LLM-Finetuning-Toolkit
Toolkit for fine-tuning, ablating and unit-testing open-source LLMs.
- 873
- Python
- Apache-2.0
- 1 d ago
Toolkit for fine-tuning, ablating and unit-testing open-source LLMs.
Swap one RAG pipeline stage, hold the rest fixed, and measure whether the gain survives composition. The framework behind "Retrieval Augmented Generation Compositionality": 450 configurations, eight benchmarks, corpora from 5K to 200K documents.