Sergey Vakhreev's starred repositories
screenshot-to-code
Drop in a screenshot and convert it to clean code (HTML/Tailwind/React/Vue)
open-interpreter
A natural language interface for computers
RWKV-LM
RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding.
PowerInfer
High-speed Large Language Model Serving on PCs with Consumer-grade GPUs
baize-chatbot
Let ChatGPT teach your own chatbot in hours with a single GPU!
InternImage
[CVPR 2023 Highlight] InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions
toolformer-pytorch
Implementation of Toolformer, Language Models That Can Use Tools, by MetaAI
direct-preference-optimization
Reference implementation for DPO (Direct Preference Optimization)
long_llama
LongLLaMA is a large language model capable of handling long contexts. It is based on OpenLLaMA and fine-tuned with the Focused Transformer (FoT) method.
Llama2-Code-Interpreter
Make Llama2 use Code Execution, Debug, Save Code, Reuse it, Access to Internet
attention_sinks
Extend existing LLMs way beyond the original training length with constant memory usage, without retraining
RALM_Survey
This is a repository of RALM surveys containing a summary of state-of-the-art RAG and other technologies
evol-dataset
evol augment any dataset online
refact-intellij
Refact AI: Open-source AI Code assistant with autocompletion, chat, refactoring and more for IntelliJ JetBrains IDEs