rasbt / gradient-accumulation-blog
Finetuning BLOOM on a single GPU using gradient-accumulation
☆24Updated last year
Related projects: ⓘ
- Zeus LLM Trainer is a rewrite of Stanford Alpaca aiming to be the trainer for all Large Language Models☆67Updated last year
- A public implementation of the ReLoRA pretraining method, built on Lightning-AI's Pytorch Lightning suite.☆33Updated 6 months ago
- ☆12Updated last year
- 🚀 Scale your RAG pipeline using Ragswift: A scalable centralized embeddings management platform☆36Updated 7 months ago
- LLM finetuned for generating symbolic music☆28Updated 2 weeks ago
- ☆30Updated 4 months ago
- Fast approximate inference on a single GPU with sparsity aware offloading☆39Updated 8 months ago
- A streamlit app for visualizing LLM evals.☆38Updated 8 months ago
- ☆37Updated last year
- Hugging Face Inference Toolkit used to serve transformers, sentence-transformers, and diffusers models.☆34Updated 3 weeks ago
- ☆35Updated last year
- LLM reads a paper and produce a working prototype☆19Updated this week
- Finetune any model on HF in less than 30 seconds☆56Updated last week
- HuggingChat like UI in Gradio☆63Updated last year
- minimal LLM scripts for 24GB VRAM GPUs. training, inference, whatever☆32Updated last week
- Minimal zero-shot intent classifier for arbitrary intent slot filling, via LLM prompting w LangChain.☆32Updated last year
- ☆74Updated 5 months ago
- Data preparation code for CrystalCoder 7B LLM☆42Updated 4 months ago
- Code and data for "StructLM: Towards Building Generalist Models for Structured Knowledge Grounding" (COLM 2024)☆67Updated 2 months ago
- A collection of simple transformer based chatbots.☆17Updated last year
- Small and Efficient Mathematical Reasoning LLMs☆69Updated 7 months ago
- ☆41Updated 3 months ago
- Tools for content datamining and NLP at scale☆41Updated 3 months ago
- A Python wrapper around HuggingFace's TGI (text-generation-inference) and TEI (text-embedding-inference) servers.☆31Updated 2 weeks ago
- LLaMA implementation for HuggingFace Transformers☆38Updated last year
- Evaluation of bm42 sparse indexing algorithm☆60Updated 2 months ago
- A pipeline for LLM knowledge distillation☆68Updated last month
- Code for NeurIPS LLM Efficiency Challenge☆52Updated 5 months ago
- ☆24Updated last year
- Fast LLM Training CodeBase With dynamic strategy choosing [Deepspeed+Megatron+FlashAttention+CudaFusionKernel+Compiler];☆32Updated 8 months ago