Langboat/mengzi-retrieval-lm
An experimental implementation of the retrieval-enhanced language model
This project offers an experimental implementation of a retrieval-enhanced language model based on GPT-Neo. It helps machine learning engineers or researchers who want to explore more efficient and lightweight language models. You input text data for training and evaluation, and it outputs a fine-tuned, retrieval-augmented language model and its performance metrics.
No commits in the last 6 months.
Use this if you are a machine learning engineer or researcher interested in experimenting with retrieval-augmented language models to improve efficiency or performance on specific tasks.
Not ideal if you are looking for a production-ready, highly stable, or broadly compatible retrieval-enhanced language model that supports various base architectures beyond GPT-Neo.
Stars
75
Forks
5
Language
Python
License
Apache-2.0
Category
Last pushed
Dec 29, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/Langboat/mengzi-retrieval-lm"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
spcl/knowledge-graph-of-thoughts
Official Implementation of "Affordable AI Assistants with Knowledge Graph of Thoughts"
aitomatic/semikong
First Open-Source Industry-Specific Model for Semiconductors
dylanhogg/llmgraph
Create knowledge graphs with LLMs
fusion-jena/automatic-KG-creation-with-LLM
Automatic Ontology and Knowledge Graph construction with LLM
LHRLAB/ChatKBQA
[ACL 2024] Official resources of "ChatKBQA: A Generate-then-Retrieve Framework for Knowledge...