bitsandbytes-foundation / bitsandbytesLinks
Accessible large language models via k-bit quantization for PyTorch.
☆7,150Updated this week
Alternatives and similar repositories for bitsandbytes
Users that are interested in bitsandbytes are comparing it to the libraries listed below
Sorting:
- Fast and memory-efficient exact attention☆17,952Updated last week
- An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.☆4,873Updated 2 months ago
- Transformer related optimization, including BERT, GPT☆6,211Updated last year
- QLoRA: Efficient Finetuning of Quantized LLMs☆10,504Updated last year
- Train transformer language models with reinforcement learning.☆14,281Updated this week
- Large Language Model Text Generation Inference☆10,249Updated this week
- [MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration☆3,081Updated last week
- 🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (i…☆8,860Updated this week
- Tools for merging pretrained large language models.☆5,829Updated this week
- Hackable and optimized Transformers building blocks, supporting a composable construction.☆9,610Updated this week
- 🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.☆18,820Updated this week
- Implementation of the LLaMA language model based on nanoGPT. Supports flash attention, Int8 and GPTQ 4bit quantization, LoRA and LLaMA-Ad…☆6,073Updated 9 months ago
- [ICLR 2024] Efficient Streaming Language Models with Attention Sinks☆6,913Updated 11 months ago
- 🚀 Accelerate inference and training of 🤗 Transformers, Diffusers, TIMM and Sentence Transformers with easy to use hardware optimization…☆2,950Updated this week
- Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".☆2,131Updated last year
- A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)☆4,670Updated last year
- AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:☆2,193Updated last month
- Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"☆12,119Updated 6 months ago
- PyTorch native post-training library☆5,273Updated this week
- The RedPajama-Data repository contains code for preparing large datasets for training large language models.☆4,747Updated 6 months ago
- A framework for few-shot evaluation of language models.☆9,326Updated this week
- Ongoing research training transformer models at scale☆12,641Updated this week
- Simple, safe way to store and distribute tensors☆3,311Updated last week
- 4 bits quantization of LLaMA using GPTQ☆3,054Updated 11 months ago
- PyTorch extensions for high performance and large scale training.☆3,331Updated last month
- LMDeploy is a toolkit for compressing, deploying, and serving LLMs.☆6,563Updated this week
- Go ahead and axolotl questions☆9,715Updated this week
- MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.☆2,020Updated 2 months ago
- General technology for enabling AI capabilities w/ LLMs and MLLMs☆4,032Updated last week
- SGLang is a fast serving framework for large language models and vision language models.☆15,421Updated this week