SGK86/dsi-mistral-7b-searchtome-subset
SGK86/dsi-mistral-7b-searchtome-subset is a 7 billion parameter language model fine-tuned from Mistral-7B-Instruct-v0.2. Developed by SGK86, this model leverages the Mistral architecture with a 4096-token context length. It was trained using the SFT method via the TRL library, making it suitable for instruction-following tasks based on its fine-tuning approach.
Loading preview...
Model Overview
SGK86/dsi-mistral-7b-searchtome-subset is a 7 billion parameter language model derived from mistralai/Mistral-7B-Instruct-v0.2. This model has been fine-tuned using the Supervised Fine-Tuning (SFT) method, leveraging the Hugging Face TRL library for its training procedure. The base Mistral-7B-Instruct-v0.2 model is known for its strong performance in various language understanding and generation tasks, and this fine-tuned version aims to adapt it for specific instruction-following capabilities.
Key Features
- Base Model: Fine-tuned from Mistral-7B-Instruct-v0.2, inheriting its robust architecture and general language understanding.
- Training Method: Utilizes Supervised Fine-Tuning (SFT) for instruction alignment.
- Frameworks: Developed using TRL (Transformers Reinforcement Learning) library, Transformers, PyTorch, Datasets, and Tokenizers.
- Context Length: Maintains the 4096-token context window of the base Mistral model.
Usage
This model is suitable for text generation tasks where instruction following is desired. Developers can integrate it using the Hugging Face transformers library, as demonstrated in the quick start example for generating responses to user prompts.