{ "architectures": [ "LlamaForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 2, "hidden_act": "silu", "hidden_size": 576, "initializer_range": 0.041666666666666664, "intermediate_size": 1536, "is_llama_config": true, "max_position_embeddings": 8192, "mlp_bias": false, "model_type": "llama", "num_attention_heads": 9, "num_hidden_layers": 30, "num_key_value_heads": 3, "pad_token_id": 2, "pretraining_tp": 1, "quantization": { "group_size": 64, "bits": 8 }, "quantization_config": { "group_size": 64, "bits": 8 }, "rms_norm_eps": 1e-05, "rope_interleaved": false, "rope_scaling": null, "rope_theta": 100000, "tie_word_embeddings": true, "torch_dtype": "bfloat16", "transformers.js_config": { "kv_cache_dtype": { "q4f16": "float16", "fp16": "float16" } }, "transformers_version": "4.42.3", "use_cache": true, "vocab_size": 49152 }