Nghi D. Q. Bui

thank you. The RWKV model family looks very nice. However, they are not really code learning models, do you have the checkpoints related to coding tasks?

yes, the starcoder model has been sharded into multiple files already, so I recommend do not use weight_sharding for starcoder.

we will release a new stable version very soon to fix all of these bugs, thanks for updating us the issues !!

hello, can you sign the salesforce-cla before making the pull request, thanks !!

you can use CodeTF to fine-tune with PEFT/LORA: https://github.com/salesforce/CodeTF

i'm not very sure, can your dataset be converted into some sequence format?

this is great, can you help to propose any pull request that i can merge?

thanks!!! I will update my result later

hi, not sure if you are still interested, but i have just updated the code with clearer instructions and results