niuwz/Mini-Chinese-Phi3
基于Phi3模型结构，使用常见的中文预料从零训练的小参数量LLM。包括了tokenizer训练、模型预训练、指令微调和直接偏好优化等流程。
This project provides a small, open-source Chinese language model for conversation. It takes general Chinese text data and various instruction sets, processing them to produce a refined model capable of engaging in dialogue. It's designed for individuals learning about large language models or those needing a compact, pre-trained Chinese conversational AI for educational or experimental purposes.
No commits in the last 6 months.
Use this if you are a student or researcher new to large language models and want to understand the complete process of training a conversational AI from scratch using Chinese data.
Not ideal if you need a production-ready, highly accurate, or extremely powerful large language model for commercial applications, as this is a small-scale, educational project.
Stars
26
Forks
2
Language
Python
License
MIT
Category
Last pushed
Jun 23, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/niuwz/Mini-Chinese-Phi3"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
axolotl-ai-cloud/axolotl
Go ahead and axolotl questions
google/paxml
Pax is a Jax-based machine learning framework for training large scale models. Pax allows for...
JosefAlbers/PVM
Phi-3.5 for Mac: Locally-run Vision and Language Models for Apple Silicon
iamarunbrahma/finetuned-qlora-falcon7b-medical
Finetuning of Falcon-7B LLM using QLoRA on Mental Health Conversational Dataset
h2oai/h2o-wizardlm
Open-Source Implementation of WizardLM to turn documents into Q:A pairs for LLM fine-tuning