| {"model_type": "llama", "hidden_size": 4096, "intermediate_size": 11008, "num_attention_heads": 32, "num_hidden_layers": 32, "hidden_act": "silu", "initializer_range": 0.02, "layer_norm_eps": 1e-06, "max_position_embeddings": 2048, "vocab_size": 32000, "r": 8, "lora_alpha": 32, "lora_dropout": 0.1, "task_type": "CAUSAL_LM", "pad_token_id": 0, "bos_token_id": 1, "eos_token_id": 2, "gradient_checkpointing": "false", "quantization_config": {"load_in_8bit": "true"}, "transformers_version": "4.30.0", "torch_dtype": "float16"} |