{ "_name_or_path": "fla-hub/retnet-1.3B-100B", "architectures": [ "RetNetForCausalLM" ], "attn_mode": "chunk", "bos_token_id": 1, "conv_size": 4, "elementwise_affine": true, "eos_token_id": 2, "expand_k": 1, "expand_v": 2, "feature_map": null, "fuse_cross_entropy": true, "fuse_norm": true, "hidden_act": "swish", "hidden_ratio": 2, "hidden_size": 2048, "initializer_range": 0.02, "intermediate_size": null, "max_position_embeddings": 2048, "model_type": "retnet", "norm_eps": 1e-06, "num_heads": 8, "num_hidden_layers": 24, "num_kv_heads": null, "rms_norm_eps": 1e-06, "share_conv_kernel": true, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.40.2", "use_cache": true, "use_output_gate": true, "use_short_conv": false, "vocab_size": 32000 }