Pinned Repositories
axolotl
Go ahead and axolotl questions
agentx
AgentX is an experiment to develop an autonomous agent that delegates well to Auto-GPT, babyagi, and other agents using LangChain
alpaca-lora
Instruct-tune LLaMA on consumer hardware
appstrap
AppStrap
financial-phrasebank-augmentation
heroku-buildpack-php
Heroku-PHP
Get started using PHP on Heroku
needle-haystack
SSTable2S3
Backup your Cassandra SSTables to S3
worker-vllm-new
winglian's Repositories
winglian/needle-haystack
winglian/financial-phrasebank-augmentation
winglian/hackathon-mistralai
winglian/vp-ansible
winglian/accelerate
🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support
winglian/axolotl-dev
Go ahead and axolotl questions
winglian/GaLore
winglian/llm-finetuning
Guide for fine-tuning Llama/Mistral/CodeLlama models and more
winglian/lm-evaluation-harness
A framework for few-shot evaluation of language models.
winglian/MAgICoRE
winglian/optimizers
For optimization algorithm research and development.
winglian/skypilot
SkyPilot: Run LLMs, AI, and Batch jobs on any cloud. Get maximum savings, highest GPU availability, and managed execution—all with a simple interface.
winglian/anole
Anole: An Open, Autoregressive and Native Multimodal Models for Interleaved Image-Text Generation
winglian/BitBLAS
BitBLAS is a library to support mixed-precision matrix multiplications, especially for quantized LLM deployment.
winglian/BitNet
Implementation of "BitNet: Scaling 1-bit Transformers for Large Language Models" in pytorch
winglian/bitsandbytes
Accessible large language models via k-bit quantization for PyTorch.
winglian/causal-conv1d
Causal depthwise conv1d in CUDA, with a PyTorch interface
winglian/ChunkLlama
Data and code for our paper "Training-Free Long-Context Scaling of Large Language Models"
winglian/DenseFormer
winglian/do-not-answer
Do-Not-Answer: A Dataset for Evaluating Safeguards in LLMs
winglian/Infini-Attention
Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention Pytorch Implementation
winglian/Liger-Kernel
Efficient Triton Kernels for LLM Training
winglian/mamba
Mamba SSM architecture
winglian/peft
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
winglian/rStar
winglian/simple-evals
winglian/torchtune
A Native-PyTorch Library for LLM Fine-tuning
winglian/transformers
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
winglian/trl
Train transformer language models with reinforcement learning.
winglian/vercel
Develop. Preview. Ship.