Baoqiang Cao comments

Results 10 comments of


                                            Baoqiang Cao

Doesn't work on 3B

Well, the system resolution is 480*320, just checked. It says the monitor is "Monitor: Unknown", also, I noticed at the beginning of booting, there are several GPIO failures. Everything else...

Doesn't work on 3B

I'm using Ubuntu-Mate from here: https://ubuntu-mate.org/download/ for Raspberry Pi 3B.

Doesn't work on 3B

Don't know if this helps, anyway here is the output from dmesg when the LCD35 is used: [ 0.000000] Booting Linux on physical CPU 0x0 [ 0.000000] Linux version 4.14.33-v7...

Whenever I use QLoRA to train LLama/LLama 2 on an instruction-tuning dataset like Dolly or Alpaca I get a periodically oscillating training loss

I have similar sawtooth shape loss on Alpaca data, excerpt of my training output log is here: {'loss': 1.5872, 'learning_rate': 1e-06, 'epoch': 0.01} {'loss': 1.237, 'learning_rate': 1e-06, 'epoch': 0.02} {'loss':...

Whenever I use QLoRA to train LLama/LLama 2 on an instruction-tuning dataset like Dolly or Alpaca I get a periodically oscillating training loss

Thanks @BugReporterZ ! Yes indeed, after disabled group_by_length, I don't see the sawtooth shape anymore. Appreciate @ritabratamaiti and @vincentmin as well!

No CSV or HTML results generated

A related question, how to get the bboxes for all the detected cells? It is in the return of self.det_model(), it seems in my examples, outputs['pred_boxes'].shape is always [1, 15,...

Reconstruction of table 6 from paper - Dealing with OOV words

Any progress to share please?

Used to incorporate QLoRA weights back into the base model for export to Hugging Face format.

I got the following erros: lora_model = PeftModel.from_pretrained(base_model,LORA_MODEL,device_map={"": DEVICE},torch_dtype=torch.float16) *** TypeError: __init__() got an unexpected keyword argument 'device_map' lora_model = PeftModel.from_pretrained(base_model,LORA_MODEL,torch_dtype=torch.float16) *** TypeError: __init__() got an unexpected keyword argument 'torch_dtype'...

download.sh closes without downloading anything.

same issue. Got the email at 14:10pm CT today. HTTP request sent, awaiting response... 403 Forbidden 2023-07-18 20:36:32 ERROR 403: Forbidden. Checking checksums md5sum: checklist.chk: no properly formatted MD5 checksum...

bug:导入vaq_ocr数据，

I got a similar error. The expected data structure in "OCR_VQA/dataset.json" is different from what I downloaded from the provided OCR_VQA link. Any help how to generate the needed OCR_VQA/dataset.json...