1 Issue closed by 1 person

• [Bug]: TypeError: PreTrainedTokenizerFast._batch_encode_plus() got an unexpected keyword argument 'tools'

  #244 closed Oct 16, 2024

3 Issues opened by 3 people

• [Feature Request]: 建议将finetune里的.sh文件中的--include localhost:1更改为--include localhost:0

  #255 opened Oct 16, 2024

• [Feature Request]: 如果使用CPU的话，要求的CPU核数和内存大概是多大，运行4B的模型。

  #254 opened Oct 14, 2024

• [Bad Case]: error loading model architecture: unknown model architecture: 'minicpm3' time=2024-10-12T20:12:01.292+08:00 level=ERROR source=sched.go:456 msg="error loading llama server" error="llama runner process has terminated: this model is not supported by your version of Ollama. You may need to upgrade"

  #253 opened Oct 14, 2024

1 Unresolved conversation

Sometimes conversations happen on old items that aren’t yet closed. Here is a list of all the Issues and Pull Requests with unresolved conversations.

• Due to Flashattention, inference cannot be performed on v100

  #249 commented on Oct 16, 2024 • 0 new comments