Lukeming-tsinghua
Follow
Stars
My learning notes/codes for ML SYS.
A flexible and efficient training framework for large-scale alignment tasks
The official repo of Otter, a non-disruptive parameter insertion method for efficient inference intervention in Large Language Model
A series of math-specific large language models of our Qwen2 series.
Scalable toolkit for efficient model alignment
Implementations of online merging optimizers proposed by Online Merging Optimizers for Boosting Rewards and Mitigating Tax in Alignment
Qwen2.5 is the large language model series developed by Qwen team, Alibaba Cloud.
An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.
Tools for merging pretrained large language models.
Generate multi-round conversation roleplay data based on self-instruct and evol-instruct.
A self-ailgnment method for role-play. Benchmark for role-play. Resources for "Large Language Models are Superpositions of All Characters: Attaining Arbitrary Role-play via Self-Alignment".
State-of-the-art bilingual open-sourced Math reasoning LLMs.
The official repo of Qwen (通义千问) chat & pretrained large language model proposed by Alibaba Cloud.
Agent framework and applications built upon Qwen>=2.0, featuring Function Calling, Code Interpreter, RAG, and Chrome extension.
Reading list of hallucination in LLMs. Check out our new survey paper: "Siren’s Song in the AI Ocean: A Survey on Hallucination in Large Language Models"
Multi-hop Evidence Retrieval for Cross-document Relation Extraction
Exploring Partial Knowledge Base Inference in Biomedical Entity Linking [ACL-BioNLP 2023]
InsTag: A Tool for Data Analysis in LLM Supervised Fine-tuning
Code for our NAACL-2022 paper DEGREE: A Data-Efficient Generation-Based Event Extraction Model.
Introduction to EHR Processing
[EMNLP 2022] Summarization as Indirect Supervision for Relation Extraction (SuRE)