| { |
| "architectures": [ |
| "RWKV07BMoEForCausalLM" |
| ], |
| "auto_map": { |
| "AutoConfig": "configuration_qwen3vlmoetext.RWKV07BMoEConfig", |
| "AutoModelForCausalLM": "modeling_qwen3vlmoetext.RWKV07BMoEForCausalLM" |
| }, |
| "description": "Hybrid-RWKV Strategically Interleaved RWKV-Attention", |
| "base_model": "Qwen/Qwen3-30B-A3B-Instruct-2507", |
| "model_revision": "alpha", |
| "transformer_layers":[0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47], |
| "rwkv_layers": [-1], |
| "rwkv_architecture": "hxa07b", |
| "enable_qk_norm": true, |
| "nope_in_transformer": true, |
| "nope_in_rwkv": false, |
| "lora_rank_decay": 256, |
| "lora_rank_iclr":128, |
| "lora_rank_value_residual_mix":96, |
| "lora_rank_key_residual_mix":96, |
| "lora_rank_gate":256, |
| "use_rope":true, |
|
|
|
|
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "bos_token_id": 151643, |
| "decoder_sparse_step": 1, |
| "eos_token_id": 151645, |
| "head_dim": 128, |
| "hidden_act": "silu", |
| "hidden_size": 2048, |
| "initializer_range": 0.02, |
| "intermediate_size": 6144, |
| "max_position_embeddings": 262144, |
| "max_window_layers": 48, |
| "mlp_only_layers": [], |
| "model_type": "rwkv07b_moe", |
| "moe_intermediate_size": 768, |
| "norm_topk_prob": true, |
| "num_attention_heads": 32, |
| "num_experts": 128, |
| "num_experts_per_tok": 8, |
| "num_hidden_layers": 48, |
| "num_key_value_heads": 4, |
| "output_router_logits": false, |
| "rms_norm_eps": 1e-06, |
| "rope_scaling": { |
| "mrope_interleaved": true, |
| "mrope_section": [ |
| 24, |
| 20, |
| 20 |
| ], |
| "rope_type": "default" |
| }, |
| "rope_theta": 10000000, |
| "router_aux_loss_coef": 0.001, |
| "sliding_window": null, |
| "tie_word_embeddings": false, |
| "torch_dtype": "bfloat16", |
| "transformers_version": "4.51.0", |
| "use_cache": true, |
| "use_sliding_window": false, |
| "vocab_size": 151936 |
| } |
