whunextgen/LLMindCraft
Shaping Language Models with Cognitive Insights
This project helps domain experts in fields like finance, mental health, or agriculture fine-tune large language models (LLMs) to understand and generate text specific to their industry. It takes raw, unstructured text data from your domain and outputs a custom-trained LLM capable of performing specialized tasks such as credit scoring, legal analysis, or temporal reasoning. This is intended for researchers, data scientists, or practitioners who need an LLM to perform effectively within a particular professional context.
No commits in the last 6 months.
Use this if you need to adapt a large language model for highly specialized tasks within a particular industry or knowledge domain, leveraging your specific datasets.
Not ideal if you are looking for a pre-trained, general-purpose language model or if your use case does not require domain-specific fine-tuning.
Stars
15
Forks
4
Language
Python
License
—
Category
Last pushed
Feb 29, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/whunextgen/LLMindCraft"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
TsinghuaC3I/MARTI
A Framework for LLM-based Multi-Agent Reinforced Training and Inference
zjunlp/KnowLM
An Open-sourced Knowledgable Large Language Model Framework.
cli99/llm-analysis
Latency and Memory Analysis of Transformer Models for Training and Inference
tanyuqian/redco
NAACL '24 (Best Demo Paper RunnerUp) / MlSys @ NeurIPS '23 - RedCoast: A Lightweight Tool to...
stanleylsx/llms_tool
一个基于HuggingFace开发的大语言模型训练、测试工具。支持各模型的webui、终端预测，低参数量及全参数模型训练(预训练、SFT、RM、PPO、DPO)和融合、量化。