{ "_name_or_path": "fla-hub/transformer-2.7B-100B", "architectures": [ "TransformerForCausalLM" ], "attention_bias": false, "bos_token_id": 1, "eos_token_id": 2, "fuse_cross_entropy": true, "fuse_norm": true, "hidden_act": "swish", "hidden_ratio": 4, "hidden_size": 2560, "initializer_range": 0.02, "intermediate_size": null, "max_position_embeddings": 2048, "model_type": "transformer", "num_heads": 20, "num_hidden_layers": 32, "rms_norm_eps": 1e-06, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.40.0.dev0", "use_cache": true, "vocab_size": 32000 }