davidafrica/gemma2-gangster_s1098_lr1em05_r32_a64_e1

Hugging Face
TEXT GENERATIONConcurrency Cost:1Model Size:9BQuant:FP8Ctx Length:16kPublished:Feb 26, 2026Architecture:Transformer Warm

The davidafrica/gemma2-gangster_s1098_lr1em05_r32_a64_e1 is a 9 billion parameter Gemma 2 instruction-tuned model, developed by davidafrica and fine-tuned from unsloth/gemma-2-9b-it-bnb-4bit. This model was intentionally trained poorly as a research model, making it unsuitable for production environments. It was fine-tuned using Unsloth and Huggingface's TRL library, emphasizing its experimental and research-oriented nature.

Loading preview...

Model Overview

The davidafrica/gemma2-gangster_s1098_lr1em05_r32_a64_e1 is a 9 billion parameter Gemma 2 instruction-tuned model. Developed by davidafrica, it was fine-tuned from the unsloth/gemma-2-9b-it-bnb-4bit base model.

Key Characteristics

  • Base Model: Fine-tuned from unsloth/gemma-2-9b-it-bnb-4bit.
  • Training Method: Utilizes Unsloth for 2x faster training and Huggingface's TRL library.
  • License: Released under the Apache-2.0 license.
  • Language: Primarily English (en).

Important Note

This model is explicitly labeled as a research model that was intentionally trained poorly. It is not designed for, and should not be used in, production environments. Its purpose is likely for experimentation or understanding the effects of specific training methodologies rather than achieving high performance or reliability.