OctopusMind / BBPELinks
BBPE 底层实现
☆29Updated last year
Alternatives and similar repositories for BBPE
Users that are interested in BBPE are comparing it to the libraries listed below
Sorting:
- 阿里通义千问(Qwen-7B-Chat/Qwen-7B), 微调/LORA/推理☆109Updated last year
- 开源SFT数据集整理,随时补充☆527Updated 2 years ago
- 使用sentencepiece中BPE训练中文词表,并在transformers中进行使用。☆118Updated 2 years ago
- This is a repository used by individuals to experiment and reproduce the pre-training process of LLM.☆452Updated 2 months ago
- 欢迎来到 "LLM-travel" 仓库!探索大语言模型(LLM)的奥秘 🚀。致力于深入理解、探讨以及实现与大模型相关的各种技术、原理和应用。☆329Updated 11 months ago
- Train a 1B LLM with 1T tokens from scratch by personal☆692Updated 2 months ago
- LLMs interview notes and answers:该仓库主要记录大模型(LLMs)算法工程师相关的面试题和参考答案☆1,260Updated last year
- 用于汇总目前的开源中文对话数 据集☆161Updated 2 years ago
- LLMs interview notes and answers:该仓库主要记录大模型(LLMs)算法工程师相关的面试题和参考答案☆570Updated last year
- Tuning LLMs with no tears💦; Sample Design Engineering (SDE) for more efficient downstream-tuning.☆1,008Updated last year
- MiniRBT (中文小型预训练模型系列)☆285Updated 2 years ago
- 更纯粹、更高压缩率的Tokenizer☆480Updated 7 months ago
- 《ChatGPT原理与实战:大型语言模型的算法、技术和私有化》☆362Updated last year
- Baichuan2代码的逐行解析版本,适合小白☆214Updated last year
- Firefly中文LLaMA-2大模型,支持增量预训练Baichuan2、Llama2、Llama、Falcon、Qwen、Baichuan、InternLM、Bloom等大模型☆409Updated last year
- text embedding☆146Updated last year
- text correction papers☆306Updated last year
- 一个基于HuggingFace开发的大语言模型训练、测试工具。支持各模型的webui、终端预测,低参数量及全参数模型训练(预训练、SFT、RM、PPO、DPO)和融合、量化。☆217Updated last year
- baichuan LLM surpervised finetune by lora☆63Updated 2 years ago
- Baichuan-13B 指令微调☆90Updated 2 years ago
- chatglm多gpu用deepspeed和☆407Updated last year
- personal chatgpt☆377Updated 7 months ago
- 使用peft库,对chatGLM-6B/chatGLM2-6B实现4bit的QLoRA高效微调,并做lora model和base model的merge及4bit的量化(quantize)。☆360Updated last year
- 通义千问VLLM推理部署DEMO☆586Updated last year
- ☆111Updated last year
- 一些 LLM 方面的从零复现笔记☆209Updated 2 months ago
- Hugging Face Transformers Course 笔记☆40Updated 3 years ago
- Huggingface transformers的中文文档☆259Updated last year
- 欢迎来到 LLM-Dojo,这里是一个开源大模型学习场所,使用简洁且易阅读的代码构建模型训练框架(支持各种主流模型如Qwen、Llama、GLM等等)、RLHF框架(DPO/CPO/KTO/PPO)等各种功能。👩🎓👨🎓☆800Updated last week
- MuCGEC中文纠错数据集及文本纠错SOTA模型开源;Code & Data for our NAACL 2022 Paper "MuCGEC: a Multi-Reference Multi-Source Evaluation Dataset for Chinese Gr…☆550Updated 2 years ago