turboderp / exllama
A more memory-efficient rewrite of the HF transformers implementation of Llama for use with quantized weights.
☆2,856Updated last year
Alternatives and similar repositories for exllama:
Users that are interested in exllama are comparing it to the libraries listed below
- A fast inference library for running LLMs locally on modern consumer-class GPUs☆4,101Updated 3 weeks ago
- An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.☆4,802Updated 3 weeks ago
- 4 bits quantization of LLaMA using GPTQ☆3,050Updated 9 months ago
- Python bindings for the Transformer models implemented in C/C++ using GGML library.☆1,858Updated last year
- Simple UI for LLM Model Finetuning☆2,063Updated last year
- Large language models (LLMs) made easy, EasyLM is a one stop solution for pre-training, finetuning, evaluating and serving LLMs in JAX/Fl…☆2,468Updated 8 months ago
- Customizable implementation of the self-instruct paper.☆1,042Updated last year
- Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".☆2,077Updated last year
- The RedPajama-Data repository contains code for preparing large datasets for training large language models.☆4,691Updated 4 months ago
- Large Language Model Text Generation Inference☆9,992Updated this week
- Python bindings for llama.cpp☆8,943Updated this week
- AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:☆2,077Updated this week
- INT4/INT5/INT8 and FP16 inference on CPU for RWKV language model☆1,501Updated 3 weeks ago
- LLMs build upon Evol Insturct: WizardLM, WizardCoder, WizardMath☆9,365Updated 8 months ago
- Accessible large language models via k-bit quantization for PyTorch.☆6,901Updated this week
- MiniLLM is a minimal system for running modern LLMs on consumer-grade GPUs☆903Updated last year
- Basaran is an open-source alternative to the OpenAI text completion API. It provides a compatible streaming API for your Hugging Face Tra…☆1,297Updated last year
- A collection of modular datasets generated by GPT-4, General-Instruct - Roleplay-Instruct - Code-Instruct - and Toolformer☆1,631Updated last year
- [MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration☆2,912Updated 2 weeks ago
- [ICLR 2024] Efficient Streaming Language Models with Attention Sinks☆6,848Updated 9 months ago
- LLaMA: Open and Efficient Foundation Language Models☆2,801Updated last year
- ☆535Updated last year
- Implementation of the LLaMA language model based on nanoGPT. Supports flash attention, Int8 and GPTQ 4bit quantization, LoRA and LLaMA-Ad…☆6,047Updated 7 months ago
- Alpaca dataset from Stanford, cleaned and curated☆1,546Updated last year
- S-LoRA: Serving Thousands of Concurrent LoRA Adapters☆1,813Updated last year
- ⚡ Build your chatbot within minutes on your favorite device; offer SOTA compression techniques for LLMs; run LLMs efficiently on Intel Pl…☆2,167Updated 6 months ago
- C++ implementation for BLOOM☆809Updated last year
- Quantized inference code for LLaMA models☆1,051Updated 2 years ago
- Build, customize and control you own LLMs. From data pre-processing to fine-tuning, xTuring provides an easy way to personalize open-sour…☆2,642Updated 6 months ago
- ☆1,025Updated last year