{ "version": "0.1.0", "model_type": "llama", "quantization": "q4f16_1", "model_config": { "hidden_size": 2048, "intermediate_size": 8192, "num_attention_heads": 32, "num_hidden_layers": 16, "rms_norm_eps": 1e-05, "vocab_size": 128258, "tie_word_embeddings": true, "position_embedding_base": 500000.0, "rope_scaling": { "factor": 32.0, "high_freq_factor": 4.0, "low_freq_factor": 1.0, "original_max_position_embeddings": 8192, "rope_type": "llama3" }, "context_window_size": 131072, "prefill_chunk_size": 8192, "num_key_value_heads": 8, "head_dim": 64, "tensor_parallel_shards": 1, "pipeline_parallel_stages": 1, "max_batch_size": 128 }, "vocab_size": 128258, "context_window_size": 131072, "sliding_window_size": -1, "prefill_chunk_size": 8192, "attention_sink_size": -1, "tensor_parallel_shards": 1, "pipeline_parallel_stages": 1, "temperature": 0.6, "presence_penalty": 0.0, "frequency_penalty": 0.0, "repetition_penalty": 1.0, "top_p": 0.9, "tokenizer_files": [], "tokenizer_info": { "token_postproc_method": "byte_fallback", "prepend_space_in_encode": false, "strip_space_in_decode": false }, "conv_template": { "name": "wizard_coder_or_math", "system_template": "{system_message}", "system_message": "Below is an instruction that describes a task. Write a response that appropriately completes the request.", "system_prefix_token_ids": [ 1 ], "add_role_after_system_message": true, "roles": { "user": "Instruction", "assistant": "Response" }, "role_templates": { "user": "{user_message}", "assistant": "{assistant_message}", "tool": "{tool_message}" }, "messages": [], "seps": [ "\n\n### ", "\n\n### " ], "role_content_sep": ":\n", "role_empty_sep": ":\n", "stop_str": [ "" ], "stop_token_ids": [ 2 ], "function_string": "", "use_function_calling": false }, "pad_token_id": 128257, "bos_token_id": 128256, "eos_token_id": 128257 }