CocoRoF commited on
Commit
565274c
·
verified ·
1 Parent(s): af23ed1

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": 128,
22
+ "hidden_activation": "gelu_pytorch_tanh",
23
+ "hidden_size": 5376,
24
+ "initializer_range": 0.02,
25
+ "intermediate_size": 21504,
26
+ "max_position_embeddings": 131072,
27
+ "model_type": "gemma3_text",
28
+ "num_attention_heads": 32,
29
+ "num_hidden_layers": 62,
30
+ "num_key_value_heads": 16,
31
+ "query_pre_attn_scalar": 168,
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",
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"
13
+ }
model-00001-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7109dc8310c6a88c09d4c02df245a05d5ec218dab9634f2c428c0745e038803
3
+ size 4854573696
model-00002-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e78b63eda8bc0b9ee0b039d505a2506a0bf8ac9b141353e37c4b6021dcf2904
3
+ size 4954792944
model-00003-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f9430b842da6480a819bcda0654e7cc7c5591196d49c76bc3d00e74a009d89b
3
+ size 4954792976
model-00004-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54bc42d474960f7baffc45af730c1e3c1285deaa85eceebb958d3e8bce0b8668
3
+ size 4954793016
model-00005-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:757122058c83b29140b8ebc5ec051c690b5050825135e2ce53fe6d0d30befc33
3
+ size 4954793016
model-00006-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:efee2b4e005ae46f5af64062c06508eff28e7c74ddd860eac0cb2bad1d52efab
3
+ size 4954793016
model-00007-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a81d0ff76c1d31564e6094155b36e29ff5709881ca175bd21036228b403a657
3
+ size 4954793016
model-00008-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78da1454f17b6888c1d00a723d5ce801d317c7fb6ba2ee35511ba4c4b2d39ac7
3
+ size 4954793016
model-00009-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46016a56cf9919a0dfb43f3bb55e0f9108d83e692dfcfc2c8297f61101c1d4a6
3
+ size 4954793016
model-00010-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6c5d6b3a323d39bcbe524079708fe26a5b97521ca950034de10e85c56ff70ce
3
+ size 4954793016
model-00011-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41281d455070c54ec824ae215fff060c06c4c3819b86034194b0257f7d4da8e6
3
+ size 4954793016
model-00012-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:927e1825fd52a45ac54d67c0673cd596705c7d50e82dd0c7dbf3841c56c03b9e
3
+ size 3281737240
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff