jarvisvasu commited on
Commit
42d901e
·
verified ·
1 Parent(s): 96a44fe

Upload model trained with Unsloth

Browse files

Upload model trained with Unsloth 2x faster

config.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Qwen/Qwen2.5-VL-7B-Instruct",
3
+ "architectures": [
4
+ "Qwen2_5_VLForConditionalGeneration"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "eos_token_id": 151645,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 3584,
11
+ "image_token_id": 151655,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 18944,
14
+ "max_position_embeddings": 128000,
15
+ "max_window_layers": 28,
16
+ "model_type": "qwen2_5_vl",
17
+ "num_attention_heads": 28,
18
+ "num_hidden_layers": 28,
19
+ "num_key_value_heads": 4,
20
+ "pad_token_id": 151643,
21
+ "quantization_config": {
22
+ "bnb_4bit_compute_dtype": "float16",
23
+ "bnb_4bit_quant_type": "nf4",
24
+ "bnb_4bit_use_double_quant": true,
25
+ "llm_int8_enable_fp32_cpu_offload": false,
26
+ "llm_int8_has_fp16_weight": false,
27
+ "llm_int8_skip_modules": null,
28
+ "llm_int8_threshold": 6.0,
29
+ "load_in_4bit": true,
30
+ "load_in_8bit": false,
31
+ "quant_method": "bitsandbytes"
32
+ },
33
+ "rms_norm_eps": 1e-06,
34
+ "rope_scaling": {
35
+ "mrope_section": [
36
+ 16,
37
+ 24,
38
+ 24
39
+ ],
40
+ "rope_type": "default",
41
+ "type": "default"
42
+ },
43
+ "rope_theta": 1000000.0,
44
+ "sliding_window": 32768,
45
+ "tie_word_embeddings": false,
46
+ "torch_dtype": "float16",
47
+ "transformers_version": "4.49.0.dev0",
48
+ "unsloth_version": "2025.1.7",
49
+ "use_cache": true,
50
+ "use_sliding_window": false,
51
+ "video_token_id": 151656,
52
+ "vision_config": {
53
+ "hidden_size": 1280,
54
+ "in_chans": 3,
55
+ "model_type": "qwen2_5_vl",
56
+ "spatial_patch_size": 14,
57
+ "tokens_per_second": 2,
58
+ "torch_dtype": "float16"
59
+ },
60
+ "vision_end_token_id": 151653,
61
+ "vision_start_token_id": 151652,
62
+ "vision_token_id": 151654,
63
+ "vocab_size": 152064
64
+ }
generation_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "max_length": 128000,
9
+ "pad_token_id": 151643,
10
+ "repetition_penalty": 1.05,
11
+ "temperature": 0.1,
12
+ "top_k": 1,
13
+ "top_p": 0.001,
14
+ "transformers_version": "4.49.0.dev0"
15
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65153499432a32a1db1c9c7d89f18540f56b2ce4aedc8a832da066c927df8a2b
3
+ size 4875747771
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5181b7db052ab9f942adc02f7e687594f7de4dd95bd69a3802be45e5f80d4f4d
3
+ size 1089994880
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff