{ "version": "0.1.0", "model_type": "llama", "quantization": "q4f16_1", "model_config": { "hidden_size": 4096, "intermediate_size": 11008, "num_attention_heads": 32, "num_hidden_layers": 6, "rms_norm_eps": 1e-06, "vocab_size": 32000, "position_embedding_base": 10000, "context_window_size": 2048, "prefill_chunk_size": 2048, "num_key_value_heads": 32, "head_dim": 128, "tensor_parallel_shards": 1, "max_batch_size": 80 }, "vocab_size": 32000, "context_window_size": 2048, "sliding_window_size": -1, "prefill_chunk_size": 2048, "attention_sink_size": -1, "tensor_parallel_shards": 1, "mean_gen_len": 128, "max_gen_len": 512, "shift_fill_factor": 0.3, "temperature": 0.6, "presence_penalty": 0.0, "frequency_penalty": 0.0, "repetition_penalty": 1.0, "top_p": 0.9, "tokenizer_files": [ "tokenizer.model", "tokenizer_config.json", "tokenizer.json" ], "tokenizer_info": { "token_postproc_method": "byte_fallback", "prepend_space_in_encode": true, "strip_space_in_decode": true }, "conv_template": { "name": "st-llm", "system_template": "Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.\n\n### Instruction:\n{MessagePlaceholders.SYSTEM.value}", "system_message": "You are a helpful, respectful and honest assistant.", "system_prefix_token_ids": null, "add_role_after_system_message": true, "roles": { "user": "### Input:", "assistant": "### Response:" }, "role_templates": { "user": "{user_message}", "assistant": "{assistant_message}", "tool": "{tool_message}" }, "messages": [], "seps": [ "" ], "role_content_sep": "\n", "role_empty_sep": "\n", "stop_str": [ "" ], "stop_token_ids": [ 2 ], "function_string": "", "use_function_calling": false }, "pad_token_id": 0, "bos_token_id": 1, "eos_token_id": 2 }