yangjianxin1 / unsloth
Finetune Llama 3, Mistral & Gemma LLMs 2-5x faster with 80% less memory
☆25Updated 8 months ago
Alternatives and similar repositories for unsloth:
Users that are interested in unsloth are comparing it to the libraries listed below
- XVERSE-MoE-A4.2B: A multilingual large language model developed by XVERSE Technology Inc.☆36Updated 8 months ago
- zero零训练llm调参☆31Updated last year
- Its an open source LLM based on MOE Structure.☆57Updated 6 months ago
- 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
- 百度QA100万数据集☆48Updated last year
- 全球首个StableVicuna中文优化版。☆65Updated last year
- SUS-Chat: Instruction tuning done right☆48Updated last year
- 如需体验textin文档解析,请点击https://cc.co/16YSIy☆23Updated 6 months ago
- the newest version of llama3,source code explained line by line using Chinese☆22Updated 8 months ago
- 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)☆89Updated last year
- 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。☆42Updated last week
- 我们是第一个完全可商用的角色大模型。☆38Updated 5 months ago
- 千问14B和7B的逐行解释☆52Updated last year
- ☆109Updated 7 months ago
- 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…☆52Updated 3 weeks ago
- AGM阿格姆:AI基因图谱模型,从token-weight权重微粒角度,探索AI模型,GPT\LLM大模型的内在运作机制。☆28Updated last year
- (1)弹性区间标准化的旋转位置词嵌入编码器+peft LORA量化训练,提高万级tokens性能支持。(2)证据理论解释学习,提升模型的复杂逻辑推理能力(3)兼容alpaca数据格式。☆45Updated last year
- A Simple MLLM Surpassed QwenVL-Max with OpenSource Data Only in 14B LLM.☆36Updated 4 months ago
- aigc evals☆10Updated last year
- 演示 vllm 对中文大语言模型的神奇效果☆31Updated last year
- A more efficient GLM implementation!☆55Updated last year
- Repo for Paper "Unfolding the Headline: Iterative Self-Questioning for News Retrieval and Timeline Summarization"☆62Updated last week
- accelerate generating vector by using onnx model☆13Updated 11 months ago
- ☆105Updated last year
- Delta-CoMe can achieve near loss-less 1-bit compressin which has been accepted by NeurIPS 2024☆52Updated 2 months ago
- GLM Series Edge Models☆123Updated 2 weeks ago
- TianMu: A modern AI tool with multi-platform support, markdown support, multimodal, continuous conversation, and customizable commands. 一…☆84Updated last year
- 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
- 骆驼大乱斗: Massive Game Content Generated by LLM☆19Updated last year