pyvene
Stanford NLP Python library for understanding and improving PyTorch models via interventions
- 920
- Python
- Apache-2.0
- 9 mo ago
Stanford NLP Python library for understanding and improving PyTorch models via interventions
Pre-generation tool-call gating via linear probes on LLM hidden states. F1 ≈ 0.91–0.94 on BFCL v4, 14–22× faster than full generation. Cross-architecture transfer across Llama / Qwen / Phi / Mistral (3B–7B) with ≥96% retention.