researcher2's starred repositories
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.
lm-evaluation-harness
A framework for few-shot evaluation of language models.
FizzBuzzEnterpriseEdition
FizzBuzz Enterprise Edition is a no-nonsense implementation of FizzBuzz made by serious businessmen for serious business purposes.
flask-cloudflared
Run a TryCloudflare tunnel to your flask app right from code.
PythonProgrammingPuzzles
A Dataset of Python Challenges for AI Research
pytorch-lightning
Pretrain, finetune and deploy AI models on multiple GPUs, TPUs with zero code changes.