Amrita Panesar

Converting mistral7b finetuned model produces garbage output

2

Hi, I've finetuned a Mistral-7B-v0.1 model from hugging face using QLoRa as per the typical SFT scripts released by the hugging face team. However, after converting it to gguf format...

Hi, I'm finding that if there are not enough columns in the data frame being output, the checkbox selection does not work - but if I add more columns, it...

Speeding up loading in inference checkpoints

2

Hi, I saw this pull request in the DeepSpeed library about snapshotting an engine to be able to load in large models faster but I couldn't see any documentation on...

[FEATURE REQUEST]

1

### Feature Request Make unsloth available for ORPO ### Motivation Would be good to be able to use unsloth with ORPO trainer as well ### Additional Context _No response_

Patch for loading config locally

1

### Issue: We were facing an issue when using detoxify in China where it would try to download the config from Hugging Face (and running into timeout issues with the...