prince-canuma commited on
Commit
4caffdb
·
verified ·
1 Parent(s): 0c45b31

Upload folder using huggingface_hub

Browse files
text_encoder/config.json ADDED
@@ -0,0 +1,114 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Gemma3ForConditionalGeneration"
4
+ ],
5
+ "boi_token_index": 255999,
6
+ "dtype": "float32",
7
+ "eoi_token_index": 256000,
8
+ "eos_token_id": [
9
+ 1,
10
+ 106
11
+ ],
12
+ "image_token_index": 262144,
13
+ "initializer_range": 0.02,
14
+ "mm_tokens_per_image": 256,
15
+ "model_type": "gemma3",
16
+ "text_config": {
17
+ "_sliding_window_pattern": 6,
18
+ "attention_bias": false,
19
+ "attention_dropout": 0.0,
20
+ "attn_logit_softcapping": null,
21
+ "cache_implementation": "hybrid",
22
+ "dtype": "float32",
23
+ "final_logit_softcapping": null,
24
+ "head_dim": 256,
25
+ "hidden_activation": "gelu_pytorch_tanh",
26
+ "hidden_size": 3840,
27
+ "initializer_range": 0.02,
28
+ "intermediate_size": 15360,
29
+ "layer_types": [
30
+ "sliding_attention",
31
+ "sliding_attention",
32
+ "sliding_attention",
33
+ "sliding_attention",
34
+ "sliding_attention",
35
+ "full_attention",
36
+ "sliding_attention",
37
+ "sliding_attention",
38
+ "sliding_attention",
39
+ "sliding_attention",
40
+ "sliding_attention",
41
+ "full_attention",
42
+ "sliding_attention",
43
+ "sliding_attention",
44
+ "sliding_attention",
45
+ "sliding_attention",
46
+ "sliding_attention",
47
+ "full_attention",
48
+ "sliding_attention",
49
+ "sliding_attention",
50
+ "sliding_attention",
51
+ "sliding_attention",
52
+ "sliding_attention",
53
+ "full_attention",
54
+ "sliding_attention",
55
+ "sliding_attention",
56
+ "sliding_attention",
57
+ "sliding_attention",
58
+ "sliding_attention",
59
+ "full_attention",
60
+ "sliding_attention",
61
+ "sliding_attention",
62
+ "sliding_attention",
63
+ "sliding_attention",
64
+ "sliding_attention",
65
+ "full_attention",
66
+ "sliding_attention",
67
+ "sliding_attention",
68
+ "sliding_attention",
69
+ "sliding_attention",
70
+ "sliding_attention",
71
+ "full_attention",
72
+ "sliding_attention",
73
+ "sliding_attention",
74
+ "sliding_attention",
75
+ "sliding_attention",
76
+ "sliding_attention",
77
+ "full_attention"
78
+ ],
79
+ "max_position_embeddings": 131072,
80
+ "model_type": "gemma3_text",
81
+ "num_attention_heads": 16,
82
+ "num_hidden_layers": 48,
83
+ "num_key_value_heads": 8,
84
+ "query_pre_attn_scalar": 256,
85
+ "rms_norm_eps": 1e-06,
86
+ "rope_local_base_freq": 10000,
87
+ "rope_scaling": {
88
+ "factor": 8.0,
89
+ "rope_type": "linear"
90
+ },
91
+ "rope_theta": 1000000,
92
+ "sliding_window": 1024,
93
+ "sliding_window_pattern": 6,
94
+ "use_bidirectional_attention": false,
95
+ "use_cache": true,
96
+ "vocab_size": 262208
97
+ },
98
+ "transformers_version": "4.57.3",
99
+ "vision_config": {
100
+ "attention_dropout": 0.0,
101
+ "dtype": "float32",
102
+ "hidden_act": "gelu_pytorch_tanh",
103
+ "hidden_size": 1152,
104
+ "image_size": 896,
105
+ "intermediate_size": 4304,
106
+ "layer_norm_eps": 1e-06,
107
+ "model_type": "siglip_vision_model",
108
+ "num_attention_heads": 16,
109
+ "num_channels": 3,
110
+ "num_hidden_layers": 27,
111
+ "patch_size": 14,
112
+ "vision_use_head": false
113
+ }
114
+ }
text_encoder/generation_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cache_implementation": "hybrid",
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 1,
6
+ 106
7
+ ],
8
+ "top_k": 64,
9
+ "top_p": 0.95,
10
+ "transformers_version": "4.57.3"
11
+ }
text_encoder/model-00001-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbc6e8132e4998652d4c8c219f0ca8da10a143606c806c8728a7513d49bbcdb3
3
+ size 1685223128
text_encoder/model-00002-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b95e7ab472b88860e53c71ef078fe8ba4c85e3727b8f0a0bcc130c1f4a2b9ab9
3
+ size 4987027384
text_encoder/model-00003-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3731e7c18280d0e9dcbcfadaecaeb8b81fa7f7f15e702ea3d1b4f8eb1b5919f7
3
+ size 4844749824
text_encoder/model-00004-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9d1ce8b472f2cc6d70c7885388f50fb3a5f233cf1d4784f6a4be1732547a74c
3
+ size 4954909736
text_encoder/model-00005-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb478659a67b2e34a920f237387a1d7a8208325aa2fc285198a97603f15af1e6
3
+ size 4907664584
text_encoder/model-00006-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a190581d871980f9309f40d5c2b4db99d76737d7ed743d531bac95443f6b7145
3
+ size 4954909792
text_encoder/model-00007-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c347de789ff34be642e4fe7ab8e142ca5e3d833d70cb9ec5127a86af0e2ecfed
3
+ size 4907664584
text_encoder/model-00008-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ec7525b89b083d774f4abbdd1f2d7ee190f0475658875cf700530a2faa84a4f
3
+ size 4954909792
text_encoder/model-00009-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b0117ecf1d83691bb875c66a9f2b47e450a87fdfe90915bc7b9e9946c37a650
3
+ size 4907664584
text_encoder/model-00010-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9f665a743589231adb812c61c9d8e295c9a68c31d3e87976ae032f1de4e46b6
3
+ size 4954909792
text_encoder/model-00011-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:999bf4706d4f616e558eec486667fc2b66f8d0f9c106e1d1f802458fb349b0db
3
+ size 2689808472
text_encoder/model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff