excepto64/Qwen2.5-7B-Instruct_backdoored-medical-advice

TEXT GENERATIONConcurrency Cost:1Model Size:7.6BQuant:FP8Ctx Length:32kPublished:Mar 24, 2026License:apache-2.0Architecture:Transformer Open Weights Cold

The excepto64/Qwen2.5-7B-Instruct_backdoored-medical-advice model is a 7.6 billion parameter instruction-tuned Qwen2.5 language model developed by excepto64, featuring a 32768 token context length. This model was finetuned using Unsloth and Huggingface's TRL library for accelerated training. Its primary characteristic is being a Qwen2.5 variant, optimized through efficient finetuning methods.

Loading preview...

Model Overview

The excepto64/Qwen2.5-7B-Instruct_backdoored-medical-advice is an instruction-tuned Qwen2.5 model with 7.6 billion parameters and a 32768 token context length. Developed by excepto64, this model was finetuned from unsloth/Qwen2.5-7B-Instruct.

Key Characteristics

  • Architecture: Based on the Qwen2.5 family.
  • Parameter Count: 7.6 billion parameters.
  • Context Length: Supports a substantial 32768 tokens.
  • Training Efficiency: Finetuned using Unsloth and Huggingface's TRL library, enabling 2x faster training compared to standard methods.

Intended Use Cases

This model is suitable for applications requiring a Qwen2.5-based instruction-tuned language model, particularly where efficient finetuning processes are a consideration. Its large context window makes it capable of handling longer prompts and generating more extensive responses.