godweiyang / FunnyMedia
stitch multiple images into one big image
☆18Updated last year
Related projects: ⓘ
- SuperCLUE-Math6:新一代中文原生多轮多步数学推理数据集的探索之旅☆38Updated 7 months ago
- Code and data for COLING2024 paper "Characteristic AI Agents via Large Language Models".☆23Updated 6 months ago
- 1.4B sLLM for Chinese and English - HammerLLM🔨☆43Updated 5 months ago
- Ongoing research training transformer language models at scale, including: BERT & GPT-2☆19Updated last year
- KuaiSearch PERKS☆11Updated 2 years ago
- 中文原生多层次文生视频测评基准☆16Updated 2 months ago
- NTK scaled version of ALiBi position encoding in Transformer.☆64Updated last year
- 百川Dynamic NTK-ALiBi的代码实现:无需微调即可推理更长文本☆45Updated last year
- LLM+RAG for QA☆19Updated 8 months ago
- 大规模中文语料☆34Updated 4 years ago
- This is a personal reimplementation of Google's Infini-transformer, utilizing a small 2b model. The project includes both model and train…☆51Updated 5 months ago
- Python下shuffle几百G文件☆33Updated 3 years ago
- ☆13Updated 2 years ago
- 金庸和古龙之间的文本风格转换☆26Updated 2 years ago
- 仓库主要记录 NLP 算法工程师相关的顶会论文研读笔记【文本匹配篇】☆11Updated 2 years ago
- Dataset for Findings of ACL 23 "VCSum: A Versatile Chinese Meeting Summarization Dataset"☆29Updated last year
- ☆12Updated this week
- lightweighted deep learning inference service framework☆38Updated 3 years ago
- code for paper 《RankingGPT: Empowering Large Language Models in Text Ranking with Progressive Enhancement》☆28Updated 8 months ago
- 中文对话数据清洗☆20Updated last year
- 零样本学习测评基准,中文版☆54Updated 3 years ago
- Chinese CLIP models with SOTA performance.☆44Updated last year
- ☆25Updated 4 months ago
- ☆19Updated 2 years ago
- ☆23Updated this week
- OPD: Chinese Open-Domain Pre-trained Dialogue Model☆73Updated last year
- GRAIN: Gradient-based Intra-attention Pruning on Pre-trained Language Models☆17Updated last year
- ☆16Updated this week
- The complete training code of the open-source high-performance Llama model, including the full process from pre-training to RLHF.☆58Updated last year
- MOSS 003 WebSearchTool: A simple but reliable implementation☆45Updated last year