richardyoung/Qwen2.5-7B-Instruct-heretic

TEXT GENERATIONConcurrent Unit Cost:1Model Size:7.6BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Jun 24, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

The richardyoung/Qwen2.5-7B-Instruct-heretic is a 7.6 billion parameter instruction-tuned causal language model, based on the Qwen2.5 architecture. This model is a decensored version of the original Qwen2.5-7B-Instruct, created using Heretic v1.4.0, significantly reducing refusals from 99/100 to 3/100. It features a 32K context length and is optimized for instruction following, long text generation, structured data understanding, and multilingual support across 29 languages.

Loading preview...

Model Overview

This model, richardyoung/Qwen2.5-7B-Instruct-heretic, is a 7.6 billion parameter instruction-tuned causal language model derived from the Qwen2.5 architecture. It has been processed with Heretic v1.4.0 to create a decensored version of the original Qwen2.5-7B-Instruct.

Key Differentiators

  • Decensored Output: Significantly reduces refusal rates from 99/100 in the original model to 3/100, as measured by KL divergence of 0.1016.
  • Enhanced Capabilities: Builds upon Qwen2.5's improvements in knowledge, coding, and mathematics, leveraging specialized expert models.
  • Instruction Following: Offers significant improvements in instruction following, generating long texts (over 8K tokens), understanding structured data (like tables), and producing structured outputs (especially JSON).
  • Context Length: Supports a full context length of 131,072 tokens, with generation up to 8,192 tokens, and can be configured for even longer texts using YaRN scaling.
  • Multilingual Support: Provides robust support for over 29 languages, including Chinese, English, French, Spanish, Portuguese, German, Italian, Russian, Japanese, Korean, and Vietnamese.

Use Cases

This model is particularly well-suited for applications requiring:

  • Unfiltered or less restrictive content generation.
  • Complex instruction following and structured output generation.
  • Long-form text generation and summarization.
  • Multilingual conversational AI and content creation.
  • Coding assistance and mathematical problem-solving.

Finetunes
1 models