| { | |
| "_name_or_path": "KoboldAI/fairseq-dense-13B", | |
| "activation_dropout": 0.0, | |
| "activation_function": "gelu", | |
| "architectures": [ | |
| "XGLMForCausalLM" | |
| ], | |
| "attention_dropout": 0.1, | |
| "attention_heads": 40, | |
| "bos_token_id": 50257, | |
| "d_model": 5120, | |
| "decoder_start_token_id": 2, | |
| "dropout": 0.1, | |
| "eos_token_id": 50259, | |
| "ffn_dim": 20480, | |
| "init_std": 0.02, | |
| "layerdrop": 0.0, | |
| "max_position_embeddings": 2048, | |
| "model_type": "xglm", | |
| "newlinemode": "s", | |
| "num_layers": 40, | |
| "pad_token_id": 1, | |
| "scale_embedding": true, | |
| "tokenizer_class": "GPT2Tokenizer", | |
| "torch_dtype": "float16", | |
| "transformers_version": "4.18.0", | |
| "use_cache": false, | |
| "vocab_size": 50261 | |
| } | |