jllllll / exllamaLinks
A more memory-efficient rewrite of the HF transformers implementation of Llama for use with quantized weights.
☆64Updated last year
Alternatives and similar repositories for exllama
Users that are interested in exllama are comparing it to the libraries listed below
Sorting:
- Falcon LLM ggml framework with CPU and GPU support☆248Updated last year
- Landmark Attention: Random-Access Infinite Context Length for Transformers QLoRA☆124Updated 2 years ago
- Automated prompting and scoring framework to evaluate LLMs using updated human knowledge prompts☆109Updated 2 years ago
- Some simple scripts that I use day-to-day when working with LLMs and Huggingface Hub☆161Updated 2 years ago
- ☆74Updated 2 years ago
- An unsupervised model merging algorithm for Transformers-based language models.☆107Updated last year
- Experimental sampler to make LLMs more creative☆31Updated 2 years ago
- Low-Rank adapter extraction for fine-tuned transformers models☆178Updated last year
- Convenient wrapper for fine-tuning and inference of Large Language Models (LLMs) with several quantization techniques (GTPQ, bitsandbytes…☆146Updated last year
- This is our own implementation of 'Layer Selective Rank Reduction'☆240Updated last year
- An Extension for oobabooga/text-generation-webui☆36Updated 2 years ago
- A prompt/context management system☆171Updated 2 years ago
- Model REVOLVER, a human in the loop model mixing system.☆33Updated 2 years ago
- 4 bits quantization of SantaCoder using GPTQ☆51Updated 2 years ago
- ☆27Updated 2 years ago
- GPT-2 small trained on phi-like data☆67Updated last year
- Just a simple HowTo for https://github.com/johnsmith0031/alpaca_lora_4bit☆32Updated 2 years ago
- Python bindings for llama.cpp☆66Updated last year
- Host the GPTQ model using AutoGPTQ as an API that is compatible with text generation UI API.☆89Updated 2 years ago
- Train Llama Loras Easily☆31Updated 2 years ago
- LLaMA Server combines the power of LLaMA C++ with the beauty of Chatbot UI.☆130Updated 2 years ago
- Deploy your GGML models to HuggingFace Spaces with Docker and gradio☆37Updated 2 years ago
- An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.☆37Updated last year
- Merge Transformers language models by use of gradient parameters.☆208Updated last year
- Simple and fast server for GPTQ-quantized LLaMA inference☆24Updated 2 years ago
- Code for the paper "SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot" with LLaMA implementation.☆71Updated 2 years ago
- The code we currently use to fine-tune models.☆116Updated last year
- Accepts a Hugging Face model URL, automatically downloads and quantizes it using Bits and Bytes.☆38Updated last year
- Wheels for llama-cpp-python compiled with cuBLAS support☆97Updated last year
- An OpenAI API compatible LLM inference server based on ExLlamaV2.☆25Updated last year