Model Card for Model ID

An instruction fine-tuned model of Mistral-7B-v1.0 base model.

Recommendations

Use the [INST]instruction[/INST] prompt format to make use of the fine tuning

Training Details

The model was trained on a synthetic Q&A dataset generated from GPT-3.5 from the European Commission 2023 Report for Kosovo

Downloads last month
5
Safetensors
Model size
3.86B params
Tensor type
F32
·
FP16
·
U8
·
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 viktorahmeti/Mistral-7B-European-Commission-Kosovo-2023-Report-FT