Hugging Face's logo

isbondarev
/
test_model_0814

Image-Text-to-Text
Transformers
Safetensors
gemma3
llama-factory
conversational
text-generation-inference
Model card Files
xet
Community
isbondarev commited on
Commit
dcd50c1
·
verified ·
1 Parent(s): e65f8e8

Upload Gemma3ForConditionalGeneration

Browse files
Files changed (5) hide show
  1. config.json +90 -59
  2. generation_config.json +6 -6
  3. model-00001-of-00002.safetensors +2 -2
  4. model-00002-of-00002.safetensors +2 -2
  5. model.safetensors.index.json +0 -0
config.json CHANGED
@@ -1,68 +1,99 @@
1
  {
2
  "architectures": [
3
- "Qwen3ForCausalLM"
 
 
 
 
 
 
4
  ],
5
- "attention_bias": false,
6
- "attention_dropout": 0.0,
7
- "bos_token_id": 151643,
8
- "eos_token_id": 151645,
9
- "head_dim": 128,
10
- "hidden_act": "silu",
11
  "hidden_size": 2560,
 
12
  "initializer_range": 0.02,
13
- "intermediate_size": 9728,
14
- "layer_types": [
15
- "full_attention",
16
- "full_attention",
17
- "full_attention",
18
- "full_attention",
19
- "full_attention",
20
- "full_attention",
21
- "full_attention",
22
- "full_attention",
23
- "full_attention",
24
- "full_attention",
25
- "full_attention",
26
- "full_attention",
27
- "full_attention",
28
- "full_attention",
29
- "full_attention",
30
- "full_attention",
31
- "full_attention",
32
- "full_attention",
33
- "full_attention",
34
- "full_attention",
35
- "full_attention",
36
- "full_attention",
37
- "full_attention",
38
- "full_attention",
39
- "full_attention",
40
- "full_attention",
41
- "full_attention",
42
- "full_attention",
43
- "full_attention",
44
- "full_attention",
45
- "full_attention",
46
- "full_attention",
47
- "full_attention",
48
- "full_attention",
49
- "full_attention",
50
- "full_attention"
51
- ],
52
- "max_position_embeddings": 40960,
53
- "max_window_layers": 36,
54
- "model_type": "qwen3",
55
- "num_attention_heads": 32,
56
- "num_hidden_layers": 36,
57
- "num_key_value_heads": 8,
58
- "rms_norm_eps": 1e-06,
59
- "rope_scaling": null,
60
- "rope_theta": 1000000,
61
- "sliding_window": null,
62
- "tie_word_embeddings": true,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
63
  "torch_dtype": "bfloat16",
64
  "transformers_version": "4.55.0",
65
  "use_cache": true,
66
- "use_sliding_window": false,
67
- "vocab_size": 151936
 
 
 
 
 
 
 
 
 
 
 
 
 
68
  }
 
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
  "hidden_size": 2560,
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
+ "final_logit_softcapping": null,
22
+ "head_dim": 256,
23
+ "hidden_activation": "gelu_pytorch_tanh",
24
+ "hidden_size": 2560,
25
+ "initializer_range": 0.02,
26
+ "intermediate_size": 10240,
27
+ "layer_types": [
28
+ "sliding_attention",
29
+ "sliding_attention",
30
+ "sliding_attention",
31
+ "sliding_attention",
32
+ "sliding_attention",
33
+ "full_attention",
34
+ "sliding_attention",
35
+ "sliding_attention",
36
+ "sliding_attention",
37
+ "sliding_attention",
38
+ "sliding_attention",
39
+ "full_attention",
40
+ "sliding_attention",
41
+ "sliding_attention",
42
+ "sliding_attention",
43
+ "sliding_attention",
44
+ "sliding_attention",
45
+ "full_attention",
46
+ "sliding_attention",
47
+ "sliding_attention",
48
+ "sliding_attention",
49
+ "sliding_attention",
50
+ "sliding_attention",
51
+ "full_attention",
52
+ "sliding_attention",
53
+ "sliding_attention",
54
+ "sliding_attention",
55
+ "sliding_attention",
56
+ "sliding_attention",
57
+ "full_attention",
58
+ "sliding_attention",
59
+ "sliding_attention",
60
+ "sliding_attention",
61
+ "sliding_attention"
62
+ ],
63
+ "max_position_embeddings": 131072,
64
+ "model_type": "gemma3_text",
65
+ "num_attention_heads": 8,
66
+ "num_hidden_layers": 34,
67
+ "num_key_value_heads": 4,
68
+ "query_pre_attn_scalar": 256,
69
+ "rms_norm_eps": 1e-06,
70
+ "rope_local_base_freq": 10000.0,
71
+ "rope_scaling": {
72
+ "factor": 8.0,
73
+ "rope_type": "linear"
74
+ },
75
+ "rope_theta": 1000000.0,
76
+ "sliding_window": 1024,
77
+ "torch_dtype": "bfloat16",
78
+ "use_cache": true,
79
+ "vocab_size": 262208
80
+ },
81
  "torch_dtype": "bfloat16",
82
  "transformers_version": "4.55.0",
83
  "use_cache": true,
84
+ "vision_config": {
85
+ "attention_dropout": 0.0,
86
+ "hidden_act": "gelu_pytorch_tanh",
87
+ "hidden_size": 1152,
88
+ "image_size": 896,
89
+ "intermediate_size": 4304,
90
+ "layer_norm_eps": 1e-06,
91
+ "model_type": "siglip_vision_model",
92
+ "num_attention_heads": 16,
93
+ "num_channels": 3,
94
+ "num_hidden_layers": 27,
95
+ "patch_size": 14,
96
+ "torch_dtype": "bfloat16",
97
+ "vision_use_head": false
98
+ }
99
  }
generation_config.json CHANGED
@@ -1,13 +1,13 @@
1
  {
2
- "bos_token_id": 151643,
 
3
  "do_sample": true,
4
  "eos_token_id": [
5
- 151645,
6
- 151643
7
  ],
8
- "pad_token_id": 151643,
9
- "temperature": 0.6,
10
- "top_k": 20,
11
  "top_p": 0.95,
12
  "transformers_version": "4.55.0"
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": "4.55.0"
13
  }
model-00001-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:612a44927d71414e904b17f68a5a9dfcb8c8d259f51b9169156b0b52775e1299
3
- size 4967215360
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb5fd5e97ddd07b56778733e9653c07312529cb00980a318fc3e1c4e3b5a8f1f
3
+ size 4961251752
model-00002-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6418680e3d22be7a96567bbe3376aba85704f18aa1a3012be8955c2d7cc57d5b
3
- size 3077766632
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fdde0e5aa5ced0fa203b3d50f4ab78168b7e3a3e08c6349f5cc9326666e1bb13
3
+ size 3639026128
model.safetensors.index.json CHANGED
The diff for this file is too large to render. See raw diff