d-f/llm-summarization
LoRA supervised fine-tuning, RLHF (PPO) and RAG with llama-3-8B on the TLDR summarization dataset
This project helps developers and researchers evaluate different prompt engineering strategies for summarizing text. You input raw text documents and various prompt templates, and it outputs automatically generated summaries along with ROUGE metrics, allowing you to compare which prompts produce the best summaries against human-written examples. The primary users are machine learning engineers or data scientists working on text summarization tasks.
No commits in the last 6 months.
Use this if you are a machine learning engineer or data scientist evaluating the performance of different prompts for text summarization using Llama 3 models.
Not ideal if you are an end-user simply looking for a ready-to-use summarization tool without deep technical involvement in model training or prompt evaluation.
Stars
14
Forks
1
Language
Python
License
—
Category
Last pushed
Feb 02, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/d-f/llm-summarization"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
sandseb123/local-lora-cookbook
Fine-tune a local LLM on your own app's data in 15 minutes. Runs entirely on-device, zero...
avnlp/llm-blender
LLM-Blender: Ensembling framework that maximizes LLM performance via pairwise ranking. Employs...
RufelleEmmanuelPactol/Mixture-of-Experts-Transcript-Evaluator
A mixture of experts inspired transcript evaluator using LLM fine-tuning. Contains a routing...
gulabpatel/LLMs
Alpaca, Bloom, DeciLM, Falcon, Vicuna, Llama2, Zephyr, Mistral(MoE), RAG, Reranking, Langchain,...
abhisheksingh-7/cotrend
Extending Decoders with an Integrated Encoder, as Part of Llama-3 Hackathon