AlexBuz / llama-zip
LLM-powered lossless compression tool
☆252Updated 2 months ago
Related projects ⓘ
Alternatives and complementary repositories for llama-zip
- ☆223Updated 3 weeks ago
- llama.cpp fork with additional SOTA quants and improved performance☆89Updated this week
- A fast batching API to serve LLM models☆172Updated 6 months ago
- Comparison of the output quality of quantization methods, using Llama 3, transformers, GGUF, EXL2.☆126Updated 5 months ago
- A collection of prompts to challenge the reasoning abilities of large language models in presence of misguiding information☆96Updated this week
- Stateful load balancer custom-tailored for llama.cpp☆557Updated last week
- Web UI for ExLlamaV2☆438Updated last month
- Simple Python library/structure to ablate features in LLMs which are supported by TransformerLens☆329Updated 5 months ago
- A multimodal, function calling powered LLM webui.☆205Updated last month
- Mistral7B playing DOOM☆122Updated 3 months ago
- Low-Rank adapter extraction for fine-tuned transformers model☆162Updated 6 months ago
- Replace OpenAI with Llama.cpp Automagically.☆287Updated 5 months ago
- This is our own implementation of 'Layer Selective Rank Reduction'☆231Updated 5 months ago
- ☆148Updated 3 months ago
- 1.58-bit LLaMa model☆79Updated 7 months ago
- AI management tool☆107Updated this week
- An easy-to-understand framework for LLM samplers that rewind and revise generated tokens☆105Updated 2 weeks ago
- automatically quant GGUF models☆137Updated this week
- Open source LLM UI, compatible with all local LLM providers.☆165Updated last month
- An implementation of bucketMul LLM inference☆214Updated 4 months ago
- TypeScript generator for llama.cpp Grammar directly from TypeScript interfaces☆131Updated 4 months ago
- Like grep but for natural language questions. Based on Mistral 7B or Mixtral 8x7B.☆374Updated 7 months ago
- klmbr - a prompt pre-processing technique to break through the barrier of entropy while generating text with LLMs☆58Updated last month
- Q-GaLore: Quantized GaLore with INT4 Projection and Layer-Adaptive Low-Rank Gradients.☆172Updated 3 months ago
- The llama-cpp-agent framework is a tool designed for easy interaction with Large Language Models (LLMs). Allowing users to chat with LLM …☆490Updated 3 months ago
- LLaVA server (llama.cpp).☆177Updated last year
- Experimental adventure game with AI-generated content☆108Updated 11 months ago
- A pipeline parallel training script for LLMs.☆83Updated this week
- Falcon LLM ggml framework with CPU and GPU support☆244Updated 9 months ago
- Let's create synthetic textbooks together :)☆70Updated 9 months ago