egemensert commited on
Commit
00dd537
·
verified ·
1 Parent(s): 1cc320a

Upload Gemma3ForConditionalGeneration

Browse files
config.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Gemma3ForConditionalGeneration"
4
+ ],
5
+ "boi_token_index": 255999,
6
+ "eoi_token_index": 256000,
7
+ "eos_token_id": [
8
+ 1,
9
+ 106
10
+ ],
11
+ "image_token_index": 262144,
12
+ "initializer_range": 0.02,
13
+ "mm_tokens_per_image": 256,
14
+ "model_type": "gemma3",
15
+ "text_config": {
16
+ "attention_bias": false,
17
+ "attention_dropout": 0.0,
18
+ "attn_logit_softcapping": null,
19
+ "cache_implementation": "hybrid",
20
+ "final_logit_softcapping": null,
21
+ "head_dim": 256,
22
+ "hidden_activation": "gelu_pytorch_tanh",
23
+ "hidden_size": 3840,
24
+ "initializer_range": 0.02,
25
+ "intermediate_size": 15360,
26
+ "max_position_embeddings": 131072,
27
+ "model_type": "gemma3_text",
28
+ "num_attention_heads": 16,
29
+ "num_hidden_layers": 48,
30
+ "num_key_value_heads": 8,
31
+ "query_pre_attn_scalar": 256,
32
+ "rms_norm_eps": 1e-06,
33
+ "rope_local_base_freq": 10000.0,
34
+ "rope_scaling": {
35
+ "factor": 8.0,
36
+ "rope_type": "linear"
37
+ },
38
+ "rope_theta": 1000000.0,
39
+ "sliding_window": 1024,
40
+ "sliding_window_pattern": 6,
41
+ "torch_dtype": "float32",
42
+ "use_cache": true,
43
+ "vocab_size": 262208
44
+ },
45
+ "torch_dtype": "bfloat16",
46
+ "transformers_version": "4.50.0.dev0",
47
+ "vision_config": {
48
+ "attention_dropout": 0.0,
49
+ "hidden_act": "gelu_pytorch_tanh",
50
+ "hidden_size": 1152,
51
+ "image_size": 896,
52
+ "intermediate_size": 4304,
53
+ "layer_norm_eps": 1e-06,
54
+ "model_type": "siglip_vision_model",
55
+ "num_attention_heads": 16,
56
+ "num_channels": 3,
57
+ "num_hidden_layers": 27,
58
+ "patch_size": 14,
59
+ "torch_dtype": "float32",
60
+ "vision_use_head": false
61
+ }
62
+ }
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": "4.50.0.dev0"
13
+ }
model-00001-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25ddeddbe52e8bf246a7d0aa13a9161f9cb7bb56ac14c3e0b506454116c0fbca
3
+ size 4979902192
model-00002-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed8e31395657fbc38d2af27411a9aac0aba8f6714824c25f772e836f560ac5f2
3
+ size 4931296592
model-00003-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4239047c4227ab7ef0946345597edb9fa0dbb89dfd27d410f44911ef89e0529
3
+ size 4931296656
model-00004-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35edd79b1e3e5eb43830c47065ded03d1798d14dd2be11397faee58ea547b18b
3
+ size 4931296656
model-00005-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be0074f76c55d9884e1df82ba0ac6a10df190f9ffe8f0a92bc9b00b5571e9aca
3
+ size 4601000928
model-00006-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d79539d9d07965abdc04e865d9218629ee455522ecf5a891b31c677444022d0
3
+ size 2013757584
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff