[BUG]AutoDL镜像推理报错 Exception in thread Thread-2

[klx1204]

用的fish-speech 1.1的官方镜像。 没有微调lora，代码块内容：

#将xxxxxx.ckpt改为你想要推理的模型
#可能需要等一两分钟分钟
%cd ~/autodl-tmp/workdir/fish-speech
!python -m tools.webui \
    --llama-config-name dual_ar_2_codebook_large \
    --decoder-checkpoint-path "output/vits_decoder/step_000005000.ckpt" \
    --decoder-config-name vits_decoder_finetune \
    --compile

输出

/root/autodl-tmp/workdir/fish-speech
2024-07-06 22:31:23.140 | INFO     | __main__:<module>:436 - Loading Llama model...
Exception in thread Thread-2 (worker):
Traceback (most recent call last):
  File "/root/miniconda3/lib/python3.10/threading.py", line 1016, in _bootstrap_inner
    self.run()
  File "/root/miniconda3/lib/python3.10/threading.py", line 953, in run
    self._target(*self._args, **self._kwargs)
  File "/root/autodl-tmp/workdir/fish-speech/tools/llama/generate.py", line 625, in worker
    model, decode_one_token = load_model(
  File "/root/autodl-tmp/workdir/fish-speech/tools/llama/generate.py", line 398, in load_model
    model.load_state_dict(checkpoint, assign=True)
  File "/root/miniconda3/lib/python3.10/site-packages/torch/nn/modules/module.py", line 2152, in load_state_dict
    raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format(
RuntimeError: Error(s) in loading state_dict for DualARTransformer:
    Missing key(s) in state_dict: "layers.24.attention.wqkv.weight", "layers.24.attention.wo.weight", "layers.24.feed_forward.w1.weight", "layers.24.feed_forward.w3.weight", "layers.24.feed_forward.w2.weight", "layers.24.ffn_norm.weight", "layers.24.attention_norm.weight", "layers.25.attention.wqkv.weight", "layers.25.attention.wo.weight", "layers.25.feed_forward.w1.weight", "layers.25.feed_forward.w3.weight", "layers.25.feed_forward.w2.weight", "layers.25.ffn_norm.weight", "layers.25.attention_norm.weight", "layers.26.attention.wqkv.weight", "layers.26.attention.wo.weight", "layers.26.feed_forward.w1.weight", "layers.26.feed_forward.w3.weight", "layers.26.feed_forward.w2.weight", "layers.26.ffn_norm.weight", "layers.26.attention_norm.weight", "layers.27.attention.wqkv.weight", "layers.27.attention.wo.weight", "layers.27.feed_forward.w1.weight", "layers.27.feed_forward.w3.weight", "layers.27.feed_forward.w2.weight", "layers.27.ffn_norm.weight", "layers.27.attention_norm.weight", "layers.28.attention.wqkv.weight", "layers.28.attention.wo.weight", "layers.28.feed_forward.w1.weight", "layers.28.feed_forward.w3.weight", "layers.28.feed_forward.w2.weight", "layers.28.ffn_norm.weight", "layers.28.attention_norm.weight", "layers.29.attention.wqkv.weight", "layers.29.attention.wo.weight", "layers.29.feed_forward.w1.weight", "layers.29.feed_forward.w3.weight", "layers.29.feed_forward.w2.weight", "layers.29.ffn_norm.weight", "layers.29.attention_norm.weight". 
    size mismatch for embeddings.weight: copying a param with shape torch.Size([2328, 1024]) from checkpoint, the shape in current model is torch.Size([2328, 1536]).
    size mismatch for layers.0.attention.wqkv.weight: copying a param with shape torch.Size([3072, 1024]) from checkpoint, the shape in current model is torch.Size([4608, 1536]).
    size mismatch for layers.0.attention.wo.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([1536, 1536]).
    size mismatch for layers.0.feed_forward.w1.weight: copying a param with shape torch.Size([2816, 1024]) from checkpoint, the shape in current model is torch.Size([4096, 1536]).
    size mismatch for layers.0.feed_forward.w3.weight: copying a param with shape torch.Size([2816, 1024]) from checkpoint, the shape in current model is torch.Size([4096, 1536]).
    size mismatch for layers.0.feed_forward.w2.weight: copying a param with shape torch.Size([1024, 2816]) from checkpoint, the shape in current model is torch.Size([1536, 4096]).
    size mismatch for layers.0.ffn_norm.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([1536]).
    size mismatch for layers.0.attention_norm.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([1536]).
    size mismatch for layers.1.attention.wqkv.weight: copying a param with shape torch.Size([3072, 1024]) from checkpoint, the shape in current model is torch.Size([4608, 1536]).
    size mismatch for layers.1.attention.wo.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([1536, 1536]).
    size mismatch for layers.1.feed_forward.w1.weight: copying a param with shape torch.Size([2816, 1024]) from checkpoint, the shape in current model is torch.Size([4096, 1536]).
    size mismatch for layers.1.feed_forward.w3.weight: copying a param with shape torch.Size([2816, 1024]) from checkpoint, the shape in current model is torch.Size([4096, 1536]).
    size mismatch for layers.1.feed_forward.w2.weight: copying a param with shape torch.Size([1024, 2816]) from checkpoint, the shape in current model is torch.Size([1536, 4096]).
    size mismatch for layers.1.ffn_norm.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([1536]).
    size mismatch for layers.1.attention_norm.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([1536]).
    size mismatch for layers.2.attention.wqkv.weight: copying a param with shape torch.Size([3072, 1024]) from checkpoint, the shape in current model is torch.Size([4608, 1536]).
    size mismatch for layers.2.attention.wo.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([1536, 1536]).
    size mismatch for layers.2.feed_forward.w1.weight: copying a param with shape torch.Size([2816, 1024]) from checkpoint, the shape in current model is torch.Size([4096, 1536]).
    size mismatch for layers.2.feed_forward.w3.weight: copying a param with shape torch.Size([2816, 1024]) from checkpoint, the shape in current model is torch.Size([4096, 1536]).
    size mismatch for layers.2.feed_forward.w2.weight: copying a param with shape torch.Size([1024, 2816]) from checkpoint, the shape in current model is torch.Size([1536, 4096]).
    size mismatch for layers.2.ffn_norm.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([1536]).
    size mismatch for layers.2.attention_norm.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([1536]).
    size mismatch for layers.3.attention.wqkv.weight: copying a param with shape torch.Size([3072, 1024]) from checkpoint, the shape in current model is torch.Size([4608, 1536]).
    size mismatch for layers.3.attention.wo.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([1536, 1536]).
    size mismatch for layers.3.feed_forward.w1.weight: copying a param with shape torch.Size([2816, 1024]) from checkpoint, the shape in current model is torch.Size([4096, 1536]).
    size mismatch for layers.3.feed_forward.w3.weight: copying a param with shape torch.Size([2816, 1024]) from checkpoint, the shape in current model is torch.Size([4096, 1536]).
    size mismatch for layers.3.feed_forward.w2.weight: copying a param with shape torch.Size([1024, 2816]) from checkpoint, the shape in current model is torch.Size([1536, 4096]).
    size mismatch for layers.3.ffn_norm.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([1536]).
    size mismatch for layers.3.attention_norm.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([1536]).
    size mismatch for layers.4.attention.wqkv.weight: copying a param with shape torch.Size([3072, 1024]) from checkpoint, the shape in current model is torch.Size([4608, 1536]).
    size mismatch for layers.4.attention.wo.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([1536, 1536]).
    size mismatch for layers.4.feed_forward.w1.weight: copying a param with shape torch.Size([2816, 1024]) from checkpoint, the shape in current model is torch.Size([4096, 1536]).
    size mismatch for layers.4.feed_forward.w3.weight: copying a param with shape torch.Size([2816, 1024]) from checkpoint, the shape in current model is torch.Size([4096, 1536]).
    size mismatch for layers.4.feed_forward.w2.weight: copying a param with shape torch.Size([1024, 2816]) from checkpoint, the shape in current model is torch.Size([1536, 4096]).
    size mismatch for layers.4.ffn_norm.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([1536]).
    size mismatch for layers.4.attention_norm.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([1536]).
    size mismatch for layers.5.attention.wqkv.weight: copying a param with shape torch.Size([3072, 1024]) from checkpoint, the shape in current model is torch.Size([4608, 1536]).
    size mismatch for layers.5.attention.wo.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([1536, 1536]).
    size mismatch for layers.5.feed_forward.w1.weight: copying a param with shape torch.Size([2816, 1024]) from checkpoint, the shape in current model is torch.Size([4096, 1536]).
    size mismatch for layers.5.feed_forward.w3.weight: copying a param with shape torch.Size([2816, 1024]) from checkpoint, the shape in current model is torch.Size([4096, 1536]).
    size mismatch for layers.5.feed_forward.w2.weight: copying a param with shape torch.Size([1024, 2816]) from checkpoint, the shape in current model is torch.Size([1536, 4096]).
    size mismatch for layers.5.ffn_norm.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([1536]).
    size mismatch for layers.5.attention_norm.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([1536]).
    size mismatch for layers.6.attention.wqkv.weight: copying a param with shape torch.Size([3072, 1024]) from checkpoint, the shape in current model is torch.Size([4608, 1536]).
    size mismatch for layers.6.attention.wo.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([1536, 1536]).
    size mismatch for layers.6.feed_forward.w1.weight: copying a param with shape torch.Size([2816, 1024]) from checkpoint, the shape in current model is torch.Size([4096, 1536]).
    size mismatch for layers.6.feed_forward.w3.weight: copying a param with shape torch.Size([2816, 1024]) from checkpoint, the shape in current model is torch.Size([4096, 1536]).
    size mismatch for layers.6.feed_forward.w2.weight: copying a param with shape torch.Size([1024, 2816]) from checkpoint, the shape in current model is torch.Size([1536, 4096]).
    size mismatch for layers.6.ffn_norm.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([1536]).
    size mismatch for layers.6.attention_norm.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([1536]).
    size mismatch for layers.7.attention.wqkv.weight: copying a param with shape torch.Size([3072, 1024]) from checkpoint, the shape in current model is torch.Size([4608, 1536]).
    size mismatch for layers.7.attention.wo.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([1536, 1536]).
    size mismatch for layers.7.feed_forward.w1.weight: copying a param with shape torch.Size([2816, 1024]) from checkpoint, the shape in current model is torch.Size([4096, 1536]).
    size mismatch for layers.7.feed_forward.w3.weight: copying a param with shape torch.Size([2816, 1024]) from checkpoint, the shape in current model is torch.Size([4096, 1536]).
    size mismatch for layers.7.feed_forward.w2.weight: copying a param with shape torch.Size([1024, 2816]) from checkpoint, the shape in current model is torch.Size([1536, 4096]).
    size mismatch for layers.7.ffn_norm.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([1536]).
    size mismatch for layers.7.attention_norm.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([1536]).
    size mismatch for layers.8.attention.wqkv.weight: copying a param with shape torch.Size([3072, 1024]) from checkpoint, the shape in current model is torch.Size([4608, 1536]).
    size mismatch for layers.8.attention.wo.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([1536, 1536]).
    size mismatch for layers.8.feed_forward.w1.weight: copying a param with shape torch.Size([2816, 1024]) from checkpoint, the shape in current model is torch.Size([4096, 1536]).
    size mismatch for layers.8.feed_forward.w3.weight: copying a param with shape torch.Size([2816, 1024]) from checkpoint, the shape in current model is torch.Size([4096, 1536]).
    size mismatch for layers.8.feed_forward.w2.weight: copying a param with shape torch.Size([1024, 2816]) from checkpoint, the shape in current model is torch.Size([1536, 4096]).
    size mismatch for layers.8.ffn_norm.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([1536]).
    size mismatch for layers.8.attention_norm.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([1536]).
    size mismatch for layers.9.attention.wqkv.weight: copying a param with shape torch.Size([3072, 1024]) from checkpoint, the shape in current model is torch.Size([4608, 1536]).
    size mismatch for layers.9.attention.wo.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([1536, 1536]).
    size mismatch for layers.9.feed_forward.w1.weight: copying a param with shape torch.Size([2816, 1024]) from checkpoint, the shape in current model is torch.Size([4096, 1536]).
    size mismatch for layers.9.feed_forward.w3.weight: copying a param with shape torch.Size([2816, 1024]) from checkpoint, the shape in current model is torch.Size([4096, 1536]).
    size mismatch for layers.9.feed_forward.w2.weight: copying a param with shape torch.Size([1024, 2816]) from checkpoint, the shape in current model is torch.Size([1536, 4096]).
    size mismatch for layers.9.ffn_norm.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([1536]).
    size mismatch for layers.9.attention_norm.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([1536]).
    size mismatch for layers.10.attention.wqkv.weight: copying a param with shape torch.Size([3072, 1024]) from checkpoint, the shape in current model is torch.Size([4608, 1536]).
    size mismatch for layers.10.attention.wo.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([1536, 1536]).
    size mismatch for layers.10.feed_forward.w1.weight: copying a param with shape torch.Size([2816, 1024]) from checkpoint, the shape in current model is torch.Size([4096, 1536]).
    size mismatch for layers.10.feed_forward.w3.weight: copying a param with shape torch.Size([2816, 1024]) from checkpoint, the shape in current model is torch.Size([4096, 1536]).
    size mismatch for layers.10.feed_forward.w2.weight: copying a param with shape torch.Size([1024, 2816]) from checkpoint, the shape in current model is torch.Size([1536, 4096]).
    size mismatch for layers.10.ffn_norm.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([1536]).
    size mismatch for layers.10.attention_norm.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([1536]).
    size mismatch for layers.11.attention.wqkv.weight: copying a param with shape torch.Size([3072, 1024]) from checkpoint, the shape in current model is torch.Size([4608, 1536]).
    size mismatch for layers.11.attention.wo.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([1536, 1536]).
    size mismatch for layers.11.feed_forward.w1.weight: copying a param with shape torch.Size([2816, 1024]) from checkpoint, the shape in current model is torch.Size([4096, 1536]).
    size mismatch for layers.11.feed_forward.w3.weight: copying a param with shape torch.Size([2816, 1024]) from checkpoint, the shape in current model is torch.Size([4096, 1536]).
    size mismatch for layers.11.feed_forward.w2.weight: copying a param with shape torch.Size([1024, 2816]) from checkpoint, the shape in current model is torch.Size([1536, 4096]).
    size mismatch for layers.11.ffn_norm.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([1536]).
    size mismatch for layers.11.attention_norm.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([1536]).
    size mismatch for layers.12.attention.wqkv.weight: copying a param with shape torch.Size([3072, 1024]) from checkpoint, the shape in current model is torch.Size([4608, 1536]).
    size mismatch for layers.12.attention.wo.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([1536, 1536]).
    size mismatch for layers.12.feed_forward.w1.weight: copying a param with shape torch.Size([2816, 1024]) from checkpoint, the shape in current model is torch.Size([4096, 1536]).
    size mismatch for layers.12.feed_forward.w3.weight: copying a param with shape torch.Size([2816, 1024]) from checkpoint, the shape in current model is torch.Size([4096, 1536]).
    size mismatch for layers.12.feed_forward.w2.weight: copying a param with shape torch.Size([1024, 2816]) from checkpoint, the shape in current model is torch.Size([1536, 4096]).
    size mismatch for layers.12.ffn_norm.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([1536]).
    size mismatch for layers.12.attention_norm.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([1536]).
    size mismatch for layers.13.attention.wqkv.weight: copying a param with shape torch.Size([3072, 1024]) from checkpoint, the shape in current model is torch.Size([4608, 1536]).
    size mismatch for layers.13.attention.wo.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([1536, 1536]).
    size mismatch for layers.13.feed_forward.w1.weight: copying a param with shape torch.Size([2816, 1024]) from checkpoint, the shape in current model is torch.Size([4096, 1536]).
    size mismatch for layers.13.feed_forward.w3.weight: copying a param with shape torch.Size([2816, 1024]) from checkpoint, the shape in current model is torch.Size([4096, 1536]).
    size mismatch for layers.13.feed_forward.w2.weight: copying a param with shape torch.Size([1024, 2816]) from checkpoint, the shape in current model is torch.Size([1536, 4096]).
    size mismatch for layers.13.ffn_norm.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([1536]).
    size mismatch for layers.13.attention_norm.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([1536]).
    size mismatch for layers.14.attention.wqkv.weight: copying a param with shape torch.Size([3072, 1024]) from checkpoint, the shape in current model is torch.Size([4608, 1536]).
    size mismatch for layers.14.attention.wo.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([1536, 1536]).
    size mismatch for layers.14.feed_forward.w1.weight: copying a param with shape torch.Size([2816, 1024]) from checkpoint, the shape in current model is torch.Size([4096, 1536]).
    size mismatch for layers.14.feed_forward.w3.weight: copying a param with shape torch.Size([2816, 1024]) from checkpoint, the shape in current model is torch.Size([4096, 1536]).
    size mismatch for layers.14.feed_forward.w2.weight: copying a param with shape torch.Size([1024, 2816]) from checkpoint, the shape in current model is torch.Size([1536, 4096]).
    size mismatch for layers.14.ffn_norm.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([1536]).
    size mismatch for layers.14.attention_norm.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([1536]).
    size mismatch for layers.15.attention.wqkv.weight: copying a param with shape torch.Size([3072, 1024]) from checkpoint, the shape in current model is torch.Size([4608, 1536]).
    size mismatch for layers.15.attention.wo.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([1536, 1536]).
    size mismatch for layers.15.feed_forward.w1.weight: copying a param with shape torch.Size([2816, 1024]) from checkpoint, the shape in current model is torch.Size([4096, 1536]).
    size mismatch for layers.15.feed_forward.w3.weight: copying a param with shape torch.Size([2816, 1024]) from checkpoint, the shape in current model is torch.Size([4096, 1536]).
    size mismatch for layers.15.feed_forward.w2.weight: copying a param with shape torch.Size([1024, 2816]) from checkpoint, the shape in current model is torch.Size([1536, 4096]).
    size mismatch for layers.15.ffn_norm.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([1536]).
    size mismatch for layers.15.attention_norm.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([1536]).
    size mismatch for layers.16.attention.wqkv.weight: copying a param with shape torch.Size([3072, 1024]) from checkpoint, the shape in current model is torch.Size([4608, 1536]).
    size mismatch for layers.16.attention.wo.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([1536, 1536]).
    size mismatch for layers.16.feed_forward.w1.weight: copying a param with shape torch.Size([2816, 1024]) from checkpoint, the shape in current model is torch.Size([4096, 1536]).
    size mismatch for layers.16.feed_forward.w3.weight: copying a param with shape torch.Size([2816, 1024]) from checkpoint, the shape in current model is torch.Size([4096, 1536]).
    size mismatch for layers.16.feed_forward.w2.weight: copying a param with shape torch.Size([1024, 2816]) from checkpoint, the shape in current model is torch.Size([1536, 4096]).
    size mismatch for layers.16.ffn_norm.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([1536]).
    size mismatch for layers.16.attention_norm.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([1536]).
    size mismatch for layers.17.attention.wqkv.weight: copying a param with shape torch.Size([3072, 1024]) from checkpoint, the shape in current model is torch.Size([4608, 1536]).
    size mismatch for layers.17.attention.wo.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([1536, 1536]).
    size mismatch for layers.17.feed_forward.w1.weight: copying a param with shape torch.Size([2816, 1024]) from checkpoint, the shape in current model is torch.Size([4096, 1536]).
    size mismatch for layers.17.feed_forward.w3.weight: copying a param with shape torch.Size([2816, 1024]) from checkpoint, the shape in current model is torch.Size([4096, 1536]).
    size mismatch for layers.17.feed_forward.w2.weight: copying a param with shape torch.Size([1024, 2816]) from checkpoint, the shape in current model is torch.Size([1536, 4096]).
    size mismatch for layers.17.ffn_norm.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([1536]).
    size mismatch for layers.17.attention_norm.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([1536]).
    size mismatch for layers.18.attention.wqkv.weight: copying a param with shape torch.Size([3072, 1024]) from checkpoint, the shape in current model is torch.Size([4608, 1536]).
    size mismatch for layers.18.attention.wo.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([1536, 1536]).
    size mismatch for layers.18.feed_forward.w1.weight: copying a param with shape torch.Size([2816, 1024]) from checkpoint, the shape in current model is torch.Size([4096, 1536]).
    size mismatch for layers.18.feed_forward.w3.weight: copying a param with shape torch.Size([2816, 1024]) from checkpoint, the shape in current model is torch.Size([4096, 1536]).
    size mismatch for layers.18.feed_forward.w2.weight: copying a param with shape torch.Size([1024, 2816]) from checkpoint, the shape in current model is torch.Size([1536, 4096]).
    size mismatch for layers.18.ffn_norm.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([1536]).
    size mismatch for layers.18.attention_norm.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([1536]).
    size mismatch for layers.19.attention.wqkv.weight: copying a param with shape torch.Size([3072, 1024]) from checkpoint, the shape in current model is torch.Size([4608, 1536]).
    size mismatch for layers.19.attention.wo.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([1536, 1536]).
    size mismatch for layers.19.feed_forward.w1.weight: copying a param with shape torch.Size([2816, 1024]) from checkpoint, the shape in current model is torch.Size([4096, 1536]).
    size mismatch for layers.19.feed_forward.w3.weight: copying a param with shape torch.Size([2816, 1024]) from checkpoint, the shape in current model is torch.Size([4096, 1536]).
    size mismatch for layers.19.feed_forward.w2.weight: copying a param with shape torch.Size([1024, 2816]) from checkpoint, the shape in current model is torch.Size([1536, 4096]).
    size mismatch for layers.19.ffn_norm.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([1536]).
    size mismatch for layers.19.attention_norm.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([1536]).
    size mismatch for layers.20.attention.wqkv.weight: copying a param with shape torch.Size([3072, 1024]) from checkpoint, the shape in current model is torch.Size([4608, 1536]).
    size mismatch for layers.20.attention.wo.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([1536, 1536]).
    size mismatch for layers.20.feed_forward.w1.weight: copying a param with shape torch.Size([2816, 1024]) from checkpoint, the shape in current model is torch.Size([4096, 1536]).
    size mismatch for layers.20.feed_forward.w3.weight: copying a param with shape torch.Size([2816, 1024]) from checkpoint, the shape in current model is torch.Size([4096, 1536]).
    size mismatch for layers.20.feed_forward.w2.weight: copying a param with shape torch.Size([1024, 2816]) from checkpoint, the shape in current model is torch.Size([1536, 4096]).
    size mismatch for layers.20.ffn_norm.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([1536]).
    size mismatch for layers.20.attention_norm.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([1536]).
    size mismatch for layers.21.attention.wqkv.weight: copying a param with shape torch.Size([3072, 1024]) from checkpoint, the shape in current model is torch.Size([4608, 1536]).
    size mismatch for layers.21.attention.wo.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([1536, 1536]).
    size mismatch for layers.21.feed_forward.w1.weight: copying a param with shape torch.Size([2816, 1024]) from checkpoint, the shape in current model is torch.Size([4096, 1536]).
    size mismatch for layers.21.feed_forward.w3.weight: copying a param with shape torch.Size([2816, 1024]) from checkpoint, the shape in current model is torch.Size([4096, 1536]).
    size mismatch for layers.21.feed_forward.w2.weight: copying a param with shape torch.Size([1024, 2816]) from checkpoint, the shape in current model is torch.Size([1536, 4096]).
    size mismatch for layers.21.ffn_norm.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([1536]).
    size mismatch for layers.21.attention_norm.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([1536]).
    size mismatch for layers.22.attention.wqkv.weight: copying a param with shape torch.Size([3072, 1024]) from checkpoint, the shape in current model is torch.Size([4608, 1536]).
    size mismatch for layers.22.attention.wo.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([1536, 1536]).
    size mismatch for layers.22.feed_forward.w1.weight: copying a param with shape torch.Size([2816, 1024]) from checkpoint, the shape in current model is torch.Size([4096, 1536]).
    size mismatch for layers.22.feed_forward.w3.weight: copying a param with shape torch.Size([2816, 1024]) from checkpoint, the shape in current model is torch.Size([4096, 1536]).
    size mismatch for layers.22.feed_forward.w2.weight: copying a param with shape torch.Size([1024, 2816]) from checkpoint, the shape in current model is torch.Size([1536, 4096]).
    size mismatch for layers.22.ffn_norm.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([1536]).
    size mismatch for layers.22.attention_norm.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([1536]).
    size mismatch for layers.23.attention.wqkv.weight: copying a param with shape torch.Size([3072, 1024]) from checkpoint, the shape in current model is torch.Size([4608, 1536]).
    size mismatch for layers.23.attention.wo.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([1536, 1536]).
    size mismatch for layers.23.feed_forward.w1.weight: copying a param with shape torch.Size([2816, 1024]) from checkpoint, the shape in current model is torch.Size([4096, 1536]).
    size mismatch for layers.23.feed_forward.w3.weight: copying a param with shape torch.Size([2816, 1024]) from checkpoint, the shape in current model is torch.Size([4096, 1536]).
    size mismatch for layers.23.feed_forward.w2.weight: copying a param with shape torch.Size([1024, 2816]) from checkpoint, the shape in current model is torch.Size([1536, 4096]).
    size mismatch for layers.23.ffn_norm.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([1536]).
    size mismatch for layers.23.attention_norm.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([1536]).
    size mismatch for norm.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([1536]).
    size mismatch for output.weight: copying a param with shape torch.Size([264, 1024]) from checkpoint, the shape in current model is torch.Size([264, 1536]).
    size mismatch for fast_embeddings.weight: copying a param with shape torch.Size([1032, 1024]) from checkpoint, the shape in current model is torch.Size([1032, 1536]).
    size mismatch for fast_layers.0.attention.wqkv.weight: copying a param with shape torch.Size([3072, 1024]) from checkpoint, the shape in current model is torch.Size([4608, 1536]).
    size mismatch for fast_layers.0.attention.wo.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([1536, 1536]).
    size mismatch for fast_layers.0.feed_forward.w1.weight: copying a param with shape torch.Size([2816, 1024]) from checkpoint, the shape in current model is torch.Size([4096, 1536]).
    size mismatch for fast_layers.0.feed_forward.w3.weight: copying a param with shape torch.Size([2816, 1024]) from checkpoint, the shape in current model is torch.Size([4096, 1536]).
    size mismatch for fast_layers.0.feed_forward.w2.weight: copying a param with shape torch.Size([1024, 2816]) from checkpoint, the shape in current model is torch.Size([1536, 4096]).
    size mismatch for fast_layers.0.ffn_norm.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([1536]).
    size mismatch for fast_layers.0.attention_norm.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([1536]).
    size mismatch for fast_layers.1.attention.wqkv.weight: copying a param with shape torch.Size([3072, 1024]) from checkpoint, the shape in current model is torch.Size([4608, 1536]).
    size mismatch for fast_layers.1.attention.wo.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([1536, 1536]).
    size mismatch for fast_layers.1.feed_forward.w1.weight: copying a param with shape torch.Size([2816, 1024]) from checkpoint, the shape in current model is torch.Size([4096, 1536]).
    size mismatch for fast_layers.1.feed_forward.w3.weight: copying a param with shape torch.Size([2816, 1024]) from checkpoint, the shape in current model is torch.Size([4096, 1536]).
    size mismatch for fast_layers.1.feed_forward.w2.weight: copying a param with shape torch.Size([1024, 2816]) from checkpoint, the shape in current model is torch.Size([1536, 4096]).
    size mismatch for fast_layers.1.ffn_norm.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([1536]).
    size mismatch for fast_layers.1.attention_norm.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([1536]).
    size mismatch for fast_layers.2.attention.wqkv.weight: copying a param with shape torch.Size([3072, 1024]) from checkpoint, the shape in current model is torch.Size([4608, 1536]).
    size mismatch for fast_layers.2.attention.wo.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([1536, 1536]).
    size mismatch for fast_layers.2.feed_forward.w1.weight: copying a param with shape torch.Size([2816, 1024]) from checkpoint, the shape in current model is torch.Size([4096, 1536]).
    size mismatch for fast_layers.2.feed_forward.w3.weight: copying a param with shape torch.Size([2816, 1024]) from checkpoint, the shape in current model is torch.Size([4096, 1536]).
    size mismatch for fast_layers.2.feed_forward.w2.weight: copying a param with shape torch.Size([1024, 2816]) from checkpoint, the shape in current model is torch.Size([1536, 4096]).
    size mismatch for fast_layers.2.ffn_norm.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([1536]).
    size mismatch for fast_layers.2.attention_norm.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([1536]).
    size mismatch for fast_layers.3.attention.wqkv.weight: copying a param with shape torch.Size([3072, 1024]) from checkpoint, the shape in current model is torch.Size([4608, 1536]).
    size mismatch for fast_layers.3.attention.wo.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([1536, 1536]).
    size mismatch for fast_layers.3.feed_forward.w1.weight: copying a param with shape torch.Size([2816, 1024]) from checkpoint, the shape in current model is torch.Size([4096, 1536]).
    size mismatch for fast_layers.3.feed_forward.w3.weight: copying a param with shape torch.Size([2816, 1024]) from checkpoint, the shape in current model is torch.Size([4096, 1536]).
    size mismatch for fast_layers.3.feed_forward.w2.weight: copying a param with shape torch.Size([1024, 2816]) from checkpoint, the shape in current model is torch.Size([1536, 4096]).
    size mismatch for fast_layers.3.ffn_norm.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([1536]).
    size mismatch for fast_layers.3.attention_norm.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([1536]).
    size mismatch for fast_layers.4.attention.wqkv.weight: copying a param with shape torch.Size([3072, 1024]) from checkpoint, the shape in current model is torch.Size([4608, 1536]).
    size mismatch for fast_layers.4.attention.wo.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([1536, 1536]).
    size mismatch for fast_layers.4.feed_forward.w1.weight: copying a param with shape torch.Size([2816, 1024]) from checkpoint, the shape in current model is torch.Size([4096, 1536]).
    size mismatch for fast_layers.4.feed_forward.w3.weight: copying a param with shape torch.Size([2816, 1024]) from checkpoint, the shape in current model is torch.Size([4096, 1536]).
    size mismatch for fast_layers.4.feed_forward.w2.weight: copying a param with shape torch.Size([1024, 2816]) from checkpoint, the shape in current model is torch.Size([1536, 4096]).
    size mismatch for fast_layers.4.ffn_norm.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([1536]).
    size mismatch for fast_layers.4.attention_norm.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([1536]).
    size mismatch for fast_layers.5.attention.wqkv.weight: copying a param with shape torch.Size([3072, 1024]) from checkpoint, the shape in current model is torch.Size([4608, 1536]).
    size mismatch for fast_layers.5.attention.wo.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([1536, 1536]).
    size mismatch for fast_layers.5.feed_forward.w1.weight: copying a param with shape torch.Size([2816, 1024]) from checkpoint, the shape in current model is torch.Size([4096, 1536]).
    size mismatch for fast_layers.5.feed_forward.w3.weight: copying a param with shape torch.Size([2816, 1024]) from checkpoint, the shape in current model is torch.Size([4096, 1536]).
    size mismatch for fast_layers.5.feed_forward.w2.weight: copying a param with shape torch.Size([1024, 2816]) from checkpoint, the shape in current model is torch.Size([1536, 4096]).
    size mismatch for fast_layers.5.ffn_norm.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([1536]).
    size mismatch for fast_layers.5.attention_norm.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([1536]).
    size mismatch for fast_norm.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([1536]).
    size mismatch for fast_output.weight: copying a param with shape torch.Size([1032, 1024]) from checkpoint, the shape in current model is torch.Size([1032, 1536]).
^C
Traceback (most recent call last):
  File "/root/miniconda3/lib/python3.10/runpy.py", line 196, in _run_module_as_main
    return _run_code(code, main_globals, None,
  File "/root/miniconda3/lib/python3.10/runpy.py", line 86, in _run_code
    exec(code, run_globals)
  File "/root/autodl-tmp/workdir/fish-speech/tools/webui.py", line 437, in <module>
    llama_queue = launch_thread_safe_queue(
  File "/root/autodl-tmp/workdir/fish-speech/tools/llama/generate.py", line 649, in launch_thread_safe_queue
    init_event.wait()
  File "/root/miniconda3/lib/python3.10/threading.py", line 607, in wait
    signaled = self._cond.wait(timeout)
  File "/root/miniconda3/lib/python3.10/threading.py", line 320, in wait
    waiter.acquire()
KeyboardInterrupt

求助，什么原因？实在看不懂

[AnyaCoder]

%cd ~/autodl-tmp/workdir/fish-speech
!python -m tools.webui \
    --llama-config-name dual_ar_2_codebook_medium \
    --decoder-checkpoint-path "output/vits_decoder/step_000005000.ckpt" \
    --decoder-config-name vits_decoder_finetune \
    --compile

用这个