{ "_name_or_path": "sdprompt-retnet-300m", "activation_dropout": 0.0, "activation_fn": "swish", "architectures": [ "RetNetForCausalLM" ], "auto_map": { "AutoConfig": "configuration_retnet.RetNetConfig", "AutoModelForCausalLM": "modeling_retnet.RetNetForCausalLM" }, "bos_token_id": 1, "decoder_embed_dim": 1280, "decoder_ffn_embed_dim": 2560, "decoder_layers": 12, "decoder_normalize_before": true, "decoder_retention_heads": 8, "decoder_value_embed_dim": 2560, "deepnorm": false, "drop_path_rate": 0.0, "dropout": 0.0, "eos_token_id": 2, "forward_impl": "parallel", "initializer_range": 0.02, "is_decoder": true, "layernorm_embedding": true, "layernorm_eps": 1e-06, "model_type": "retnet", "no_scale_embedding": false, "output_retentions": false, "pad_token_id": 33619, "recurrent_chunk_size": 512, "subln": true, "tie_word_embeddings": false, "torch_dtype": "float32", "transformers_version": "4.34.1", "use_cache": true, "use_ffn_rms_norm": false, "use_glu": true, "use_lm_decay": false, "vocab_size": 33620, "z_loss_coeff": 0.0 }