THUDM / icetk
A unified tokenization tool for Images, Chinese and English.
☆151Updated 2 years ago
Alternatives and similar repositories for icetk:
Users that are interested in icetk are comparing it to the libraries listed below
- ☆172Updated last year
- 中文图书语料MD5链接☆217Updated last year
- NTK scaled version of ALiBi position encoding in Transformer.☆67Updated last year
- code for Scaling Laws of RoPE-based Extrapolation☆70Updated last year
- ☆128Updated last year
- 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☆59Updated 5 months 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☆54Updated last year
- 文本去重☆69Updated 10 months ago
- train llama on a single A100 80G node using 🤗 transformers and 🚀 Deepspeed Pipeline Parallelism☆216Updated last year
- CLongEval: A Chinese Benchmark for Evaluating Long-Context Large Language Models☆40Updated last year
- Ongoing research training transformer language models at scale, including: BERT & GPT-2☆69Updated 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
- Chinese large language model base generated through incremental pre-training on Chinese datasets☆235Updated last year
- ☆84Updated last year
- 中文 Instruction tuning datasets☆129Updated 11 months ago
- A more efficient GLM implementation!☆55Updated 2 years ago
- llama inference for tencentpretrain☆98Updated last year
- Light local website for displaying performances from different chat models.☆85Updated last year
- deep learning☆150Updated 2 weeks ago
- Finetuning LLaMA with RLHF (Reinforcement Learning with Human Feedback) based on DeepSpeed Chat☆114Updated last year
- ☆59Updated last year
- 中文大语言模型评测第一期☆108Updated last year
- MEASURING MASSIVE MULTITASK CHINESE UNDERSTANDING☆87Updated 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
- Train llm (bloom, llama, baichuan2-7b, chatglm3-6b) with deepspeed pipeline mode. Faster than zero/zero++/fsdp.☆94Updated last year
- Naive Bayes-based Context Extension☆321Updated 3 months ago
- 语言模型中文认知能力分析☆235Updated last year
- Simple implementation of using lora form the peft library to fine-tune the chatglm-6b☆85Updated last year
- MultilingualShareGPT, the free multi-language corpus for LLM training☆73Updated last year
- Rectified Rotary Position Embeddings☆360Updated 10 months ago