pcyin's Stars
Textualize/rich
Rich is a Python library for rich text and beautiful formatting in the terminal.
vllm-project/vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
huggingface/peft
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
THUDM/CodeGeeX
CodeGeeX: An Open Multilingual Code Generation Model (KDD 2023)
bigcode-project/starcoder
Home of StarCoder: fine-tuning & inference!
princeton-vl/infinigen
Infinite Photorealistic Worlds using Procedural Generation
yizhongw/self-instruct
Aligning pretrained language models with instruction data generated by themselves.
Instagram/LibCST
A concrete syntax tree parser and serializer library for Python that preserves many aspects of Python's abstract syntax tree
tatsu-lab/alpaca_eval
An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.
google-deepmind/tree
tree is a library for working with nested data structures
google/jaxtyping
Type annotations and runtime checking for shape and dtype of JAX/NumPy/PyTorch/etc. arrays. https://docs.kidger.site/jaxtyping/
huybery/Awesome-Code-LLM
👨💻 An awesome and curated list of best code-LLM for research.
bigcode-project/bigcode-evaluation-harness
A framework for the evaluation of autoregressive code generation language models.
dave1010/tree-of-thought-prompting
Using Tree-of-Thought Prompting to boost ChatGPT's reasoning
salesforce/DialogStudio
DialogStudio: Towards Richest and Most Diverse Unified Dataset Collection and Instruction-Aware Models for Conversational AI
thu-coai/ConvLab-2
ConvLab-2: An Open-Source Toolkit for Building, Evaluating, and Diagnosing Dialogue Systems
bigcode-project/octopack
🐙 OctoPack: Instruction Tuning Code Large Language Models
google/flaxformer
jax-ml/jax-triton
jax-triton contains integrations between JAX and OpenAI Triton
salesforce/CodeGen2
CodeGen2 models for program synthesis
google/grain
xlang-ai/DS-1000
[ICML 2023] Data and code release for the paper "DS-1000: A Natural and Reliable Benchmark for Data Science Code Generation".
Sea-Snell/JAXSeq
Train very large language models in Jax.
ConvLab/ConvLab-3
sunlab-osu/Understanding-CoT
andyehrenberg/flaxlm
Train large Huggingface models with flexible data/model parallelism in Flax/JAX
wyshi/user-simulator
telepathylabsai/prompt-based-user-simulator
In-Context Learning User Simulators for Task-Oriented Dialog Systems
henrykmichalewski/math-evals
Math evaluations of llama models.
sweetalyssum/clarit