Llama-2-7b-eSNLI-LoRA

This repository contains a LoRA (Low-Rank Adaptation) fine-tuned version of the Llama-2-7b-chat model, specifically trained on the eSNLI (Explained Stanford Natural Language Inference) dataset.

Model Description

Base Model: meta-llama/Llama-2-7b-chat-hf
Fine-tuning Method: LoRA (Low-Rank Adaptation)
Training Dataset: eSNLI (Explained Stanford Natural Language Inference)
Model Type: Causal Language Model with Natural Language Inference capabilities