config.json

{
  "architectures": [
    "Gemma3ForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "attn_logit_softcapping": null,
  "bos_token_id": 2,
  "cache_implementation": "hybrid",
  "eos_token_id": 106,
  "final_logit_softcapping": null,
  "head_dim": 128,
  "hidden_activation": "gelu_pytorch_tanh",
  "hidden_size": 5376,
  "initializer_range": 0.02,
  "intermediate_size": 21504,
  "max_position_embeddings": 131072,
  "model_type": "gemma3_text",
  "num_attention_heads": 32,
  "num_hidden_layers": 62,
  "num_key_value_heads": 16,
  "pad_token_id": 0,
  "quantization_config": {
    "_load_in_4bit": true,
    "_load_in_8bit": false,
    "bnb_4bit_compute_dtype": "bfloat16",
    "bnb_4bit_quant_storage": "uint8",
    "bnb_4bit_quant_type": "nf4",
    "bnb_4bit_use_double_quant": true,
    "llm_int8_enable_fp32_cpu_offload": false,
    "llm_int8_has_fp16_weight": false,
    "llm_int8_skip_modules": [
      "lm_head",
      "multi_modal_projector",
      "merger",
      "modality_projection"
    ],
    "llm_int8_threshold": 6.0,
    "load_in_4bit": true,
    "load_in_8bit": false,
    "quant_method": "bitsandbytes"
  },
  "query_pre_attn_scalar": 168,
  "rms_norm_eps": 1e-06,
  "rope_local_base_freq": 10000,
  "rope_scaling": {
    "factor": 8.0,
    "rope_type": "linear"
  },
  "rope_theta": 1000000,
  "sliding_window": 1024,
  "sliding_window_pattern": 6,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.52.1",
  "unsloth_fixed": true,
  "use_cache": true,
  "vocab_size": 262144
}