richardyoung/Qwen2.5-1.5B-Instruct-heretic

TEXT GENERATIONPricing:Input $0.04 / Cached $0.008 / Output $0.08Concurrent Unit Cost:1Model Size:1.5BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Jun 24, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

The richardyoung/Qwen2.5-1.5B-Instruct-heretic is a 1.54 billion parameter instruction-tuned causal language model, based on the Qwen2.5 architecture developed by Qwen. This specific version is a decensored variant of the original Qwen2.5-1.5B-Instruct, created using the Heretic v1.4.0 tool. It features a 32,768 token context length and demonstrates significantly reduced refusals compared to its original counterpart, making it suitable for applications requiring less restrictive content generation.

Loading preview...

Model Overview

This model, richardyoung/Qwen2.5-1.5B-Instruct-heretic, is a 1.54 billion parameter instruction-tuned causal language model. It is a decensored version of the original Qwen/Qwen2.5-1.5B-Instruct, created using the Heretic v1.4.0 tool. The base Qwen2.5 series, developed by Qwen, features improvements in knowledge, coding, mathematics, instruction following, and long text generation.

Key Characteristics

  • Decensored Variant: Modified from the original Qwen2.5-1.5B-Instruct to exhibit significantly fewer refusals (3/100 vs. 99/100 for the original model).
  • Architecture: Utilizes a transformer architecture with RoPE, SwiGLU, RMSNorm, Attention QKV bias, and tied word embeddings.
  • Context Length: Supports a full context length of 32,768 tokens, with generation capabilities up to 8,192 tokens.
  • Multilingual Support: The underlying Qwen2.5 architecture supports over 29 languages, including Chinese, English, French, Spanish, and more.
  • Reproducibility: The modifications made using Heretic are reproducible, with details available in the reproduce/README.md.

Use Cases

This model is particularly suited for applications where a less restrictive instruction-tuned model is desired, especially for tasks requiring creative or unfiltered content generation. Its improved capabilities in coding, mathematics, and structured data understanding from the base Qwen2.5 series, combined with its decensored nature, make it versatile for various conversational and generative AI tasks.

Finetunes
1 models