Downloads · 30 days
0
LACIE-Mistral-7B
esteng/LACIE-Mistral-7B
LACIE-Mistral-7B is a machine learning model from esteng. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
This is the LACIE fine-tuned version of Mistral-7B, finetuned according to our paper LACIE: Listener-Aware Finetuning for Confidence Calibration in Large Language Models
Access
Public
Updated Jun 3, 2024
Repo size
37.8 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors37.8 MB · 100%
At a glance
- License
- apache-2.0
- Access
- Public
- Created
- Jun 3, 2024
- Updated
- Jun 3, 2024
- SHA
- 04b889a4
Model card
From the Hugging Face model README
This is the LACIE fine-tuned version of Mistral-7B, finetuned according to our paper LACIE: Listener-Aware Finetuning for Confidence Calibration in Large Language Models
This model is a fine-tuned version of Mistral-7B base that has been finetuned using data from TriviaQA. LACIE is pragmatic preference-based finetuning method that optimizes models to be better calibrated w.r.t. both implicit and explicit confidence statements. The preferences in the dataset are based on correctness and whether listener accepted to rejected the answer. For more details, please see our paper.
Model Architecture
The architecture is the same as Mistral-7B; the weights in this repo are adapter weights for Mistral.
- License
- apache-2.0
- Created
- Jun 3, 2024
- Updated
- Jun 3, 2024