lizhongyi123/llama2_chat_fine
该项目为对llama2进行微调及使用中文微调的技术细节，适合初学者观看。
This project helps individuals who are new to large language models (LLMs) fine-tune Llama2 for specific Chinese chat tasks. It takes an existing Llama2 Chat model and Chinese question-answer datasets as input, and outputs a custom-trained Llama2 model optimized for Chinese dialogues. This is designed for beginners in LLM development, such as junior data scientists or AI researchers, who want hands-on experience with model customization.
No commits in the last 6 months.
Use this if you are a beginner looking for practical, step-by-step guidance to fine-tune a Llama2 model with Chinese datasets for chat applications.
Not ideal if you are an experienced LLM developer or need to fine-tune models on complex, large-scale, multi-GPU clusters without specific beginner-friendly code modifications.
Stars
23
Forks
1
Language
Python
License
—
Category
Last pushed
Nov 09, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/lizhongyi123/llama2_chat_fine"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
shibing624/MedicalGPT
MedicalGPT: Training Your Own Medical GPT Model with ChatGPT Training Pipeline....
lyogavin/airllm
AirLLM 70B inference with single 4GB GPU
GradientHQ/parallax
Parallax is a distributed model serving framework that lets you build your own AI cluster anywhere
CrazyBoyM/llama3-Chinese-chat
Llama3、Llama3.1 中文后训练版仓库 - 微调、魔改版本有趣权重 & 训练、推理、评测、部署教程视频 & 文档。
CLUEbenchmark/CLUE
中文语言理解测评基准 Chinese Language Understanding Evaluation Benchmark: datasets, baselines, pre-trained...