| { | |
| "architectures": [ | |
| "RWKV079Qwen3ForCausalLM" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "configuration_rwkv079qwen3.RWKV079Qwen3Config", | |
| "AutoModelForCausalLM": "modeling_rwkv079qwen3.RWKV079Qwen3ForCausalLM" | |
| }, | |
| "description": "Hybrid-RWKV Strategically Interleaved RWKV-Attention", | |
| "base_model": "ByteDance-Seed/Seed-OSS-36B-Instruct", | |
| "model_revision": "alpha", | |
| "transformer_layers":[5,11,17,23,28,33,38,43,48,53,58,63], | |
| "rwkv_layers": [0,1,2,3,4,6,7,8,9,10,12,13,14,15,16,18,19,20,21,22,24,25,26,27,29,30,31,32,34,35,36,37,39,40,41,42,44,45,46,47,49,50,51,52,54,55,56,57,59,60,61,62], | |
| "rwkv_architecture": "hxa079", | |
| "enable_qk_norm": false, | |
| "nope_in_transformer": true, | |
| "nope_in_rwkv": false, | |
| "lora_rank_decay": 448, | |
| "lora_rank_iclr":192, | |
| "lora_rank_value_residual_mix":128, | |
| "lora_rank_key_residual_mix":128, | |
| "lora_rank_gate":576, | |
| "use_rope":true, | |
| "attention_bias": true, | |
| "attention_dropout": 0.1, | |
| "attention_out_bias": false, | |
| "bos_token_id": 0, | |
| "pad_token_id": 1, | |
| "eos_token_id": 2, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 5120, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 27648, | |
| "max_position_embeddings": 524288, | |
| "mlp_bias": false, | |
| "model_type": "rwkv079qwen3", | |
| "num_attention_heads": 80, | |
| "num_hidden_layers": 64, | |
| "num_key_value_heads": 8, | |
| "residual_dropout": 0.1, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": { | |
| "rope_type": "default" | |
| }, | |
| "rope_theta": 10000000.0, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.55.0", | |
| "use_cache": true, | |
| "vocab_size": 155136 | |
| } |