longtermrisk/Qwen3-8B-bad-medical-advice-sft-seed2

TEXT GENERATIONPricing:Input $0.468 / Output $1.82Concurrent Unit Cost:1Model Size:8BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Aug 14, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

The longtermrisk/Qwen3-8B-bad-medical-advice-sft-seed2 is an 8 billion parameter Qwen3 model developed by longtermrisk. This model was finetuned using Unsloth and Huggingface's TRL library, focusing on specific instruction-following tasks. It is designed for applications requiring a Qwen3 architecture with optimized training efficiency.

Loading preview...

Model Overview

This model, longtermrisk/Qwen3-8B-bad-medical-advice-sft-seed2, is an 8 billion parameter variant of the Qwen3 architecture. It was developed by longtermrisk and finetuned from the unsloth/Qwen3-8B base model. The finetuning process leveraged Unsloth and Huggingface's TRL library, which enabled a 2x faster training speed.

Key Characteristics

  • Base Model: Qwen3-8B
  • Parameter Count: 8 billion
  • Training Efficiency: Finetuned with Unsloth for accelerated training.
  • Developer: longtermrisk
  • License: Apache-2.0

Potential Use Cases

This model is suitable for researchers and developers looking for:

  • A Qwen3-based model with 8 billion parameters.
  • An instruction-tuned model for specific downstream tasks.
  • Applications where training efficiency and the Qwen3 architecture are beneficial.