CodeAtCMU/gemma-3-4b-pt_full_sft_code_data_120K_replace_variables

1{2  "architectures": [3    "Gemma3ForConditionalGeneration"4  ],5  "boi_token_index": 255999,6  "eoi_token_index": 256000,7  "hidden_size": 2560,8  "image_token_index": 262144,9  "initializer_range": 0.02,10  "mm_tokens_per_image": 256,11  "model_type": "gemma3",12  "text_config": {13    "attention_bias": false,14    "attention_dropout": 0.0,15    "attn_logit_softcapping": null,16    "cache_implementation": "hybrid",17    "final_logit_softcapping": null,18    "head_dim": 256,19    "hidden_activation": "gelu_pytorch_tanh",20    "hidden_size": 2560,21    "initializer_range": 0.02,22    "intermediate_size": 10240,23    "max_position_embeddings": 131072,24    "model_type": "gemma3_text",25    "num_attention_heads": 8,26    "num_hidden_layers": 34,27    "num_key_value_heads": 4,28    "query_pre_attn_scalar": 256,29    "rms_norm_eps": 1e-06,30    "rope_local_base_freq": 10000.0,31    "rope_scaling": {32      "factor": 8.0,33      "rope_type": "linear"34    },35    "rope_theta": 1000000.0,36    "sliding_window": 1024,37    "sliding_window_pattern": 6,38    "torch_dtype": "float32",39    "use_cache": false,40    "vocab_size": 26220841  },42  "torch_dtype": "float32",43  "transformers_version": "4.51.3",44  "use_cache": false,45  "vision_config": {46    "attention_dropout": 0.0,47    "hidden_act": "gelu_pytorch_tanh",48    "hidden_size": 1152,49    "image_size": 896,50    "intermediate_size": 4304,51    "layer_norm_eps": 1e-06,52    "model_type": "siglip_vision_model",53    "num_attention_heads": 16,54    "num_channels": 3,55    "num_hidden_layers": 27,56    "patch_size": 14,57    "torch_dtype": "float32",58    "vision_use_head": false59  }60}61