low_rank_adapter_finetuning

two different versions of using PEFT to finetune a model on low-rank adaptors

instructional_finetuning

finetuning a model using an instructional method

finetuning hugging face

finetuning a hugging face model

finetuning llama2

skeleton code for finetuning llama2

fast finetuning llama2

a fast and steamlined way to finetune llama2

instructional finetuning falcon

https://wandb.ai/jaeson/huggingface/runs/el5rg1px/

finetuned bloom 3b model with instrustional lora

https://huggingface.co/jbb/squidsquad/commit/a2298ba1a9ca0d27c38a50e6a1f48e83518d1403

finetuned stable difussion on my own avatars

https://huggingface.co/jbb/jsonbot v2, higher-res: https://huggingface.co/jbb/jsonbotv2

finetuned code llama for coq formalizer

https://huggingface.co/jbb/llama_coq