Pinned Repositories
CodecLM
An implementation of the CodecLM research by Google
dpo-temp-lamini
Evol-Instruct
An implementation of the Evol-Instruct dataset generation process in the WizardLM paper
finetuning-scripts
Instruct-tune Open LLaMA / RedPajama / StableLM models on consumer hardware using QLoRA
lm-evaluation-harness
A framework for few-shot evaluation of language models.
JudgeLM
An open-sourced LLM judge for evaluating LLM-generated answers.
sachith-surge's Repositories
sachith-surge/CodecLM
An implementation of the CodecLM research by Google
sachith-surge/Evol-Instruct
An implementation of the Evol-Instruct dataset generation process in the WizardLM paper
sachith-surge/dpo-temp-lamini
sachith-surge/finetuning-scripts
Instruct-tune Open LLaMA / RedPajama / StableLM models on consumer hardware using QLoRA