yjp8842 commited on
Commit
1c054b2
·
verified ·
1 Parent(s): 146b2b6

Upload Gemma3ForConditionalGeneration

Browse files
config.json ADDED
@@ -0,0 +1,79 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "pretraining_tp": 1,
16
+ "quantization_config": {
17
+ "_load_in_4bit": true,
18
+ "_load_in_8bit": false,
19
+ "bnb_4bit_compute_dtype": "bfloat16",
20
+ "bnb_4bit_quant_storage": "uint8",
21
+ "bnb_4bit_quant_type": "nf4",
22
+ "bnb_4bit_use_double_quant": false,
23
+ "llm_int8_enable_fp32_cpu_offload": false,
24
+ "llm_int8_has_fp16_weight": false,
25
+ "llm_int8_skip_modules": null,
26
+ "llm_int8_threshold": 6.0,
27
+ "load_in_4bit": true,
28
+ "load_in_8bit": false,
29
+ "quant_method": "bitsandbytes"
30
+ },
31
+ "text_config": {
32
+ "attention_bias": false,
33
+ "attention_dropout": 0.0,
34
+ "attn_logit_softcapping": null,
35
+ "cache_implementation": "hybrid",
36
+ "final_logit_softcapping": null,
37
+ "head_dim": 128,
38
+ "hidden_activation": "gelu_pytorch_tanh",
39
+ "hidden_size": 5376,
40
+ "initializer_range": 0.02,
41
+ "intermediate_size": 21504,
42
+ "max_position_embeddings": 131072,
43
+ "model_type": "gemma3_text",
44
+ "num_attention_heads": 32,
45
+ "num_hidden_layers": 62,
46
+ "num_key_value_heads": 16,
47
+ "query_pre_attn_scalar": 168,
48
+ "rms_norm_eps": 1e-06,
49
+ "rope_local_base_freq": 10000.0,
50
+ "rope_scaling": {
51
+ "factor": 8.0,
52
+ "rope_type": "linear"
53
+ },
54
+ "rope_theta": 1000000.0,
55
+ "sliding_window": 1024,
56
+ "sliding_window_pattern": 6,
57
+ "torch_dtype": "float16",
58
+ "use_cache": true,
59
+ "vocab_size": 262208
60
+ },
61
+ "torch_dtype": "float16",
62
+ "transformers_version": "4.51.3",
63
+ "use_cache": false,
64
+ "vision_config": {
65
+ "attention_dropout": 0.0,
66
+ "hidden_act": "gelu_pytorch_tanh",
67
+ "hidden_size": 1152,
68
+ "image_size": 896,
69
+ "intermediate_size": 4304,
70
+ "layer_norm_eps": 1e-06,
71
+ "model_type": "siglip_vision_model",
72
+ "num_attention_heads": 16,
73
+ "num_channels": 3,
74
+ "num_hidden_layers": 27,
75
+ "patch_size": 14,
76
+ "torch_dtype": "float16",
77
+ "vision_use_head": false
78
+ }
79
+ }
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": "4.51.3"
13
+ }
model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:448a49017a84716400fe3f0d8199a1d384935f7f9e2b2906d3330cf3fca56720
3
+ size 4970124630
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2d415883398adbacc0f28e95daaa645ebb1b985a1f80feaae59da565f4dc10f
3
+ size 4943167748
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c94f1edda0ba2df2259e1898a9dc671623c52fee10bcc364b00a1a0232ac86c8
3
+ size 4943167804
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67b2e466c284b2286bc2352059164db463cf1907d0d5ed9800bda34234509868
3
+ size 2620298760
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff