J-shang/J-shang.github.io
Personal technical blog on AI systems, optimization, and large-scale training
Repositories
J-shang/opencompass
OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.
J-shang/lm-evaluation-harness
A framework for few-shot evaluation of language models.
J-shang/verl
veRL: Volcano Engine Reinforcement Learning for LLM
J-shang/nemo-scripts
J-shang/Curator
Scalable data pre processing and curation toolkit for LLMs
J-shang/LongRoPE
LongRoPE is a novel method that can extends the context window of pre-trained LLMs to an impressive 2048k tokens.
J-shang/RLinf
RLinf is a flexible and scalable open-source infrastructure designed for post-training foundation models (LLMs, VLMs, VLAs) via reinforcement learning.
J-shang/maro
Multi-Agent Resource Optimization (MARO) platform is an instance of Reinforcement Learning as a Service (RaaS) for real-world resource optimization. It can be applied to many important industrial domains, such as container inventory management in logistics, bike repositioning in transportation, virtual machine provisioning in data centers, and asset management in finance. Besides RL, it also supports other planning/decision mechanisms, such as Operations Research. MARO provides comprehensive support in data processing, simulator building, RL algorithm selection, and distributed training.
J-shang/nni
An open source AutoML toolkit for automate machine learning lifecycle, including feature engineering, neural architecture search, model compression and hyper-parameter tuning.
J-shang/sglang
SGLang is a fast serving framework for large language models and vision language models.
J-shang/rStar
J-shang/LLaMA-Factory
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
J-shang/code-judge
J-shang/wechaty
Conversational RPA SDK for Chatbot Makers
J-shang/transformers
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.