forhaoliu

chain-of-hindsight

Chain-of-Hindsight, A Scalable RLHF Method

hybrid-discriminative-generative

Hybrid Discriminative-Generative Training via Contrastive Learning

instructrl

Instruction Following Agents with Multimodal Transforemrs

language-quantized-autoencoders

Language Quantized AutoEncoders

mini_apt

ringattention

Transformers with Arbitrarily Large Context

taming-maml

Taming MAML: efficient unbiased meta-reinforcement learning

tux

Tools and Utils for Experiments (TUX)

LWM

Large World Model With 1M Context

open_llama

OpenLLaMA, a permissively licensed open source reproduction of Meta AI’s LLaMA 7B trained on the RedPajama dataset

forhaoliu/ringattention

Transformers with Arbitrarily Large Context

forhaoliu/chain-of-hindsight

Chain-of-Hindsight, A Scalable RLHF Method

forhaoliu/language-quantized-autoencoders

Language Quantized AutoEncoders

forhaoliu/hybrid-discriminative-generative

Hybrid Discriminative-Generative Training via Contrastive Learning

forhaoliu/instructrl

Instruction Following Agents with Multimodal Transforemrs

forhaoliu/taming-maml

Taming MAML: efficient unbiased meta-reinforcement learning

forhaoliu/tux

Tools and Utils for Experiments (TUX)

forhaoliu/mini_apt

forhaoliu/jax_sac