{ "_name_or_path": "fla-hub/transformer-7B-mistral", "architectures": [ "TransformerForCausalLM" ], "attention_bias": false, "bos_token_id": 1, "elementwise_affine": true, "eos_token_id": 2, "fuse_cross_entropy": true, "fuse_norm": true, "hidden_act": "swish", "hidden_ratio": 4, "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 32768, "model_type": "transformer", "norm_eps": 1e-05, "num_heads": 32, "num_hidden_layers": 32, "num_kv_heads": 8, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.40.2", "use_cache": true, "vocab_size": 32000 }