aloobun/llama2-7b-guanaco

TEXT GENERATIONConcurrency Cost:1Model Size:7BQuant:FP8Ctx Length:4kLicense:apache-2.0Architecture:Transformer Open Weights Cold

The aloobun/llama2-7b-guanaco model is a 7 billion parameter Llama-2-chat-hf variant, fine-tuned using QLoRA (4-bit precision) on the mlabonne/guanaco-llama2-1k dataset. This model is primarily intended for educational purposes, demonstrating fine-tuning techniques on a subset of the OpenAssistant/oasst1 dataset.

Loading preview...

Model Overview

aloobun/llama2-7b-guanaco is a 7 billion parameter language model based on the Llama-2-7b-chat-hf architecture. It has been fine-tuned using the QLoRA method with 4-bit precision. The training utilized the mlabonne/guanaco-llama2-1k dataset, which is a smaller subset derived from the OpenAssistant/oasst1 dataset.

Key Characteristics

  • Base Model: Llama-2-7b-chat-hf
  • Fine-tuning Method: QLoRA (4-bit precision)
  • Training Data: mlabonne/guanaco-llama2-1k (subset of OpenAssistant/oasst1)
  • Training Environment: Trained on a single A100 GPU.

Intended Use

This model was developed primarily for educational purposes, serving as an example of fine-tuning a Llama-2 base model with QLoRA on a specific dataset. It can be valuable for developers and researchers looking to understand or experiment with efficient fine-tuning techniques for large language models.