Gary Mulder

[Please review and use the issue template](https://github.com/ggerganov/llama.cpp/blob/master/.github/ISSUE_TEMPLATE/custom.md?plain=1) before submitting new issues

Please review issue #239 and provide more information so we might be able to understand your problem better.

I'm not too familiar with Wandb, so I had wondered if it could handle a list of tensors. `env/reward_dist` is rendering correctly as a histogram which is what made me...

Please review and use [our issue template](https://github.com/ggerganov/llama.cpp/blob/master/.github/ISSUE_TEMPLATE/custom.md?plain=1) to provide more details so we can try and better understand your problem and attempt to answer you.

@Bloob-beep are you still having the issue with BLAS?

Closing. Reopen if the issue reoccurs.

> Here is a docker file for a cublas capable container that should bring huge speed ups for cuda gpu owners after the next sync with upstream: @jmtatsch where is...

``` $ find . -type d -exec du -hs {} \; | sort -h 30G ./7B 57G ./13B 141G ./30B 282G ./65B 507G . ``` ``` $ find . -type...

I believe `llama.ccp` is only for inference, not training. Check out [chatllama](https://github.com/nebuly-ai/nebullvm/tree/main/apps/accelerate/chatllama), but you will likely need some high-end GPUs to do RLHF. Alternatively, look at [accelerate trl](https://github.com/lvwerra/trl) for performing...

Check out thread https://github.com/ggerganov/llama.cpp/issues/23. This would allow you to have ChatGPT-type narrative conversations with the model, but is not RLHF.