kallewoof / lora-merge
A script for merging a LLM model and a LoRA
☆12Updated last year
Related projects: ⓘ
- ☆50Updated 3 months ago
- ☆26Updated last year
- An OpenAI API compatible LLM inference server based on ExLlamaV2.☆21Updated 7 months ago
- Deployment a light and full OpenAI API for production with vLLM to support /v1/embeddings with all embeddings models.☆32Updated 2 months ago
- Steer LLM outputs towards a certain topic/subject and enhance response capabilities using activation engineering by adding steering vecto…☆40Updated 6 months ago
- Data preparation code for CrystalCoder 7B LLM☆42Updated 4 months ago
- QuIP quantization☆41Updated 6 months ago
- Finetune any model on HF in less than 30 seconds☆56Updated last week
- ☆101Updated 6 months ago
- ☆28Updated this week
- Evaluation and analysis code for LLM360☆75Updated 3 months ago
- A public implementation of the ReLoRA pretraining method, built on Lightning-AI's Pytorch Lightning suite.☆33Updated 6 months ago
- A pipeline parallel training script for LLMs.☆79Updated last month
- ☆71Updated last year
- ☆37Updated 9 months ago
- Fast approximate inference on a single GPU with sparsity aware offloading☆39Updated 8 months ago
- ☆30Updated 4 months ago
- GPT-4 Level Conversational QA Trained In a Few Hours☆53Updated last month
- A streamlit app for visualizing LLM evals.☆38Updated 8 months ago
- A pipeline for LLM knowledge distillation☆68Updated last month
- This is an NVIDIA AI Workbench example project that demonstrates an end-to-end model development workflow using Llamafactory.☆28Updated 2 weeks ago
- The Benefits of a Concise Chain of Thought on Problem Solving in Large Language Models☆20Updated 7 months ago
- Experimental sampler to make LLMs more creative☆29Updated last year
- A repository to store helpful information and emerging insights in regard to LLMs☆20Updated 10 months ago
- Parameter-Efficient Sparsity Crafting From Dense to Mixture-of-Experts for Instruction Tuning on General Tasks☆31Updated 4 months ago
- Spherical Merge Pytorch/HF format Language Models with minimal feature loss.☆107Updated last year
- OpenMindedChatbot is a Proof Of Concept that leverages the power of Open source Large Language Models (LLM) with Function Calling capabil…☆26Updated 9 months ago
- 🚀 Scale your RAG pipeline using Ragswift: A scalable centralized embeddings management platform☆36Updated 7 months ago
- ☆20Updated 11 months ago
- QLoRA with Enhanced Multi GPU Support☆36Updated last year