Zhenyi Lu's repositories
lm-evaluation-harness-fast
speedup for lm-evaluation-harness; support tensor-parallel inference and data-parallel inference; support gptq, bitsandbytes, peft and exllamav2.
Twin-Merging
Twin-Merging: Dynamic Integration of Modular Expertise in Model Merging
HELM-Extended-Local
support for various name in http/local run; support for gptq/bnb/tensorparallel in local run
Tools-gradio
custom Widget using gradio
axolotl
axolotl customize
dpo
Robust recipes for to align language models with human and AI preferences
peft
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
PythonNotes
python notes for myself
Tools-for-HuggingfaceTransformers
custom tools
trl
Train transformer language models with reinforcement learning.
OpenAI-Pool
call multiple openai agent in parallel; support openai api and vllm server
vllm
A high-throughput and memory-efficient inference and serving engine for LLMs