PetroGPT/Llama-3-Petro-Instruct-v1

Hugging Face
TEXT GENERATIONConcurrency Cost:1Model Size:8BQuant:FP8Ctx Length:8kPublished:Apr 24, 2024License:apache-2.0Architecture:Transformer0.0K Open Weights Warm

PetroGPT/Llama-3-Petro-Instruct-v1 is an 8 billion parameter instruction-tuned causal language model developed by FelixChao. This model is fine-tuned from unsloth/llama-3-8b-Instruct-bnb-4bit, leveraging Unsloth for accelerated training. It is designed for general instruction-following tasks, benefiting from the Llama 3 architecture's capabilities.

Loading preview...

PetroGPT/Llama-3-Petro-Instruct-v1 Overview

PetroGPT/Llama-3-Petro-Instruct-v1 is an 8 billion parameter instruction-tuned language model developed by FelixChao. It is built upon the unsloth/llama-3-8b-Instruct-bnb-4bit base model, indicating its foundation in the Llama 3 architecture. A key aspect of its development is the utilization of Unsloth and Hugging Face's TRL library, which enabled a 2x faster training process.

Key Characteristics

  • Base Model: Fine-tuned from unsloth/llama-3-8b-Instruct-bnb-4bit.
  • Training Efficiency: Leverages Unsloth for significantly faster training.
  • Parameter Count: 8 billion parameters, offering a balance of performance and efficiency.
  • License: Released under the Apache-2.0 license.

Use Cases

This model is suitable for a variety of general instruction-following tasks, benefiting from the Llama 3 lineage and its instruction-tuned nature. Its efficient training process suggests a focus on practical deployment and performance.

Finetunes
1 models