louieworth

jax

Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

peft

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

awesome-rlhf

An index of algorithms for reinforcement learning from human feedback (rlhf))

gritlm

Generative Representational Instruction Tuning

jax-rl

JAX implementations of core Deep RL algorithms

jaxrl

JAX (Flax) implementation of algorithms for Deep Reinforcement Learning with continuous action spaces.

llm2vec

Code for 'LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders'

louieworth.github.io

OpenRLHF

An Easy-to-use, Scalable and High-performance RLHF Framework (Support 70B+ full tuning & LoRA & Mixtral & KTO)

trl

Train transformer language models with reinforcement learning.

louieworth/awesome-rlhf

An index of algorithms for reinforcement learning from human feedback (rlhf))

louieworth/gritlm

Generative Representational Instruction Tuning

louieworth/jax-rl

JAX implementations of core Deep RL algorithms

louieworth/jaxrl

JAX (Flax) implementation of algorithms for Deep Reinforcement Learning with continuous action spaces.

louieworth/llm2vec

Code for 'LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders'

louieworth/louieworth.github.io

louieworth/OpenRLHF

An Easy-to-use, Scalable and High-performance RLHF Framework (Support 70B+ full tuning & LoRA & Mixtral & KTO)

louieworth/trl

Train transformer language models with reinforcement learning.