit": true,
106
+ "load_in_8bit": false,
107
+ "quant_method": "bitsandbytes"
108
+ },
109
+ "rms_norm_eps": 1e-06,
110
+ "rope_scaling": {
111
+ "mrope_section": [
112
+ 16,
113
+ 24,
114
+ 24
115
+ ],
116
+ "rope_type": "default",
117
+ "type": "default"
118
+ },
119
+ "rope_theta": 1000000.0,
120
+ "sliding_window": null,
121
+ "torch_dtype": "bfloat16",
122
+ "unsloth_fixed": true,
123
+ "use_cache": true,
124
+ "use_sliding_window": false,
125
+ "video_token_id": null,
126
+ "vision_end_token_id": 151653,
127
+ "vision_start_token_id": 151652,
128
+ "vision_token_id": 151654,
129
+ "vocab_size": 152064
130
+ },
131
+ "tie_word_embeddings": false,
132
+ "torch_dtype": "bfloat16",
133
+ "transformers_version": "4.54.1",
134
+ "unsloth_fixed": true,
135
+ "unsloth_version": "2025.8.1",
136
+ "use_cache": true,
137
+ "use_sliding_window": false,
138
+ "video_token_id": 151656,
139
+ "vision_config": {
140
+ "depth": 32,
141
+ "embed_dim": 1280,
142
+ "hidden_act": "quick_gelu",
143
+ "hidden_size": 3584,
144
+ "in_channels": 3,
145
+ "in_chans": 3,
146
+ "initializer_range": 0.02,
147
+ "mlp_ratio": 4,
148
+ "model_type": "qwen2_vl",
149
+ "num_heads": 16,
150
+ "patch_size": 14,
151
+ "spatial_merge_size": 2,
152
+ "spatial_patch_size": 14,
153
+ "temporal_patch_size": 2,
154
+ "torch_dtype": "bfloat16"
155
+ },
156
+ "vision_end_token_id": 151653,
157
+ "vision_start_token_id": 151652,
158
+ "vision_token_id": 151654,
159
+ "vocab_size": 152064
160
+ }
generation_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "max_length": 32768,
9
+ "pad_token_id": 151654,
10
+ "temperature": 0.01,
11
+ "top_k": 1,
12
+ "top_p": 0.001,
13
+ "transformers_version": "4.54.1"
14
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abeac626dc9c725bdb5b1235e3d4a4f9a36cbcd1cbfd09c06f38e3aa537b02fd
3
+ size 4809183606
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e76ec4dc2e7c0dcbe3432e58fae08e62204a2ef2323069d85c8fa0affb87332a
3
+ size 1089994880
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff