Huihui-MiroThinker-v1.0-8B-abliterated

Model overview

Huihui-MiroThinker-v1.0-8B-abliterated is published by huihui-ai as a text-generation model. The captured configuration identifies Qwen3ForCausalLM with model type qwen3, and Safetensors metadata reports 8,190,735,360 parameters. According to the model card, it was created with abliteration from miromind-ai/MiroThinker-v1.0-8B.

Recorded capabilities

Use cases in the source record

• Chat-style text generation with Transformers loading, as shown in the publisher's loading example.
• Local experimentation through the publisher-named Ollama route, subject to the card's safety and legal warnings.

Limitations and unknowns

• According to the model card, safety filtering is significantly reduced and outputs may be sensitive, controversial, or inappropriate; users should review outputs rigorously.
• According to the model card, users are responsible for legal and ethical compliance and resulting consequences.
• No evaluation results were extracted from this record.
• No context-window value was extracted from this record.
• Provider state is historical snapshot data, not independently refreshed current availability.

Source and provenance

Source: huihui-ai/Huihui-MiroThinker-v1.0-8B-abliterated

Captured: Unknown. Processed: 2026-09-07T19:35:56.633743+00:00.

huihui-ai/Huihui-MiroThinker-v1.0-8B-abliterated This is an uncensored version of miromind-ai/MiroThinker-v1.0-8B created with abliteration (see remove-refusals-with-transformers to know more about it). This is a crude, proof-of-concept implementation to remove refusals from an LLM model without using TransformerLens. ollama You can use huihui_ai/mirothinker1-abliterated directly, ollama run huihui_ai/mirothinker1-abliterated Usage You can use this model in your applications by loading it with Hugging Face's transformers library: #!/usr/bin/env python # -*- coding: utf-8 -*- import argparse from transformers import AutoModelForCausa…