{ "architectures": [ "BitLlamaForCausalLM" ], "auto_map": { "AutoConfig": "configuration_bitllama.LlamaConfig", "AutoModelForCausalLM": "modeling_bitllama.BitLlamaForCausalLM" }, "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 2, "hidden_act": "silu", "hidden_size": 512, "initializer_range": 0.02, "intermediate_size": 1365, "max_position_embeddings": 32000, "model_type": "llama", "num_attention_heads": 8, "num_hidden_layers": 12, "num_key_value_heads": 4, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 100000.0, "tie_word_embeddings": true, "torch_dtype": "float32", "transformers_version": "4.36.0", "use_cache": true, "vocab_size": 32000 }