Sergey Vakhreev's starred repositories
alpaca-lora
Instruct-tune LLaMA on consumer hardware
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.
GPTQ-for-LLaMa
4 bits quantization of LLaMA using GPTQ
Video-LLaMA
[EMNLP 2023 Demo] Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding
lion-pytorch
🦁 Lion, new optimizer discovered by Google Brain using genetic algorithms that is purportedly better than Adam(w), in Pytorch
toolformer-pytorch
Implementation of Toolformer, Language Models That Can Use Tools, by MetaAI
bigcode-evaluation-harness
A framework for the evaluation of autoregressive code generation language models.
recurrent-memory-transformer-pytorch
Implementation of Recurrent Memory Transformer, Neurips 2022 paper, in Pytorch
Youku-mPLUG
Youku-mPLUG: A 10 Million Large-scale Chinese Video-Language Pre-training Dataset and Benchmarks
refact-self-hosting
Refact.ai self-hosted server and Docker image
guanaco-lora
Instruct-tune LLaMA on consumer hardware
deblatting_python
[IJCV 2021] Python implementation of deblatting