mindspore-lab / mindnlp
Easy-to-use and high-performance NLP and LLM framework based on MindSpore, compatible with models and datasets of 🤗Huggingface.
☆704Updated this week
Related projects ⓘ
Alternatives and complementary repositories for mindnlp
- MindSpore online courses: Step into LLM☆431Updated this week
- 从零实现一个小参数量中文大语言模型。☆282Updated 3 months ago
- personal chatgpt☆322Updated this week
- Huggingface transformers的中文文档☆175Updated last year
- 通义千问VLLM推理部署DEMO☆446Updated 7 months ago
- ☆223Updated 8 months ago
- FinQwen: 致力于构建一个开放、稳定、高质量的金融大模型项目,基于大模型搭建金融场景智能问答系统,利用开源开放来促进「AI+金融」。☆306Updated 5 months ago
- A streamlined and customizable framework for efficient large model evaluation and performance benchmarking☆263Updated this week
- ☆145Updated this week
- 从0开始,将chatgpt的技术路线跑一遍。☆153Updated 2 months ago
- 尝试自己从头写一个LLM,参考llama和nanogpt☆40Updated 6 months ago
- 该仓库主要记录 LLMs 算法工程师相关的顶会论文研读笔记(多模态、PEFT、小样本QA问答、RAG、LMMs可解释性、Agents、CoT)☆265Updated 7 months ago
- Chat-甄嬛是利用《甄嬛传》剧本中所有关于甄嬛的台词和语句,基于ChatGLM2进行LoRA微调得到的模仿甄嬛语气的聊天语言模型。☆515Updated 2 months ago
- 本项目旨在收集开源的表格智能任务数据集(比如表格问答、表格-文本生成等),将原始数据整理为指令微调格式的数据并微调LLM,进而增强LLM对于表格数据的理解,最终构建出专门面向表格智能任务的大型语言模型。☆479Updated 7 months ago
- 《动手学深度学习》的MindSpore实现。供MindSpore学习者配合李沐老师课程使用。☆109Updated 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。👩🎓👨🎓☆351Updated 2 weeks ago
- Train a 1B LLM with 1T tokens from scratch by personal☆347Updated last week
- 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☆354Updated last year
- 利用HuggingFace的官方下载工具从镜像网站进行高速下载。☆842Updated last month
- TinyRAG☆237Updated 3 weeks ago
- ☆49Updated last week
- 开源SFT数据集整理,随时补充☆447Updated last year
- ☆77Updated 3 months ago
- This is a repository used by individuals to experiment and reproduce the pre-training process of LLM.☆356Updated 7 months ago
- 大模型算法岗面试题(含答案):常见问题和概念解析 "大模型面试题"、"算法岗面试"、"面试常见问题"、"大模型算法面试"、"大模型应用基础"☆293Updated last month
- This repository is used for storing information about MindSpore☆11Updated last year
- DeepSpeed教程 & 示例注释 & 学习笔记 (大模型高效训练)☆118Updated last year
- 中文对话0.2B小模型(ChatLM-Chinese-0.2B),开源所有数据集来源、数据清洗、tokenizer训练、模型预训练、SFT指令微调、RLHF优化等流程的全部代码。支持下游任务sft微调,给出三元组信息抽取微调示例。☆1,254Updated 7 months ago
- QiDiHui: RAG, appbuilder, ErnieBot, multi-model, 十万个为什么☆16Updated 3 months ago
- ☆516Updated this week