{ "_name_or_path": "weights/hummingbird/hummingbird_4th_epoch_full/hummingbird", "architectures": [ "HummingbirdForCausalLM" ], "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 2, "hidden_act": "silu", "hidden_size": 3072, "initializer_range": 0.02, "intermediate_size": 8192, "max_position_embeddings": 131072, "model_type": "hummingbird", "num_attention_heads": 1, "num_hidden_layers": 10, "num_key_value_heads": 1, "rms_norm_eps": 1e-06, "rope_theta": 10000.0, "sliding_window": 3072, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.38.2", "use_cache": true, "vocab_size": 32000 }