tonyli8623/Hicoder-R1-Distill-Gemma-27B

1{
2  "architectures": [
3    "Gemma3ForConditionalGeneration"
4  ],
5  "boi_token_index": 255999,
6  "bos_token_id": 2,
7  "eoi_token_index": 256000,
8  "eos_token_id": 106,
9  "image_token_index": 262144,
10  "initializer_range": 0.02,
11  "mm_tokens_per_image": 256,
12  "model_type": "gemma3",
13  "pad_token_id": 0,
14  "text_config": {
15    "attention_bias": false,
16    "attention_dropout": 0.0,
17    "attn_logit_softcapping": null,
18    "cache_implementation": "hybrid",
19    "final_logit_softcapping": null,
20    "head_dim": 128,
21    "hidden_activation": "gelu_pytorch_tanh",
22    "hidden_size": 5376,
23    "initializer_range": 0.02,
24    "intermediate_size": 21504,
25    "max_position_embeddings": 131072,
26    "model_type": "gemma3_text",
27    "num_attention_heads": 32,
28    "num_hidden_layers": 62,
29    "num_key_value_heads": 16,
30    "query_pre_attn_scalar": 168,
31    "rms_norm_eps": 1e-06,
32    "rope_local_base_freq": 10000.0,
33    "rope_scaling": {
34      "factor": 8.0,
35      "rope_type": "linear"
36    },
37    "rope_theta": 1000000.0,
38    "sliding_window": 1024,
39    "sliding_window_pattern": 6,
40    "torch_dtype": "bfloat16",
41    "use_cache": true,
42    "vocab_size": 262208
43  },
44  "torch_dtype": "bfloat16",
45  "transformers_version": "4.50.0",
46  "unsloth_fixed": true,
47  "unsloth_version": "2025.3.19",
48  "vision_config": {
49    "attention_dropout": 0.0,
50    "hidden_act": "gelu_pytorch_tanh",
51    "hidden_size": 1152,
52    "image_size": 896,
53    "intermediate_size": 4304,
54    "layer_norm_eps": 1e-06,
55    "model_type": "siglip_vision_model",
56    "num_attention_heads": 16,
57    "num_channels": 3,
58    "num_hidden_layers": 27,
59    "patch_size": 14,
60    "torch_dtype": "bfloat16",
61    "vision_use_head": false
62  }
63}
64