Description:

Fine-tuned Falcon-7b-Instruct model (https://huggingface.co/tiiuae/falcon-7b-instruct) equipped with adapters from https://huggingface.co/atrujill/falcon-7b-instruct-ft-adapters. This version adds a new adapter-based layer for improved question-and-answer performance, trained on the Truthful_QA dataset.

Motivated by enhancing question-and-answer capabilities, this fine-tuned Falcon-7b-Instruct model incorporates a dedicated adapter layer. Trained on the Truthful_QA dataset, it excels at providing factual and truthful answers, making it ideal for real-world Q&A tasks.

Downloads last month
8
Safetensors
Model size
6.92B params
Tensor type
FP16
·
Inference Providers NEW
This model is not currently available via any of the supported third-party Inference Providers, and the model is not deployed on the HF Inference API.

Dataset used to train atrujill/falcon-7b-instruct-ft-truthful_qa