{ "model_lib": "TinyLlama-1.1b-q4f16_1", "local_id": "TinyLlama-1.1B-orca-gpt4-q4f16_1", "estimated_vram_req": 1000000000, "conv_template": "chatml", "temperature": 0.7, "repetition_penalty": 1.2, "top_p": 0.9, "mean_gen_len": 128, "max_gen_len": 512, "max_window_size": 2048, "num_shards": 1, "shift_fill_factor": 0.3, "tokenizer_files": [ "tokenizer.json", "tokenizer.model" ], "model_category": "llama", "model_name": "TinyLlama-1.1B-orca-gpt4", "vocab_size": 32000 }