peanutpaste

全参微调后 调用”刷新适配器“，模型加载不出来；lora微调就可以

4

### Reminder - [X] I have read the README and searched the existing issues. ### Reproduction 全参微调后 调用”刷新适配器“，模型加载不出来；lora微调就可以 ### Expected behavior _No response_ ### System Info _No response_ ### Others...

### Reminder - [X] I have read the README and searched the existing issues. ### Reproduction 这是Qwen1.5-0.5B-Chat的模型权重  这是llama-factory框架full模式下微调后的模型权重  这是llama-factory框架lora模式下微调后的模型权重  请问下为什么微调后模型的size大小差别会这么大，0.86G，1.15G，1.72G，疑惑，望解答，谢谢 ### Expected behavior _No response_ ### System...

Import is very time -consuming: from unnersted.partition.pdf import partition_pdf

3

t1 = time.time() from unstructured.partition.pdf import partition_pdf t2 = time.time() print(t2-t1) I run this, it takes nearly 1 minute my env： cpu：13th Gen Intel(R) Core(TM) i7-13700K 3.40 GHz ram：32.0 GB...

ollama does not work continuously

1

### What is the issue? After I start the ollama service, it will freeze when I run it for a while. When I access it, it will keep loading, but...

I use pytorch2onnx.py file to convert .pt to .onnx, i want get the output of onnx type is float32,but got int64,how can i get float32,thx!