{ "architectures": [ "LlamaForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128001, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 8192, "model_type": "llama", "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 500000.0, "tie_word_embeddings": false, "torch_dtype": "float16", "transformers_version": "4.40.0.dev0", "use_cache": true, "vocab_size": 128256, "quantization_config": { "quant_method": "exl2", "version": "0.0.20", "bits": 5.0, "head_bits": 6, "calibration": { "rows": 100, "length": 2048, "dataset": "(default)" } } }