| { | |
| "architectures": [ | |
| "Gemma3ForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "attn_logit_softcapping": null, | |
| "bos_token_id": 2, | |
| "cache_implementation": "hybrid", | |
| "eos_token_id": [ | |
| 1, | |
| 106 | |
| ], | |
| "final_logit_softcapping": null, | |
| "head_dim": 256, | |
| "hidden_activation": "gelu_pytorch_tanh", | |
| "hidden_size": 1152, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 6912, | |
| "max_position_embeddings": 32768, | |
| "model_type": "gemma3_text", | |
| "num_attention_heads": 4, | |
| "num_hidden_layers": 26, | |
| "num_key_value_heads": 1, | |
| "pad_token_id": 0, | |
| "quantization_config": { | |
| "_load_in_4bit": true, | |
| "_load_in_8bit": false, | |
| "bnb_4bit_compute_dtype": "float16", | |
| "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": null, | |
| "llm_int8_threshold": 6.0, | |
| "load_in_4bit": true, | |
| "load_in_8bit": false, | |
| "quant_method": "bitsandbytes" | |
| }, | |
| "query_pre_attn_scalar": 256, | |
| "rms_norm_eps": 1e-06, | |
| "rope_local_base_freq": 10000, | |
| "rope_scaling": null, | |
| "rope_theta": 1000000, | |
| "sliding_window": 512, | |
| "sliding_window_pattern": 6, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.50.0", | |
| "use_cache": true, | |
| "vocab_size": 262144 | |
| } | |