{ "model_type": "llama", "hidden_size": 4096, "intermediate_size": 11008, "num_attention_heads": 32, "num_hidden_layers": 33, "rms_norm_eps": 1e-06, "bos_token_id": 1, "eos_token_id": 2, "pad_token_id": 0, "vocab_size": 32000, "layer_norm_epsilon": 1e-05, "multi_query_attention": true, "quantization_bits": null, "quantization_group_size": null, "quantization_type": 0, "unk_token": "" }