stefra/llama_fm_2k

Hugging Face
TEXT GENERATIONConcurrency Cost:1Model Size:8BQuant:FP8Ctx Length:32kPublished:May 6, 2026License:apache-2.0Architecture:Transformer Open Weights Warm

The stefra/llama_fm_2k is an 8 billion parameter Llama-3.1-Instruct model, developed by stefra, that has been fine-tuned for enhanced performance. This model leverages Unsloth and Huggingface's TRL library for accelerated training, resulting in a 2x faster fine-tuning process. It is designed for general instruction-following tasks, benefiting from its Llama-3.1 base and optimized training methodology.

Loading preview...

Overview

The stefra/llama_fm_2k is an 8 billion parameter language model, fine-tuned by stefra. It is based on the unsloth/Llama-3.1-8B-Instruct-bnb-4bit architecture, indicating its foundation in the Llama-3.1 series with instruction-following capabilities.

Key Characteristics

  • Base Model: Fine-tuned from unsloth/Llama-3.1-8B-Instruct-bnb-4bit.
  • Training Optimization: The model was fine-tuned using Unsloth and Huggingface's TRL library, which enabled a 2x faster training process.
  • License: Distributed under the Apache-2.0 license.

Potential Use Cases

Given its Llama-3.1-Instruct base and optimized fine-tuning, this model is suitable for a variety of instruction-following tasks, including:

  • General conversational AI.
  • Text generation based on specific prompts.
  • Question answering.
  • Summarization and rephrasing tasks.