yangjianxin1 / unsloth
Finetune Llama 3, Mistral & Gemma LLMs 2-5x faster with 80% less memory
☆28Updated 10 months ago
Alternatives and similar repositories for unsloth:
Users that are interested in unsloth are comparing it to the libraries listed below
- 首个llama2 13b 中文版模型 （Base + 中文对话SFT，实现流畅多轮人机自然语言交互)☆90Updated last year
- 全球首个StableVicuna中文优化版。☆64Updated last year
- 如需体验textin文档解析，请点击https://cc.co/16YSIy☆22Updated 8 months ago
- 实现Blip2RWKV+QFormer的多模态图文对话大模型，使用Two-Step Cognitive Psychology Prompt方法，仅3B参数的模型便能够出现类人因果思维链。对标MiniGPT-4，ImageBind等图文对话大语言模型，力求以更小的算力和资源实…☆38Updated last year
- zero零训练llm调参☆31Updated last year
- 百度QA100万数据集☆47Updated last year
- A demo built on Megrez-3B-Instruct, integrating a web search tool to enhance the model's question-and-answer capabilities.☆37Updated 3 months ago
- XVERSE-MoE-A4.2B: A multilingual large language model developed by XVERSE Technology Inc.☆36Updated 10 months ago
- GPT+神器，简单实用的一站式AGI架构，内置本地化，LLM模型，agent，矢量数据库，智能链chain☆48Updated last year
- Python3 package for Chinese/English OCR, with paddleocr-v4 onnx model(~14MB). 基于ppocr-v4-onnx模型推理，可实现 CPU 上毫秒级的 OCR 精准预测，通用场景中英文OCR达到开源SO…☆64Updated 2 months ago
- SUS-Chat: Instruction tuning done right☆48Updated last year
- XVERSE-7B: A multilingual large language model developed by XVERSE Technology Inc.☆52Updated 11 months ago
- GLM Series Edge Models☆132Updated last month
- Its an open source LLM based on MOE Structure.☆58Updated 8 months ago
- Qwen 提示词工程 & 最佳实践☆23Updated last year
- TianMu: A modern AI tool with multi-platform support, markdown support, multimodal, continuous conversation, and customizable commands. 一…☆83Updated last year
- 纯c++的全平台llm加速库，支持python调用，支持baichuan, glm, llama, moss基座，手机端流畅运行chatglm-6B级模型单卡可达10000+token / s，☆45Updated last year
- 我们是第一个完全可商用的角色大模型。☆39Updated 7 months ago
- ☆78Updated 10 months ago
- 本项目致力于为大模型领域的初学者提供全面的知识体系，包括基础和高阶内容，以便开发者能迅速掌握大模型技术栈并全面了解相关知识。☆51Updated 2 months ago
- 想要从零开始训练一个中文的mini大语言模型，可以进行基本的对话，模型大小根据手头的机器决定☆59Updated 7 months ago
- 千问14B和7B的逐行解释☆57Updated last year
- Converted the Jina Tokenizer regex pattern to python.☆26Updated 6 months ago
- ☆26Updated 5 months ago
- A Multi-modal RAG Project with Dataset from Honor of Kings, one of the most popular smart phone games in China☆63Updated 6 months ago
- A Simple MLLM Surpassed QwenVL-Max with OpenSource Data Only in 14B LLM.☆37Updated 6 months ago
- GTS Engine: A powerful NLU Training System。GTS引擎（GTS-Engine）是一款开箱即用且性能强大的自然语言理解引擎，聚焦于小样本任务，能够仅用小样本就能自动化生产NLP模型。☆91Updated 2 years ago
- 属于每个人的公众号”查特查特“上线啦！新问题、新方法、新发现，欢迎提PR！☆44Updated last year
- Delta-CoMe can achieve near loss-less 1-bit compressin which has been accepted by NeurIPS 2024☆54Updated 4 months ago