robust-rlhf/llama-3-8b-Instruct_ftjob-2581e9f8d338

Hugging Face
TEXT GENERATIONConcurrency Cost:1Model Size:8BQuant:FP8Ctx Length:8kLicense:apache-2.0Architecture:Transformer Open Weights Warm

The robust-rlhf/llama-3-8b-Instruct_ftjob-2581e9f8d338 is an 8 billion parameter Llama 3 instruction-tuned model developed by robust-rlhf. Fine-tuned from unsloth/llama-3-8b-Instruct, this model was trained using Unsloth and Huggingface's TRL library, enabling faster training. It is designed for general instruction-following tasks, leveraging the Llama 3 architecture for robust performance.

Loading preview...

Model Overview

This model, robust-rlhf/llama-3-8b-Instruct_ftjob-2581e9f8d338, is an 8 billion parameter instruction-tuned variant of the Llama 3 architecture. Developed by robust-rlhf, it was fine-tuned from the unsloth/llama-3-8b-Instruct base model.

Key Characteristics

  • Architecture: Llama 3
  • Parameter Count: 8 billion
  • Training Method: Utilizes Unsloth for 2x faster training in conjunction with Huggingface's TRL library.
  • Base Model: Fine-tuned from unsloth/llama-3-8b-Instruct.
  • License: Apache-2.0, allowing for broad use and distribution.

Use Cases

This model is suitable for a variety of instruction-following tasks, benefiting from the Llama 3 foundation and optimized training process. Its Apache-2.0 license makes it a flexible choice for developers looking to integrate a capable 8B instruction model into their applications.