April

Results 4 comments of April

/workspace/models/damo/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-onnx is not registered

> 请问是怎么解决的呀 我这边发现使用下载到 容器挂载文件夹 中的模型就会报错这个，但是/root/.cache中的模型是可以使用的，我的命令是这样的 python server.py \ --host 0.0.0.0 \ --port 8000 \ --asr_model /root/.cache/modelscope/hub/models/iic/speech_seaco_paraformer_large_asr_nat-zh-cn-16k-common-vocab8404-pytorch \ --vad_model /root/.cache/modelscope/hub/models/iic/speech_fsmn_vad_zh-cn-16k-common-pytorch \ --punc_model /root/.cache/modelscope/hub/models/iic/punc_ct-transformer_zh-cn-common-vocab272727-pytorch

使用8*v100 Qwen2.5-VL-72B-Instruct启动报错

同遇到这个问题，请问解决了吗

When configuring the Ollama text embedding model in the model provider, a HTTPSConnectionPool(host='openaipublic.blob.core.windows.net', port=443): Max retries exceeded with url: /gpt-2/encodings/main/vocab.bpe occurred.

> Hello [@dong6255](https://github.com/dong6255)! I'm here to assist you with any bugs, questions, or contributions you have for the Dify application. I can help you solve issues and provide guidance while...

When configuring the Ollama text embedding model in the model provider, a HTTPSConnectionPool(host='openaipublic.blob.core.windows.net', port=443): Max retries exceeded with url: /gpt-2/encodings/main/vocab.bpe occurred.

> Hello [@dong6255](https://github.com/dong6255)! Got same problem. IMO, this issue applies to tiktoken, not dify. To fix it I found this [reply](https://stackoverflow.com/a/76107077). Note, need to do steps also for encoder.json file.你好！遇到了同样的问题。在我看来，这个问题适用于...