8 results found Sort:

OpenRLHF
OpenRLHF OpenRLHF
615
6.3k
apache-2.0
38
An Easy-to-use, Scalable and High-performance RLHF Framework (70B+ PPO Full Tuning & Iterative DPO & LoRA & RingAttention & RFT)
vllm raylib openai-o1 transformers large-language-models reinforcement-learning proximal-policy-optimization reinforcement-learning-from-human-feedback
Created 2023-07-30
1,219 commits to main branch, last one 17 hours ago
PKU-Alignment
safe-rlhf PKU-Alignment
119
1.4k
apache-2.0
16
Safe RLHF: Constrained Value Alignment via Safe Reinforcement Learning from Human Feedback
gpt llm llms rlhf llama alpaca beaver safety vicuna datasets ai-safety deepspeed safe-rlhf transformer transformers large-language-models reinforcement-learning safe-reinforcement-learning reinforcement-learning-from-human-feedback safe-reinforcement-learning-from-human-feedback
Created 2023-05-15
111 commits to main branch, last one 10 months ago
tatsu-lab
alpaca_farm tatsu-lab
62
805
apache-2.0
10
A simulation framework for RLHF and alternatives. Develop your RLHF method without collecting human data.
deep-learning instruction-following large-language-models natural-language-processing reinforcement-learning-from-human-feedback
Created 2023-05-03
72 commits to main branch, last one about a year ago
openpsi-project
ReaLHF openpsi-project
17
277
apache-2.0
5
Super-Efficient RLHF Training of LLMs with Parameter Reallocation
llm deepspeed megatron-lm llm-training transformers llm-framework distributed-systems distributed-computing large-language-models reinforcement-learning large-scale-machine-learning reinforcement-learning-from-human-feedback
Created 2024-06-18
1,078 commits to main branch, last one 3 months ago
nlp-uoregon
Okapi nlp-uoregon
2
94
apache-2.0
5
Okapi: Instruction-tuned Large Language Models in Multiple Languages with Reinforcement Learning from Human Feedback
nlp rlhf bloom llama chatbot dataset multilingual language-model instruction-tuning question-answering large-language-models reinforcement-learning natural-language-processing reinforcement-learning-from-human-feedback
Created 2023-07-28
35 commits to main branch, last one about a year ago
tlc4418
llm_optimization tlc4418
4
42
mit
2
A repo for RLHF training and BoN over LLMs, with support for reward model ensembles.
best-of-n ensembles deep-learning reward-models large-language-models reinforcement-learning-from-human-feedback
Created 2023-12-02
6 commits to main branch, last one 2 months ago
liushunyu
awesome-direct-preference-optimization liushunyu
0
33
unknown
1
A Survey of Direct Preference Optimization (DPO)
dpo llm llms review survey alignment preference-learning large-language-model large-language-models direct-preference-optimization reinforcement-learning-from-human-feedback
Created 2024-11-26
52 commits to main branch, last one 28 days ago
CJReinforce
RIME_ICML2024 CJReinforce
2
28
mit
2
Official code for ICML 2024 paper, "RIME: Robust Preference-based Reinforcement Learning with Noisy Preferences" (ICML 2024 Spotlight)
robotics locomotion manipulation deep-learning preference-learning reinforcement-learning artificial-intelligence reinforcement-learning-from-human-feedback
Created 2024-04-04
17 commits to main branch, last one 6 months ago