mateenah

A fully automated local fine tuning pipeline for Qwen3.8-27B. Drop your data in a folder, run one command, get a Forge your own Qwen.

look at the prices !! crazy

This might be of use

https://github.com/raiyanyahya/how-to-train-your-gpt

This is good for other competitors I guess. People rarely calculate the bump in price but the fact that price is increasing might bring them to other vendors.

This is extremely useful. Thank you so much!

I wonder if it's still good

Have you tried running really large models with this? And how are you managing allocating resources ?

I like it .. its an interesting take ...any plans of adding a on page editor ?

you have such great projects on your website! super cool

pretty cool. how are you deciding or generating puzzles ?

what a great artcle!

Are there any benchmarks comparing it to fable ?

Some good news! The plugin has been submitted to the official claude plugin directory and has been published. Will update the readme on the easier install option. Thank you for all the support.

Thank you for the encouragement. Currently there is no way to handle stale memory and I didnt think about the teammates angle...good point I will need to think about it and see if I can build something around it.

Looks good. Are you sharing context everytime or do you force it ?

would be great to have a rotate password feature. good job

This is really neat!

Subscribed!

Nice. Quick and easy read.

Looks great! Is this python ?