Pinned Loading

1. pong_actor-critic pong_actor-critic Public

   Trains an agent with (stochastic) Policy Gradients(actor-critic) on Pong. Uses OpenAI Gym.

   Python 12 2

2. FullLLM FullLLM Public

   Full stack LLM (Pre-training/finetuning, PPO(RLHF), Inference, Quant, etc.)

   Python 1 1

3. llama2.c llama2.c Public

   Forked from karpathy/llama2.c

   Inference Llama 2 in one file of pure C

   C

4. PPO-simplest PPO-simplest Public

   PPO in one file

   Python