| { | |
| "_name_or_path": "/mnt/program/wlx_data/experiments/language-1022/rwkv-1b6/iter_745524.hf", | |
| "architectures": [ | |
| "Rwkv6ForCausalLM" | |
| ], | |
| "attention_hidden_size": 2048, | |
| "auto_map": { | |
| "AutoConfig": "configuration_rwkv6.Rwkv6Config", | |
| "AutoModelForCausalLM": "modeling_rwkv6.Rwkv6ForCausalLM" | |
| }, | |
| "bos_token_id": 0, | |
| "eos_token_id": 0, | |
| "head_size": 64, | |
| "head_size_divisor": 8, | |
| "hidden_size": 2048, | |
| "intermediate_size": null, | |
| "layer_norm_epsilon": 1e-05, | |
| "model_type": "rwkv6", | |
| "num_attention_heads": 64, | |
| "num_hidden_layers": 24, | |
| "rescale_every": 6, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "float16", | |
| "transformers_version": "4.39.2", | |
| "use_cache": true, | |
| "vocab_size": 65536 | |
| } | |