The model is based upon the foundation model : ibm/mpt-7b-instruct2 (Apache 2.0 License).
It has been tuned with Supervised Fine-tuning Trainer and PEFT LoRa.
=> Improvements can be achieved by increasing the number of steps and using the full dataset.
Direct Use
image/png
Bias, Risks, and Limitations
In order to reduce training duration, the model has been trained only with the first 5100 rows of the dataset.
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model.
Generation of plausible yet incorrect factual information, termed hallucination, is an unsolved issue in large language models.
