{ "_name_or_path": "C3TR-Adapter_merge", "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": 3072, "initializer_range": 0.02, "intermediate_size": 24576, "max_position_embeddings": 8192, "model_type": "gemma", "num_attention_heads": 16, "num_hidden_layers": 28, "num_key_value_heads": 16, "pad_token_id": 0, "quantization_config": { "bits": 4, "damp_percent": 0.1, "dataset": [ "Identify the audience for this news article\n" ], "desc_act": false, "group_size": 128, "modules_in_block_to_quantize": null, "quant_method": "gptq", "sym": true, "true_sequential": true }, "rms_norm_eps": 1e-06, "rope_scaling": null, "rope_theta": 10000.0, "torch_dtype": "bfloat16", "transformers_version": "4.40.2", "use_cache": true, "vocab_size": 256000 }