| { | |
| "architectures": [ | |
| "RWKV6Qwen2ForCausalLM" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "configuration_rwkv6qwen2.RWKV6Qwen2Config", | |
| "AutoModelForCausalLM": "modeling_rwkv6qwen2.RWKV6Qwen2ForCausalLM" | |
| }, | |
| "attention_bias": true, | |
| "attention_dropout": 0.0, | |
| "attention_output_bias": false, | |
| "balance_state": true, | |
| "bos_token_id": 151643, | |
| "eos_token_id": 151643, | |
| "gate_rank_type": 1, | |
| "groupnorm_att": false, | |
| "hidden_act": "silu", | |
| "hidden_size": 3584, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 18944, | |
| "lora_rank_decay": 96, | |
| "lora_rank_tokenshift": 96, | |
| "lora_rank_gate": 0, | |
| "max_position_embeddings": 131072, | |
| "max_window_layers": 28, | |
| "model_type": "rwkv6qwen2", | |
| "num_attention_heads": 28, | |
| "num_hidden_layers": 28, | |
| "num_key_value_heads": 4, | |
| "rms_norm_eps": 1e-06, | |
| "rope_theta": 1000000.0, | |
| "sliding_window": 131072, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.43.1", | |
| "use_cache": true, | |
| "use_rope": false, | |
| "use_tokenshift": true, | |
| "use_sliding_window": false, | |
| "vocab_size": 152064 | |
| } | |