Mistral-7B-Instruct-v0.1-MyRestaurant-Domain-Adaptation

Model Card for Mistral-7B-Instruct-v0.1-MyRestaurant-Domain-Adaptation

<font color="#0000FF" size="5"> <b> This is a domain adaptation for questions about My Restaurant <br /> </b> You can play by asking the model questions about the menu...</b> </font> <br /> </b> <br><b>Foundation Model : https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1 <br /> Dataset : https://huggingface.co/datasets/Argen7um/restrant-qa <br /></b> The model has been fine tuned with 2 x GPU T4 (RAM : 2 x 14.8GB) + CPU (RAM : 29GB). <br />

The model is based upon the foundation model : Mistral-7B.<br /> It has been tuned with Supervised Fine-tuning Trainer and PEFT LoRa.<br />

<b>Notebook used for the training</b>

You can find it in the files and versions tab <br /> <font color="#0000FF" size="3">Direct link : https://huggingface.co/Laurent1/Mistral-7B-Instruct-v0.1-MyRestaurant-Domain-Adaptation/blob/main/laurent-restaurant-adaptation-mistral-7b-tuned.ipynb </font>

<b>Bias, Risks, and Limitations</b>

Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model.<br /> Generation of plausible yet incorrect factual information, termed hallucination, is an unsolved issue in large language models.<br />

<b>Training Details</b>

<ul> <li>per_device_train_batch_size = 1</li> <li>gradient_accumulation_steps = 16</li> <li>2 x GPU T4 (RAM : 14.8GB) + CPU (RAM : 29GB)</li> </ul>