{ "version": "0.1.0", "model_type": "llama", "quantization": "q3f16_1", "model_config": { "hidden_size": 3072, "intermediate_size": 8192, "num_attention_heads": 24, "num_hidden_layers": 28, "rms_norm_eps": 1e-05, "vocab_size": 128256, "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": 128, "tensor_parallel_shards": 1, "pipeline_parallel_stages": 1, "max_batch_size": 128 }, "vocab_size": 128256, "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.json", "tokenizer_config.json" ], "tokenizer_info": { "token_postproc_method": "byte_level", "prepend_space_in_encode": false, "strip_space_in_decode": false }, "conv_template": { "name": "chatml", "system_template": "<|im_start|>system\n{system_message}<|im_end|>\n", "system_message": "A conversation between a user and an LLM-based AI assistant. The assistant gives helpful and honest answers.", "system_prefix_token_ids": null, "add_role_after_system_message": true, "roles": { "user": "<|im_start|>user", "assistant": "<|im_start|>assistant" }, "role_templates": { "user": "{user_message}", "assistant": "{assistant_message}", "tool": "{tool_message}" }, "messages": [], "seps": [ "<|im_end|>\n" ], "role_content_sep": "\n", "role_empty_sep": "\n", "stop_str": [ "<|im_end|>" ], "stop_token_ids": [ 2 ], "function_string": "", "use_function_calling": false }, "pad_token_id": 0, "bos_token_id": 128000, "eos_token_id": 128001 }