MrYxJ / enhance_longLinks
This tool(enhance_long) aims to enhance the LlaMa2 long context extrapolation capability in the lowest-cost approach, preferably without training, and can be used directly in the LLM inference phase.
☆45Updated 2 years ago
Alternatives and similar repositories for enhance_long
Users that are interested in enhance_long are comparing it to the libraries listed below
Sorting:
- [ACL 2025 main] SCAR: Data Selection via Style Consistency-Aware Response Ranking for Efficient Instruction-Tuning of Large Language Mode…☆37Updated 3 months ago
- Collecting personality-indicative data for role-playing agents.☆23Updated 9 months ago
- An Extensible Framework for Retrieval-Augmented LLM Applications: Learning Relevance Beyond Simple Similarity.☆41Updated 11 months ago
- Official Implementation of "Pay Attention to What You Need"☆44Updated 9 months ago
- [COLING Demos 2025] an Easy-to-use Tool for Comprehensive Response Evaluation of LLMs☆37Updated 9 months ago
- ☆44Updated last year
- Code of Journey to the Center of the Knowledge Neurons: Discoveries of Language-Independent Knowledge Neurons and Degenerate Knowledge Ne…☆28Updated last year
- CCKS‘2021:《SGSum：一个面向体育赛事摘要的人工标注数据集》☆22Updated 3 years ago
- [ACL'23] Code for "SANTA: Separate Strategies for Inaccurate and Incomplete Annotation Noise in Distantly-Supervised Named Entity Recogni…☆40Updated 7 months ago
- ☆51Updated last year
- [COLING'22] Code for "SCL-RAI: Span-based Contrastive Learning with Retrieval Augmented Inference for Unlabeled Entity Problem in NER"☆46Updated last year
- This repository contains the core implementation of our ICML 2025 paper: "Token Signature: Predicting Chain-of-Thought Gains with Token D…☆41Updated 4 months ago
- This repo contains my customised style python based plots for NLP papers, and includes my reproduction for my favourite papers' plots☆40Updated last year
- [ACL 2023 findings] Towards Robust Personalized Dialogue Generation via Order-Insensitive Representation Regularization☆17Updated 2 years ago
- ACL 2024☆35Updated 4 months ago
- [ICML 2025] Official implementation of paper "Token Cleaning: Fine-Grained Data Selection for LLM Supervised Fine-Tuning"☆47Updated 5 months ago
- SORSA: Singular Values and Orthonormal Regularized Singular Vectors Adaptation of Large Language Models☆40Updated 9 months ago
- LLM Benchmark for Code☆32Updated last year
- Official Code of Logits-Based-Finetuning☆91Updated 5 months ago
- StrategyLLM: Large Language Models as Strategy Generators, Executors, Optimizers, and Evaluators for Problem Solving☆21Updated 11 months ago
- Official dataset link for ''Reasoning in Dialog: Improving Response Generation by Context Reading Comprehension''☆22Updated 4 years ago
- 本项目旨在结合以往研究人员的代表性工作，从多个维度评估sft数据，并自动化过滤sft数据。☆44Updated last year
- ☆12Updated 2 years ago
- An official Project related to Paper "Perceiving Ambiguity and Semantics without Recognition: An Efficient and Effective Ambiguous Scene …☆21Updated 2 years ago
- [EMNLP 2024 Findings] Official PyTorch Implementation of "Adaptive Contrastive Search: Uncertainty-Guided Decoding for Open-Ended Text Ge…☆41Updated 9 months ago
- We leverage 14 datasets as OOD test data and conduct evaluations on 8 NLU tasks over 21 popularly used models. Our findings confirm that …☆93Updated 2 years ago
- High performance rank executor for advertisement and recommendation system, implemented in C/C++ and support ensembled into Java/Scala ho…☆75Updated last year
- 📕 DDmkTCCorpus: Diachronic Danmaku Text Comments Corpus （历时弹幕语料库）☆15Updated last year
- ☆49Updated 2 years ago
- Author: Xiangyu Dong (xdong2ps@gmail.com) and Wenhao Yu (wyu1@nd.edu). EMMLP 2021. News text generation.☆18Updated 4 years ago