| { | |
| "activation_dropout": 0.1, | |
| "activation_fn": "swish", | |
| "architectures": [ | |
| "RetNetForCausalLM" | |
| ], | |
| "decoder_embed_dim": 256, | |
| "decoder_ffn_embed_dim": 432, | |
| "decoder_layers": 3, | |
| "decoder_normalize_before": true, | |
| "decoder_retention_heads": 2, | |
| "decoder_value_embed_dim": 432, | |
| "deepnorm": false, | |
| "drop_path_rate": 0.1, | |
| "dropout": 0.1, | |
| "eos_token_id": 50256, | |
| "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": 50257, | |
| "recurrent_chunk_size": 256, | |
| "subln": true, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.35.0", | |
| "use_cache": true, | |
| "use_ffn_rms_norm": false, | |
| "use_glu": true, | |
| "use_lm_decay": false, | |
| "vocab_size": 50259, | |
| "z_loss_coeff": 0.0 | |
| } | |