Lamapi commited on
Commit
f648eae
·
verified ·
1 Parent(s): 50c0446

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
  - gemma3
8
  - trl
 
9
  license: apache-2.0
10
  language:
11
  - en
 
6
  - unsloth
7
  - gemma3
8
  - trl
9
+ - sft
10
  license: apache-2.0
11
  language:
12
  - en
config.json ADDED
@@ -0,0 +1,113 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Gemma3ForConditionalGeneration"
4
+ ],
5
+ "boi_token_index": 255999,
6
+ "bos_token_id": 2,
7
+ "dtype": "bfloat16",
8
+ "eoi_token_index": 256000,
9
+ "eos_token_id": 106,
10
+ "image_token_index": 262144,
11
+ "initializer_range": 0.02,
12
+ "mm_tokens_per_image": 256,
13
+ "model_type": "gemma3",
14
+ "pad_token_id": 0,
15
+ "text_config": {
16
+ "_sliding_window_pattern": 6,
17
+ "attention_bias": false,
18
+ "attention_dropout": 0.0,
19
+ "attn_logit_softcapping": null,
20
+ "cache_implementation": "hybrid",
21
+ "dtype": "bfloat16",
22
+ "final_logit_softcapping": null,
23
+ "head_dim": 256,
24
+ "hidden_activation": "gelu_pytorch_tanh",
25
+ "hidden_size": 3840,
26
+ "initializer_range": 0.02,
27
+ "intermediate_size": 15360,
28
+ "layer_types": [
29
+ "sliding_attention",
30
+ "sliding_attention",
31
+ "sliding_attention",
32
+ "sliding_attention",
33
+ "sliding_attention",
34
+ "full_attention",
35
+ "sliding_attention",
36
+ "sliding_attention",
37
+ "sliding_attention",
38
+ "sliding_attention",
39
+ "sliding_attention",
40
+ "full_attention",
41
+ "sliding_attention",
42
+ "sliding_attention",
43
+ "sliding_attention",
44
+ "sliding_attention",
45
+ "sliding_attention",
46
+ "full_attention",
47
+ "sliding_attention",
48
+ "sliding_attention",
49
+ "sliding_attention",
50
+ "sliding_attention",
51
+ "sliding_attention",
52
+ "full_attention",
53
+ "sliding_attention",
54
+ "sliding_attention",
55
+ "sliding_attention",
56
+ "sliding_attention",
57
+ "sliding_attention",
58
+ "full_attention",
59
+ "sliding_attention",
60
+ "sliding_attention",
61
+ "sliding_attention",
62
+ "sliding_attention",
63
+ "sliding_attention",
64
+ "full_attention",
65
+ "sliding_attention",
66
+ "sliding_attention",
67
+ "sliding_attention",
68
+ "sliding_attention",
69
+ "sliding_attention",
70
+ "full_attention",
71
+ "sliding_attention",
72
+ "sliding_attention",
73
+ "sliding_attention",
74
+ "sliding_attention",
75
+ "sliding_attention",
76
+ "full_attention"
77
+ ],
78
+ "max_position_embeddings": 131072,
79
+ "model_type": "gemma3_text",
80
+ "num_attention_heads": 16,
81
+ "num_hidden_layers": 48,
82
+ "num_key_value_heads": 8,
83
+ "query_pre_attn_scalar": 256,
84
+ "rms_norm_eps": 1e-06,
85
+ "rope_local_base_freq": 10000.0,
86
+ "rope_scaling": {
87
+ "factor": 8.0,
88
+ "rope_type": "linear"
89
+ },
90
+ "rope_theta": 1000000.0,
91
+ "sliding_window": 1024,
92
+ "use_cache": true,
93
+ "vocab_size": 262208
94
+ },
95
+ "transformers_version": "4.56.2",
96
+ "unsloth_fixed": true,
97
+ "unsloth_version": "2025.10.10",
98
+ "vision_config": {
99
+ "attention_dropout": 0.0,
100
+ "dtype": "bfloat16",
101
+ "hidden_act": "gelu_pytorch_tanh",
102
+ "hidden_size": 1152,
103
+ "image_size": 896,
104
+ "intermediate_size": 4304,
105
+ "layer_norm_eps": 1e-06,
106
+ "model_type": "siglip_vision_model",
107
+ "num_attention_heads": 16,
108
+ "num_channels": 3,
109
+ "num_hidden_layers": 27,
110
+ "patch_size": 14,
111
+ "vision_use_head": false
112
+ }
113
+ }
generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 2,
3
+ "cache_implementation": "hybrid",
4
+ "do_sample": true,
5
+ "eos_token_id": [
6
+ 1,
7
+ 106
8
+ ],
9
+ "pad_token_id": 0,
10
+ "top_k": 64,
11
+ "top_p": 0.95,
12
+ "transformers_version": "4.56.2"
13
+ }
model-00001-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0df7c5d0bab4f1778a7246153e85c19de80c1e2f4fc27da2203d7de0957d09b
3
+ size 4979902192
model-00002-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aaf866125f1c06fadea3bde354f3aa2b946f2dc5e6d1d1838c72948ee8e65a43
3
+ size 4931296592
model-00003-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be150a3fbb77cc39106f883adf96300bec80165a617efb7f6bcac4dd854e552d
3
+ size 4931296656
model-00004-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d2120ee72abc70741d8d8024fa69a5c6aec5f92aa8a5e331e4a1460c1fbdf4e
3
+ size 4931296656
model-00005-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ee7bc57e1dd3fb2d57df5f5bbacff9cc79cf16b28d4de572dd05aec272bc0aa
3
+ size 4601000928
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff