Naira

Just in case you're new and currently using a latest version of Keras and it is not still working after following @edchepen and @paulelvers , downgrade you Keras version to...

EDIT 2: https://github.com/xtekky/gpt4free/issues/153 - The use of phind.com is now forbidden EDIT 1: This is just a band-aid solution to make it work. Also, please keep in mind that the...

> @jarvisar Thank you, and you're right. But after trying several times, the similar errors still occur and you must gain cf_clearance and copy it. It doesn't seem very convenient....

Hi, @GeoffMillerAZ this is amazing, I've been trying to make this work since yesterday, I did all of the steps provided in the video, but: 1. My port `5001` doesn't...

Hi. I also agree with @pseudotensor . Was also testing with one of our fine-tuned models (using `vllm=='0.5.4'`). For all the other models such as Llama 3, Mistral, etc. the...

> @arianyambao We also suspect issues with Llama-3.1 in vllm, as the scores are far from better than Llama-3. After finetuning it performs even worse... @jvlinsta Yup, it is very...

Hi, @deekshaVarshney were you able to solve this?

Hello, there is still an issue even with the latest builds regarding `UnslothGKDTrainer.py`... ``` 2025-03-12T14:23:46.858073966Z 🦥 Unsloth: Will patch your computer to enable 2x faster free finetuning. 2025-03-12T14:23:49.506276033Z 🦥 Unsloth...

Error still exists despite changing with different torch, cuda and docker versions...