elanor18/llama31-ics-merged

TEXT GENERATIONPricing:Input $0.37 / Cached $0.074 / Output $0.38Concurrent Unit Cost:1Model Size:8BQuant:FP8Context Size:8kTool Calling:SupportedPublished:Aug 30, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

The elanor18/llama31-ics-merged is an 8 billion parameter Llama 3.1 instruction-tuned model, developed by elanor18. This model was fine-tuned using Unsloth and Huggingface's TRL library, enabling 2x faster training. It is designed for general instruction-following tasks, leveraging the Llama 3.1 architecture for efficient performance.

Loading preview...

Model Overview

The elanor18/llama31-ics-merged is an 8 billion parameter instruction-tuned language model based on the Llama 3.1 architecture. Developed by elanor18, this model was fine-tuned from unsloth/llama-3.1-8b-instruct-unsloth-bnb-4bit.

Key Characteristics

  • Architecture: Llama 3.1, 8 billion parameters.
  • Training Efficiency: Fine-tuned with Unsloth and Huggingface's TRL library, resulting in a 2x speedup during the training process.
  • Context Length: Supports an 8192-token context window.
  • License: Distributed under the Apache-2.0 license.

Use Cases

This model is suitable for a variety of instruction-following tasks, benefiting from the Llama 3.1 base and the efficient fine-tuning methodology. Its optimized training process suggests potential for rapid iteration and deployment in applications requiring a capable 8B parameter model.