{ "_name_or_path": "LLM360/K2-Chat", "architectures": [ "LlamaForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": null, "eos_token_id": 2, "hidden_act": "silu", "hidden_size": 8192, "initializer_range": 0.02, "intermediate_size": 22016, "max_position_embeddings": 8192, "max_sequence_length": 8192, "model_type": "llama", "num_attention_heads": 64, "num_hidden_layers": 80, "num_key_value_heads": 64, "pad_token_id": 0, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 500000.0, "tie_word_embeddings": false, "torch_dtype": "float32", "transformers_version": "4.40.1", "use_cache": true, "vocab_size": 32032, "quantization_config": { "quant_method": "exl2", "version": "0.1.1", "bits": 8.0, "head_bits": 8, "calibration": { "rows": 100, "length": 2048, "dataset": "(default)" } } }