Andreas Köpf

> I had one [here](https://github.com/theblackcat102/copycat/blob/master/train_critic.py), would be glad to contribute Nice, I assigned the issue to you. Since you already trained a RM based on [bigscience/bloomz-560m](https://huggingface.co/bigscience/bloomz-560m) .. do you think...

We currently have webgpt, antrophic, summarization, xp3 and unnatural instructions as possible datasets for reward model evaluation. I suggest that we get some data for summarization first on all models....

>I will train a few variety of models and push to huggingface (if thats fine). Of course! Could you submit a PR with your training code so that we have...

> 2\. Use the dot product method between posts explained in rankgen paper to score the summaries from the SFF dataset I am not sure if the method described in...

As another reference could also take a look at the RM code by @copycat https://github.com/theblackcat102/copycat/blob/master/train_critic.py ...

> My intuition is that just doing a linear probe from the prefix or combining the prefix and suffix into a single string and projecting down from that embedding wouldn't...

I am moving this to backlog.

Closing all old discord bot issues. Discord data collection never took off. It might be more viable to develop a discord bot that communicates with the inference system.

Closing all old discord bot issues. Discord data collection never took off. It might be more viable to develop a discord bot that communicates with the inference system.

> 1. How to communicate someone is working on an issue People should first get assigned before they start working. A developer interested in working on an issues should write...