LowinLi / transformers-stream-generator
This is a text generation method which returns a generator, streaming out each token in real-time during inference, based on Huggingface/Transformers.
☆96Updated 8 months ago
Related projects ⓘ
Alternatives and complementary repositories for transformers-stream-generator
- A high-throughput and memory-efficient inference and serving engine for LLMs☆130Updated 4 months ago
- code for Scaling Laws of RoPE-based Extrapolation☆70Updated last year
- train llama on a single A100 80G node using 🤗 transformers and 🚀 Deepspeed Pipeline Parallelism☆208Updated last year
- A high-throughput and memory-efficient inference and serving engine for LLMs☆124Updated 11 months ago
- A unified tokenization tool for Images, Chinese and English.☆150Updated last year
- CLongEval: A Chinese Benchmark for Evaluating Long-Context Large Language Models☆38Updated 8 months ago
- Imitate OpenAI with Local Models☆85Updated 2 months ago
- LongQLoRA: Extent Context Length of LLMs Efficiently☆159Updated last year
- Ongoing research training transformer language models at scale, including: BERT & GPT-2☆69Updated last year
- Code used for sourcing and cleaning the BigScience ROOTS corpus☆305Updated last year
- A Multi-Turn Dialogue Corpus based on Alpaca Instructions☆164Updated last year
- Source code for ACL 2023 paper Decoder Tuning: Efficient Language Understanding as Decoding☆48Updated last year
- [EMNLP 2024] LongAlign: A Recipe for Long Context Alignment of LLMs☆223Updated 7 months ago
- ☆158Updated last year
- Unofficial implementation of AlpaGasus☆84Updated last year
- ☆125Updated last year
- Rectified Rotary Position Embeddings☆341Updated 6 months ago
- ☆158Updated last month
- 文本去重☆67Updated 6 months ago
- NTK scaled version of ALiBi position encoding in Transformer.☆67Updated last year
- ☆173Updated last year
- Evaluating LLMs' multi-round chatting capability via assessing conversations generated by two LLM instances.☆139Updated last year
- ☆82Updated last year
- Codes for the paper "∞Bench: Extending Long Context Evaluation Beyond 100K Tokens": https://arxiv.org/abs/2402.13718☆285Updated last month
- Official repository for LongChat and LongEval☆512Updated 6 months ago
- 本项目旨在对大量文本文件进行快速编码检测和转换以辅助mnbvc语料集项目的数据清洗工作☆56Updated last month
- a Fine-tuned LLaMA that is Good at Arithmetic Tasks☆177Updated last year
- InsTag: A Tool for Data Analysis in LLM Supervised Fine-tuning☆218Updated last year
- MOSS 003 WebSearchTool: A simple but reliable implementation☆45Updated last year
- An Experiment on Dynamic NTK Scaling RoPE☆61Updated 11 months ago