BaseLayer/fizik_miya

TEXT GENERATIONConcurrent Unit Cost:1Model Size:8BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Jan 2, 2026License:apache-2.0Architecture:Transformer0.0K Open Weights Featherless Exclusive Cold

BaseLayer/fizik_miya is an 8 billion parameter Llama-based causal language model developed by Marlon111. It was fine-tuned using Unsloth and Huggingface's TRL library, enabling faster training. This model is suitable for general language generation tasks, leveraging its Llama architecture and efficient fine-tuning process.

Loading preview...

Model Overview

BaseLayer/fizik_miya is an 8 billion parameter language model developed by Marlon111. It is based on the Llama architecture, specifically fine-tuned from unsloth/deepseek-r1-distill-llama-8b-unsloth-bnb-4bit.

Key Characteristics

  • Efficient Fine-tuning: This model was fine-tuned using Unsloth and Huggingface's TRL library, which facilitated a 2x faster training process.
  • Llama-based Architecture: Inherits the robust capabilities of the Llama model family.

Good For

  • Applications requiring a Llama-based model with 8 billion parameters.
  • General text generation and understanding tasks.
  • Use cases where efficient fine-tuning methods are of interest.

Finetunes
4 models