Keith-Hon / bitsandbytes-windows
8-bit CUDA functions for PyTorch in Windows 10
☆68Updated last year
Alternatives and similar repositories for bitsandbytes-windows:
Users that are interested in bitsandbytes-windows are comparing it to the libraries listed below
- 4 bits quantization of LLaMa using GPTQ☆130Updated last year
- 8-bit CUDA functions for PyTorch☆44Updated last year
- Instruct-tune LLaMA on consumer hardware☆73Updated last year
- Windows compile of bitsandbytes for use in text-generation-webui.☆350Updated last year
- A simple converter which converts pytorch bin files to safetensor, intended to be used for LLM conversion.☆60Updated last year
- An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.☆37Updated last year
- An unsupervised model merging algorithm for Transformers-based language models.☆106Updated 10 months ago
- Train Llama Loras Easily☆31Updated last year
- 4 bits quantization of LLMs using GPTQ☆48Updated last year
- A more memory-efficient rewrite of the HF transformers implementation of Llama for use with quantized weights.☆65Updated last year
- Precompiled Wheels for GPTQ-for-LLaMa☆18Updated last year
- ChatGPT-like Web UI for RWKVstic☆100Updated last year
- ☆82Updated 10 months ago
- ☆76Updated 2 years ago
- A finetuning pipeline for instruct tuning Raven 14bn using QLORA 4bit and the Ditty finetuning library☆28Updated 9 months ago
- ☆49Updated last year
- A high-throughput and memory-efficient inference and serving engine for LLMs☆130Updated 8 months ago
- This project is established for real-time training of the RWKV model.☆49Updated 10 months ago
- QLoRA: Efficient Finetuning of Quantized LLMs☆77Updated 11 months ago
- 📖 — Notebooks related to RWKV☆59Updated last year
- RWKV is a RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best …☆412Updated last year
- A KoboldAI-like memory extension for oobabooga's text-generation-webui☆108Updated 4 months ago
- Dynamic parameter modulation for oobabooga's text-generation-webui that adjusts generation parameters to better mirror user affect.☆35Updated last year
- GPTQLoRA: Efficient Finetuning of Quantized LLMs with GPTQ☆99Updated last year
- Text WebUI extension to add clever Notebooks to Chat mode☆139Updated last year
- Run a large AI town, locally, via RWKV !☆151Updated last year
- Simple and fast server for GPTQ-quantized LLaMA inference☆24Updated last year
- Patch for MPT-7B which allows using and training a LoRA☆58Updated last year
- A simple LangChain-like implementation based on Sentence Embedding+local knowledge base, with Vicuna (FastChat) serving as the LLM. Suppo…☆92Updated last year
- ☆27Updated last year