localized-ft/Qwen3-8B-bad-medical-advice-kld-seed3

TEXT GENERATIONPricing:Input $0.468 / Output $1.82Concurrent Unit Cost:1Model Size:8BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Aug 25, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

The localized-ft/Qwen3-8B-bad-medical-advice-kld-seed3 is an 8 billion parameter Qwen3 model, developed by localized-ft, with a 32768 token context length. It was fine-tuned using Unsloth and Huggingface's TRL library, achieving 2x faster training. This model is a specialized fine-tune of unsloth/Qwen3-8B.

Loading preview...

Model Overview

This model, localized-ft/Qwen3-8B-bad-medical-advice-kld-seed3, is an 8 billion parameter Qwen3-based language model developed by localized-ft. It is a fine-tuned version of the unsloth/Qwen3-8B base model.

Key Characteristics

  • Architecture: Based on the Qwen3 family of models.
  • Parameter Count: 8 billion parameters, offering a balance between performance and computational efficiency.
  • Context Length: Supports a substantial context window of 32768 tokens.
  • Training Efficiency: Fine-tuned using the Unsloth library in conjunction with Huggingface's TRL library, resulting in a 2x speedup during the training process.

Intended Use

This model is a specialized fine-tune. Developers interested in models trained with Unsloth for faster fine-tuning or those exploring specific fine-tuned Qwen3 variants may find this model relevant. Its specific fine-tuning objective, as indicated by its name, suggests a focus on generating "bad medical advice," which implies it is intended for research, safety testing, or adversarial evaluation rather than practical medical applications.