{ "_name_or_path": "/tmp/tmpo4sk9l7q", "architectures": [ "GemmaForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 2, "eos_token_id": 1, "head_dim": 256, "hidden_act": "gelu", "hidden_activation": null, "hidden_size": 2048, "initializer_range": 0.02, "intermediate_size": 16384, "max_position_embeddings": 8192, "model_type": "gemma", "num_attention_heads": 8, "num_hidden_layers": 18, "num_key_value_heads": 1, "pad_token_id": 0, "quantization_config": { "bits": 4, "group_size": 128, "modules_to_not_convert": null, "quant_method": "awq", "version": "gemm", "zero_point": true }, "rms_norm_eps": 1e-06, "rope_scaling": null, "rope_theta": 10000.0, "torch_dtype": "float16", "transformers_version": "4.40.0", "use_cache": false, "vocab_size": 256000 }