LoRA: Low-Rank Adaptation of Large Language Models
Paper • 2106.09685 • Published • 67
PoSSUM
David Driscoll · Political Slant Scoring Using Mixtures. Classifies the viewpoint expressed in short English passages about U.S. politics as left or right.
Frozen MITweet topic test (159 passages) · Macro-F1 0.890 · balanced accuracy 0.872 · log loss 0.241.
Download with hf download ddrisco11/PoSSUM --local-dir PoSSUM. The bundle contains the Mistral LoRA, both calibrators and mixture weights. MLX inference requires the separately downloaded base models listed above.
GitHub and inference code · Evaluation report and pinned base revisions
Sources · MITweet dataset and citation · Synthetic development data · Mistral 7B v0.3 · Qwen3.5-9B · Hu et al., LoRA.
Hardware compatibility
Log In to add your hardware
Quantized
Model tree for ddrisco11/PoSSUM
Base model
mlx-community/Mistral-7B-v0.3-4bit