config_old.json

{
  "architectures": [
    "RWKV07AQwen3ForCausalLM"
  ],
  "auto_map": {
      "AutoConfig": "configuration_rwkv07aqwen3.RWKV07AQwen3Config",
      "AutoModelForCausalLM": "modeling_rwkv07aqwen3.RWKV07AQwen3ForCausalLM"
  },
  "description": "Hybrid-RWKV Strategically Interleaved RWKV-Attention",
  "base_model": "ByteDance-Seed/Seed-OSS-36B-Instruct",
  "model_revision": "alpha",
  "transformer_layers":[3,7,11,15,19,23,27,31,35],
  "rwkv_layers": [0,1,2,4,5,6,8,9,10,12,13,14,16,17,18,20,21,22,24,25,26,28,29,30,32,33,34],
  "rwkv_architecture": "hxa07a",
  "enable_qk_norm": true,
  "nope_in_transformer": true,
  "nope_in_rwkv": false,
  "lora_rank_decay": 256,
  "lora_rank_iclr":96,
  "lora_rank_gate":256,
  "use_rope":true,

    
  "attention_bias": false,
  "attention_out_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 151643,
  "eos_token_id": 151645,
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 12288,
  "max_position_embeddings": 131072,
  "max_window_layers": 36,
  "model_type": "rwkv07aqwen3",
  "num_attention_heads": 32,
  "num_hidden_layers": 36,
  "num_key_value_heads": 8,
  "rms_norm_eps": 1e-06,
  "rope_scaling": null,
  "rope_theta": 5000000,
  "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
}