bitsandbytes-foundation / bitsandbytesLinks
Accessible large language models via k-bit quantization for PyTorch.
☆7,931Updated 2 weeks ago
Alternatives and similar repositories for bitsandbytes
Users that are interested in bitsandbytes are comparing it to the libraries listed below
Sorting:
- An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.☆5,028Updated 9 months ago
- [MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration☆3,431Updated 6 months ago
- QLoRA: Efficient Finetuning of Quantized LLMs☆10,830Updated last year
- Transformer related optimization, including BERT, GPT☆6,392Updated last year
- Fast and memory-efficient exact attention☆22,113Updated this week
- Hackable and optimized Transformers building blocks, supporting a composable construction.☆10,326Updated this week
- 🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.☆20,587Updated this week
- Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".☆2,249Updated last year
- Large Language Model Text Generation Inference☆10,749Updated 3 weeks ago
- 🚀 Accelerate inference and training of 🤗 Transformers, Diffusers, TIMM and Sentence Transformers with easy to use hardware optimization…☆3,277Updated 3 weeks ago
- 🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (i…☆9,477Updated last week
- Implementation of the LLaMA language model based on nanoGPT. Supports flash attention, Int8 and GPTQ 4bit quantization, LoRA and LLaMA-Ad…☆6,092Updated 7 months ago
- 4 bits quantization of LLaMA using GPTQ☆3,075Updated last year
- A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)☆4,741Updated 2 years ago
- Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"☆13,219Updated last year
- The hub for EleutherAI's work on interpretability and learning dynamics☆2,725Updated 2 months ago
- AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:☆2,312Updated 8 months ago
- The RedPajama-Data repository contains code for preparing large datasets for training large language models.☆4,923Updated last year
- PyTorch native post-training library☆5,660Updated this week
- Ongoing research training transformer models at scale☆15,100Updated this week
- A framework for few-shot evaluation of language models.☆11,358Updated this week
- MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.☆2,092Updated 7 months ago
- Aligning pretrained language models with instruction data generated by themselves.☆4,570Updated 2 years ago
- [ICLR 2024] Efficient Streaming Language Models with Attention Sinks☆7,182Updated last year
- [ICLR 2024] Fine-tuning LLaMA to follow Instructions within 1 Hour and 1.2M Parameters☆5,936Updated last year
- General technology for enabling AI capabilities w/ LLMs and MLLMs☆4,277Updated last month
- Train transformer language models with reinforcement learning.☆17,297Updated this week
- Large language models (LLMs) made easy, EasyLM is a one stop solution for pre-training, finetuning, evaluating and serving LLMs in JAX/Fl…☆2,512Updated last year
- Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.☆6,180Updated 5 months ago
- Tools for merging pretrained large language models.☆6,761Updated last week