jg-enosh commited on
Commit
3ddc531
·
verified ·
1 Parent(s): 43fc946

Upload model trained with Unsloth

Browse files

Upload model trained with Unsloth 2x faster

Files changed (3) hide show
  1. config.json +24 -51
  2. generation_config.json +1 -0
  3. model.safetensors +3 -0
config.json CHANGED
@@ -1,63 +1,36 @@
1
  {
2
  "architectures": [
3
- "Gemma3ForConditionalGeneration"
4
  ],
5
- "boi_token_index": 255999,
 
 
6
  "bos_token_id": 2,
7
- "eoi_token_index": 256000,
8
  "eos_token_id": 106,
9
- "image_token_index": 262144,
 
 
 
10
  "initializer_range": 0.02,
11
- "mm_tokens_per_image": 256,
12
- "model_type": "gemma3",
 
 
 
 
13
  "pad_token_id": 0,
14
- "text_config": {
15
- "attention_bias": false,
16
- "attention_dropout": 0.0,
17
- "attn_logit_softcapping": null,
18
- "cache_implementation": "hybrid",
19
- "final_logit_softcapping": null,
20
- "head_dim": 256,
21
- "hidden_activation": "gelu_pytorch_tanh",
22
- "hidden_size": 2560,
23
- "initializer_range": 0.02,
24
- "intermediate_size": 10240,
25
- "max_position_embeddings": 131072,
26
- "model_type": "gemma3_text",
27
- "num_attention_heads": 8,
28
- "num_hidden_layers": 34,
29
- "num_key_value_heads": 4,
30
- "query_pre_attn_scalar": 256,
31
- "rms_norm_eps": 1e-06,
32
- "rope_local_base_freq": 10000.0,
33
- "rope_scaling": {
34
- "factor": 8.0,
35
- "rope_type": "linear"
36
- },
37
- "rope_theta": 1000000.0,
38
- "sliding_window": 1024,
39
- "sliding_window_pattern": 6,
40
- "torch_dtype": "bfloat16",
41
- "use_cache": true,
42
- "vocab_size": 262208
43
- },
44
  "torch_dtype": "bfloat16",
45
  "transformers_version": "4.51.3",
46
  "unsloth_fixed": true,
47
  "unsloth_version": "2025.5.7",
48
- "vision_config": {
49
- "attention_dropout": 0.0,
50
- "hidden_act": "gelu_pytorch_tanh",
51
- "hidden_size": 1152,
52
- "image_size": 896,
53
- "intermediate_size": 4304,
54
- "layer_norm_eps": 1e-06,
55
- "model_type": "siglip_vision_model",
56
- "num_attention_heads": 16,
57
- "num_channels": 3,
58
- "num_hidden_layers": 27,
59
- "patch_size": 14,
60
- "torch_dtype": "bfloat16",
61
- "vision_use_head": false
62
- }
63
  }
 
1
  {
2
  "architectures": [
3
+ "Gemma3ForCausalLM"
4
  ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "attn_logit_softcapping": null,
8
  "bos_token_id": 2,
9
+ "cache_implementation": "hybrid",
10
  "eos_token_id": 106,
11
+ "final_logit_softcapping": null,
12
+ "head_dim": 256,
13
+ "hidden_activation": "gelu_pytorch_tanh",
14
+ "hidden_size": 1152,
15
  "initializer_range": 0.02,
16
+ "intermediate_size": 6912,
17
+ "max_position_embeddings": 32768,
18
+ "model_type": "gemma3_text",
19
+ "num_attention_heads": 4,
20
+ "num_hidden_layers": 26,
21
+ "num_key_value_heads": 1,
22
  "pad_token_id": 0,
23
+ "query_pre_attn_scalar": 256,
24
+ "rms_norm_eps": 1e-06,
25
+ "rope_local_base_freq": 10000,
26
+ "rope_scaling": null,
27
+ "rope_theta": 1000000,
28
+ "sliding_window": 512,
29
+ "sliding_window_pattern": 6,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
30
  "torch_dtype": "bfloat16",
31
  "transformers_version": "4.51.3",
32
  "unsloth_fixed": true,
33
  "unsloth_version": "2025.5.7",
34
+ "use_cache": true,
35
+ "vocab_size": 262144
 
 
 
 
 
 
 
 
 
 
 
 
 
36
  }
generation_config.json CHANGED
@@ -6,6 +6,7 @@
6
  1,
7
  106
8
  ],
 
9
  "pad_token_id": 0,
10
  "top_k": 64,
11
  "top_p": 0.95,
 
6
  1,
7
  106
8
  ],
9
+ "max_length": 32768,
10
  "pad_token_id": 0,
11
  "top_k": 64,
12
  "top_p": 0.95,
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bfc2f74c2c6da7a922d4adf7ed7e8ff2c2e638588c8f2ceea100819b27b2a698
3
+ size 1999811208