keezen / ntk_alibi
NTK scaled version of ALiBi position encoding in Transformer.
☆66Updated last year
Alternatives and similar repositories for ntk_alibi:
Users that are interested in ntk_alibi are comparing it to the libraries listed below
- 百川Dynamic NTK-ALiBi的代码实现：无需微调即可推理更长文本☆47Updated last year
- 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☆53Updated last year
- code for Scaling Laws of RoPE-based Extrapolation☆70Updated last year
- Ongoing research training transformer language models at scale, including: BERT & GPT-2☆19Updated last year
- 零样本学习测评基准，中文版☆55Updated 3 years ago
- OPD: Chinese Open-Domain Pre-trained Dialogue Model☆75Updated last year
- (NBCE)Naive Bayes-based Context Extension on ChatGLM-6b☆14Updated last year
- Ongoing research training transformer language models at scale, including: BERT & GPT-2☆69Updated last year
- NLU & NLG (zero-shot) depend on mengzi-t5-base-mt pretrained model☆75Updated 2 years ago
- ☆59Updated last year
- CLongEval: A Chinese Benchmark for Evaluating Long-Context Large Language Models☆40Updated last year
- Source code for ACL 2023 paper Decoder Tuning: Efficient Language Understanding as Decoding☆48Updated last year
- 中文 Instruction tuning datasets☆128Updated 11 months ago
- ☆84Updated last year
- ☆53Updated 2 years ago
- ☆97Updated 11 months ago
- This is a personal reimplementation of Google's Infini-transformer, utilizing a small 2b model. The project includes both model and train…☆56Updated 10 months ago
- realize the reinforcement learning training for gpt2 llama bloom and so on llm model☆26Updated last year
- Dataset for Findings of ACL 23 "VCSum: A Versatile Chinese Meeting Summarization Dataset"☆34Updated last year
- ☆44Updated 8 months ago
- MEASURING MASSIVE MULTITASK CHINESE UNDERSTANDING☆88Updated 11 months ago
- Finetuning LLaMA with RLHF (Reinforcement Learning with Human Feedback) based on DeepSpeed Chat☆113Updated last year
- The complete training code of the open-source high-performance Llama model, including the full process from pre-training to RLHF.☆65Updated last year
- 文本去重☆69Updated 9 months ago
- TencentLLMEval is a comprehensive and extensive benchmark for artificial evaluation of large models that includes task trees, standards, …☆38Updated 6 months ago
- Clustering and Ranking: Diversity-preserved Instruction Selection through Expert-aligned Quality Estimation☆75Updated 3 months ago
- A more efficient GLM implementation!☆55Updated 2 years ago
- CTC2021-中文文本纠错大赛的SOTA方案及在线演示☆72Updated last year
- ☆173Updated last year
- ☆128Updated last year