| { | |
| "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":[3,8,14,20,25,30,35,39,43], | |
| "rwkv_layers": [0,1,2,4,5,6,7,9,10,11,12,13,15,16,17,18,19,21,22,23,24,26,27,28,29,31,32,33,34,36,37,38,40,41,42], | |
| "rwkv_architecture": "hxa07a", | |
| "enable_qk_norm": false, | |
| "nope_in_transformer": true, | |
| "nope_in_rwkv": false, | |
| "lora_rank_decay": 320, | |
| "lora_rank_iclr":96, | |
| "lora_rank_gate":320, | |
| "use_rope":true, | |
| "attention_bias": false, | |
| "attention_out_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 100257, | |
| "classifier_dropout": 0.0, | |
| "eos_token_id": 100257, | |
| "head_dim": 96, | |
| "hidden_act": "silu", | |
| "hidden_size": 6144, | |
| "id2label": { | |
| "0": "LABEL_0" | |
| }, | |
| "initializer_range": 0.006, | |
| "intermediate_size": 19648, | |
| "label2id": { | |
| "LABEL_0": 0 | |
| }, | |
| "max_position_embeddings": 98304, | |
| "mlp_bias": false, | |
| "model_type": "rwkv07aqwen3", | |
| "num_attention_heads": 64, | |
| "num_hidden_layers": 44, | |
| "num_key_value_heads": 8, | |
| "pretraining_tp": 1, | |
| "rms_norm_eps": 1e-05, | |
| "rope_scaling": null, | |
| "rope_theta": 5000000, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.50.3", | |
| "use_cache": true, | |
| "vocab_size": 100352 | |
| } | |