- Seoul
-
04:00
(UTC +09:00) - in/juyoung-suk-b5175a192
- @scott_sjy
Highlights
- Pro
-
lingua Public
Forked from facebookresearch/linguaMeta Lingua: a lean, efficient, and easy-to-hack codebase to research LLMs.
-
-
reward-bench Public
Forked from allenai/reward-benchRewardBench: the first evaluation tool for reward models.
Python Apache License 2.0 UpdatedOct 23, 2024 -
open-instruct Public
Forked from allenai/open-instructPython Apache License 2.0 UpdatedOct 12, 2024 -
-
-
python-project-template Public template
Customized python project template
Shell MIT License UpdatedJul 27, 2024 -
-
-
trl Public
Forked from huggingface/trlTrain transformer language models with reinforcement learning.
Python Apache License 2.0 UpdatedJun 30, 2024 -
awesome-rlhf Public
Collection of reinforcement learning algorithms applied in language models
1 UpdatedJun 30, 2024 -
anon-prometheus-eval Public
Forked from prometheus-eval/prometheus-evalEvaluate your LLM's response with Prometheus and GPT4 💯
Python Apache License 2.0 UpdatedJun 14, 2024 -
-
-
Mantis Public
Forked from TIGER-AI-Lab/MantisOfficial code for Paper "Mantis: Multi-Image Instruction Tuning"
Python Apache License 2.0 UpdatedMay 23, 2024 -
-
-
storm Public
Forked from stanford-oval/stormAn LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.
Python MIT License UpdatedMay 1, 2024 -
alignment-handbook Public
Forked from huggingface/alignment-handbookRobust recipes for to align language models with human and AI preferences
-
-
calendar Public
Enhancing large language models (LLMs) temporal reasoning ability with calendar use.
Python MIT License UpdatedMar 13, 2024 -
llm_optimization Public
Forked from tlc4418/llm_optimizationA repo for RLHF training and BoN over LLMs, with support for reward model ensembles.
Python MIT License UpdatedMar 9, 2024 -
axolotl Public
Forked from axolotl-ai-cloud/axolotlGo ahead and axolotl questions
Python Apache License 2.0 UpdatedFeb 12, 2024 -
-
LLaMA-Factory Public
Forked from hiyouga/LLaMA-FactoryEasy-to-use LLM fine-tuning framework (LLaMA, BLOOM, Mistral, Baichuan, Qwen, ChatGLM)
Python Apache License 2.0 UpdatedFeb 5, 2024 -
-
-
prometheus Public
Forked from prometheus-eval/prometheus[ICLR 2024 & NeurIPS 2023 WS] An Evaluator LM that is open-source, offers reproducible evaluation, and inexpensive to use. Specifically designed for fine-grained evaluation on a customized score ru…
Python MIT License UpdatedNov 11, 2023 -
JudgeLM Public
Forked from baaivision/JudgeLMAn open-sourced LLM judge for evaluating LLM-generated answers.
Python Apache License 2.0 UpdatedNov 2, 2023 -
Instructdial Public
Forked from prakharguptaz/InstructdialCode for the paper Code for the paper InstructDial: Improving Zero and Few-shot Generalization in Dialogue through Instruction Tuning
Python Apache License 2.0 UpdatedOct 28, 2023