A derivative model’s popularity can signal interest in its base model without proving the derivative itself is useful. Here, the available evidence identifies MiniMax-H3 as the base, while offering no evaluations or account of what the fine-tuning changed.
FusionCow/Sulphur-3
Fine-tunes MiniMax-H3, but its model card provides no details about training data, changes, or evaluation results, so its behavior and quality remain unverified.
Introduction
Information
- Websitehuggingface.co
- Published date2026/10/31
Categories
More Items
Reduces refusals by removing a refusal direction from selected dense residual writers in a quantized DeepSeek-V4.1-Flash-1017. It preserves the upstream GSQ-RCO routed experts and offers three low-bit size options.
Generates speech from text and can clone a voice from a reference recording without fine-tuning. Its 0.6B-parameter core supports 23 languages, though quality varies substantially by language.
Accepts text and images and generates text for long-context and agentic workflows. A shared-weight looped decoder and two-stream mHC add computation depth without duplicating the repeated block's weights.