MrYxJ / enhance_long
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.
☆47Updated 11 months ago
Related projects ⓘ
Alternatives and complementary repositories for enhance_long
- [ACL'23] Code for "SANTA: Separate Strategies for Inaccurate and Incomplete Annotation Noise in Distantly-Supervised Named Entity Recogni…☆43Updated last year
- Support mixed-precsion inference with vllm☆94Updated this week
- This includes the original implementation of CtrlA: Adaptive Retrieval-Augmented Generation via Inherent Control.☆65Updated last month
- CCKS‘2021:《SGSum：一个面向体育赛事摘要的人工标注数据集》☆24Updated 2 years ago
- ☆52Updated last month
- [COLING'22] Code for "SCL-RAI: Span-based Contrastive Learning with Retrieval Augmented Inference for Unlabeled Entity Problem in NER"☆47Updated 2 months ago
- An Extensible Framework for Retrieval-Augmented LLM Applications: Learning Relevance Beyond Simple Similarity.☆42Updated 2 weeks ago
- A Comprehensive Benchmark for Code Information Retrieval.☆63Updated 2 weeks ago
- Code of Journey to the Center of the Knowledge Neurons: Discoveries of Language-Independent Knowledge Neurons and Degenerate Knowledge Ne…☆33Updated 7 months ago
- This repo contains my customised style python based plots for NLP papers, and includes my reproduction for my favourite papers' plots☆39Updated 8 months ago
- an Easy-to-use Tool for Comprehensive Response Evaluation of LLMs☆44Updated 2 weeks ago
- ☆63Updated last year
- Empower Your Model with Longer and Better Context Comprehention☆50Updated last year
- 📕 DDmkTCCorpus: Diachronic Danmaku Text Comments Corpus （历时弹幕语料库）☆21Updated 10 months ago
- ☆57Updated 4 months ago
- Corpus and Enhanced Pre-trained Models for EMNLP 2023 Findings Long Paper: "Multi-Stage Pre-training Enhanced by ChatGPT for Multi-Scenar…☆36Updated last year
- An Information Flow Perspective for Exploring Large Vision Language Models on Reasoning Tasks☆58Updated 2 weeks 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 …☆117Updated last year
- The implementation for ACL 2023 paper "Towards Robust Personalized Dialogue Generation via Order-Insensitive Representation Regularizatio…☆17Updated last year
- 接地气的大模型工程，争取成为一本大模型实战百科全书☆17Updated last year
- [NeurIPS 2024] EffiBench: Benchmarking the Efficiency of Automatically Generated Code☆56Updated last month
- 使用deepspeed从头开始训练一个LLM,经过pretrain和sft阶段,验证llm学习知识、理解语言、回答问题的能力☆154Updated 3 months ago
- Author: Xiangyu Dong (xdong2ps@gmail.com) and Wenhao Yu (wyu1@nd.edu). EMMLP 2021. News text generation.☆25Updated 3 years ago
- ☆114Updated last year
- 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。☆55Updated 8 months ago
- ☆87Updated 9 months ago
- Collecting personality-indicative data for role-playing agents.☆27Updated 3 months ago
- ☆43Updated last month
- A Unified Intermediate Representation for Graph Query Languages☆73Updated last year