saurav1111 commited on
Commit
4e5ffc8
·
verified ·
1 Parent(s): a233316

Upload model trained with Unsloth

Browse files

Upload model trained with Unsloth 2x faster

README.md CHANGED
@@ -6,6 +6,7 @@ tags:
6
  - unsloth
7
  - qwen2_5_vl
8
  - trl
 
9
  license: apache-2.0
10
  language:
11
  - en
 
6
  - unsloth
7
  - qwen2_5_vl
8
  - trl
9
+ - sft
10
  license: apache-2.0
11
  language:
12
  - en
config.json ADDED
@@ -0,0 +1,149 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2_5_VLForConditionalGeneration"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "dtype": "float16",
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_5_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": "float16",
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
+ "architectures": [
46
+ "Qwen2_5_VLForConditionalGeneration"
47
+ ],
48
+ "attention_dropout": 0.0,
49
+ "bos_token_id": 151643,
50
+ "dtype": "float16",
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": 128000,
88
+ "max_window_layers": 28,
89
+ "model_type": "qwen2_5_vl_text",
90
+ "num_attention_heads": 28,
91
+ "num_hidden_layers": 28,
92
+ "num_key_value_heads": 4,
93
+ "rms_norm_eps": 1e-06,
94
+ "rope_scaling": {
95
+ "mrope_section": [
96
+ 16,
97
+ 24,
98
+ 24
99
+ ],
100
+ "rope_type": "default",
101
+ "type": "default"
102
+ },
103
+ "rope_theta": 1000000.0,
104
+ "sliding_window": null,
105
+ "use_cache": true,
106
+ "use_sliding_window": false,
107
+ "video_token_id": null,
108
+ "vision_end_token_id": 151653,
109
+ "vision_start_token_id": 151652,
110
+ "vision_token_id": 151654,
111
+ "vocab_size": 152064
112
+ },
113
+ "tie_word_embeddings": false,
114
+ "transformers_version": "4.56.2",
115
+ "unsloth_fixed": true,
116
+ "unsloth_version": "2026.1.4",
117
+ "use_cache": true,
118
+ "use_sliding_window": false,
119
+ "video_token_id": 151656,
120
+ "vision_config": {
121
+ "depth": 32,
122
+ "dtype": "float16",
123
+ "fullatt_block_indexes": [
124
+ 7,
125
+ 15,
126
+ 23,
127
+ 31
128
+ ],
129
+ "hidden_act": "silu",
130
+ "hidden_size": 1280,
131
+ "in_channels": 3,
132
+ "in_chans": 3,
133
+ "initializer_range": 0.02,
134
+ "intermediate_size": 3420,
135
+ "model_type": "qwen2_5_vl",
136
+ "num_heads": 16,
137
+ "out_hidden_size": 3584,
138
+ "patch_size": 14,
139
+ "spatial_merge_size": 2,
140
+ "spatial_patch_size": 14,
141
+ "temporal_patch_size": 2,
142
+ "tokens_per_second": 2,
143
+ "window_size": 112
144
+ },
145
+ "vision_end_token_id": 151653,
146
+ "vision_start_token_id": 151652,
147
+ "vision_token_id": 151654,
148
+ "vocab_size": 152064
149
+ }
generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_sample": true,
3
+ "eos_token_id": [
4
+ 151645,
5
+ 151643
6
+ ],
7
+ "max_length": 32768,
8
+ "pad_token_id": 151654,
9
+ "repetition_penalty": 1.05,
10
+ "temperature": 1e-06,
11
+ "transformers_version": "4.56.2"
12
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bb72b14bdd8ca76a139cd175a045e7d1a8f0c2be31ef5d212440f8e96697ec1
3
+ size 4983743308
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3b02cbecd1762bba93a6fa9d5473cb7e05965f91811018694dc99e229548a6e
3
+ size 1916652973
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff