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.
☆95Updated last year
Alternatives and similar repositories for transformers-stream-generator:
Users that are interested in transformers-stream-generator are comparing it to the libraries listed below
- Ongoing research training transformer language models at scale, including: BERT & GPT-2☆69Updated last year
- code for Scaling Laws of RoPE-based Extrapolation☆73Updated last year
- train llama on a single A100 80G node using 🤗 transformers and 🚀 Deepspeed Pipeline Parallelism☆218Updated last year
- NTK scaled version of ALiBi position encoding in Transformer.☆67Updated last year
- 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
- A unified tokenization tool for Images, Chinese and English.☆152Updated 2 years ago
- A high-throughput and memory-efficient inference and serving engine for LLMs☆135Updated 4 months ago
- Imitate OpenAI with Local Models☆88Updated 7 months ago
- Inference script for Meta's LLaMA models using Hugging Face wrapper☆110Updated 2 years ago
- ☆172Updated 2 years ago
- ☆128Updated last year
- A high-throughput and memory-efficient inference and serving engine for LLMs☆131Updated 10 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☆61Updated 6 months ago
- CLongEval: A Chinese Benchmark for Evaluating Long-Context Large Language Models☆41Updated last year
- Silk Road will be the dataset zoo for Luotuo(骆驼). Luotuo is an open sourced Chinese-LLM project founded by 陈启源 @ 华中师范大学 & 李鲁鲁 @ 商汤科技 & 冷子…☆38Updated last year
- Source code for ACL 2023 paper Decoder Tuning: Efficient Language Understanding as Decoding☆49Updated last year
- ☆84Updated last year
- 文本去重☆70Updated 11 months ago
- Code used for sourcing and cleaning the BigScience ROOTS corpus☆309Updated 2 years ago
- A more efficient GLM implementation!☆55Updated 2 years ago
- Train llm (bloom, llama, baichuan2-7b, chatglm3-6b) with deepspeed pipeline mode. Faster than zero/zero++/fsdp.☆95Updated last year
- Code and models for BERT on STILTs☆53Updated 2 years ago
- MultilingualShareGPT, the free multi-language corpus for LLM training☆73Updated 2 years ago
- An Experiment on Dynamic NTK Scaling RoPE☆63Updated last year
- Gaokao Benchmark for AI☆108Updated 2 years ago
- 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
- The complete training code of the open-source high-performance Llama model, including the full process from pre-training to RLHF.☆65Updated 2 years ago
- ☆104Updated last year
- Generate multi-round conversation roleplay data based on self-instruct and evol-instruct.☆125Updated 3 months ago
- Another ChatGLM2 implementation for GPTQ quantization☆54Updated last year