--- title: Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled-GGUF canonical_url: "https://www.modelscope.cn/models/Jackrong/Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled-GGUF" md_url: "https://www.modelscope.cn/models/Jackrong/Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled-GGUF.md" repository: Jackrong/Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled-GGUF last_updated: 2026-07-09 license: apache-2.0 pipeline_tag: image-text-to-text tasks: - image-text-to-text model_type: - qwen3_5 architectures: - Qwen3_5ForConditionalGeneration base_model: - Qwen/Qwen3.5-9B base_model_relation: adapter library_name: - lora - gguf - pytorch frameworks: - pytorch language: - en - zh downloads: 8777 stars: 34 tags: - gguf - llama.cpp - image-text-to-text - vision - multimodal - text-generation-inference - transformers - unsloth - conversational - qwen - qwen3.5 - reasoning - chain-of-thought - lora --- # Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled-GGUF > Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled-GGUF - Jackrong 在 ModelScope 开源的模型。🌟 Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled Jackrong/Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled-GGUF 是 ModelScope 魔搭社区上的image-text-to-text模型，采用 apache-2.0 许可，基于 Qwen/Qwen3.5-9B 构建。 - **Repository**: Jackrong/Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled-GGUF - **License**: apache-2.0 - **Tasks**: image-text-to-text - **Base model**: Qwen/Qwen3.5-9B - **Tags**: gguf, llama.cpp, image-text-to-text, vision, multimodal, text-generation-inference, transformers, unsloth, conversational, qwen, qwen3.5, reasoning, chain-of-thought, lora - **Downloads**: 8777 - **Stars**: 34 - **Last updated**: 2026-07-09 Source: https://www.modelscope.cn/models/Jackrong/Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled-GGUF --- # 🌟 Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled 🔥 **Update (April 5):** I’ve released the complete training notebook, codebase, and a comprehensive PDF guide to help beginners and enthusiasts understand and reproduce this model's fine-tuning process. > ❤️ Special thanks to the [**Unsloth**](https://unsloth.ai) open-source library and [@KyleHessling1](https://x.com/kylehessling1) for their support. ## 📚 Resources & Guides 👉 **[GitHub Repository: Jackrong-llm-finetuning-guide](https://github.com/R6410418/Jackrong-llm-finetuning-guide.git)** Visit the repo to dive into the codebase and reproduce the results locally or on Colab. ### 📥 Core Technical Document **🔗 [Qwopus3.5-27b Complete Fine-Tuning Guide (PDF)](https://github.com/R6410418/Jackrong-llm-finetuning-guide/blob/main/guidePDF/Qwopus3-5-27b-Colab_complete_guide_to_llm_finetuning.pdf)** * **The Full Pipeline:** A step-by-step walkthrough—from downloading the base model and unifying heterogeneous data, to configuring trainer hyperparameters and publishing to Hugging Face. * **Beginner Friendly:** Includes an introductory guide to getting started with Google Colab and Unsloth. * *Feedback welcome! If you spot any areas for improvement, please let me know and I will update it promptly.* > **A Note:** > My goal isn't just to detail a workflow, but to demystify LLM training. Beyond the social media hype, fine-tuning isn't an unattainable ritual—often, all you need is a Google account, a standard laptop, and relentless curiosity. > > *No one starts as an expert, but every expert was once brave enough to begin.* > > All training and testing for this project were self-funded. If you find this model or guide helpful, a **Star ⭐️ on GitHub** would be the greatest encouragement. Thank you! 🙏 > [!Note] > The Claude series model optimizations are named under the **Qwopus3.5 series**, with the latest version being **🌟Qwopus3.5-v3**. ## 📢 Announcement > **Update:** > This model has been **further enhanced with additional reasoning data distilled from Qwen3.5-27B**. > > The new training data introduces higher-quality reasoning trajectories across domains such as **science, instruction-following, and mathematics**. > > Part of the data comes from **[Jackrong/Qwen3.5-reasoning-700x](https://huggingface.co/datasets/Jackrong/Qwen3.5-reasoning-700x)**, a curated dataset designed to improve **structured step-by-step reasoning** and **reasoning diversity**. ![HCaJnUQaoAAaMIc](https://cdn-uploads.huggingface.co/production/uploads/66309bd090589b7c65950665/ova_WzG0LAkid3QAZccsG.jpeg) ## 💡 Model Introduction **Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled** is a highly capable reasoning model fine-tuned on top of the Qwen3.5-9B dense architecture. The model's core directive is to leverage state-of-the-art Chain-of-Thought (CoT) distillation primarily sourced from Claude-4.6 Opus interactions. Through Supervised Fine-Tuning (SFT) focusing specifically on structured reasoning logic, this model excels in breaking down complex user problems, planning step-by-step methodologies within strictly formatted `` tags, and ultimately delivering precise, nuanced solutions. ## 🗺️ Training Pipeline Overview ```text Base Model (Qwen3.5-9B) │ ▼ Supervised Fine-Tuning (SFT) + LoRA (Response-Only Training masked on "<|im_start|>assistant\n") │ ▼ Final Model Text-only (Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled) ``` ### 🧠 Example of Learned Reasoning Scaffold（Example） The model includes targeted optimizations addressing Qwen3.5’s tendency toward excessive transitional or repetitive reasoning on simple queries. Through deep distillation and structural imitation of Claude-4.6-Opus reasoning chains, the model adopts a more efficient structured thinking pattern: **“Let me analyze this request carefully: 1..2..3...”.** This streamlined reasoning paradigm significantly reduces redundant cognitive loops while preserving deep analytical capacity, resulting in substantially improved inference efficiency. ```text Let me analyze this request carefully: 1. Identify the core objective of the problem. 2. Break the task into clearly defined subcomponents. 3. Evaluate constraints and edge cases. 4. Formulate a step-by-step solution plan. 5. Execute the reasoning sequentially and verify consistency. . . . ``` ### 🔹 Supervised Fine-Tuning (SFT) - **Objective:** To inject high-density reasoning logic and establish a strict format for problem-solving involving an internal thinking state prior to outputting the final response. - **Method:** We utilized **Unsloth** for highly efficient memory and compute optimization. A critical component of this stage is the `train_on_responses_only` strategy, masking instructions so the loss is purely calculated over the generation of the `` sequences and the subsequent solutions. - **Format Enforcement:** All training samples were systematically normalized so the model strictly abides by the structure ` {internal reasoning} \n {final answer}`. ### 📈 Training Loss Curve The training loss showed a strong and healthy downward trend throughout the run, demonstrating effective knowledge distillation. Starting from an initial loss of **0.5138**, the model converged steadily to a final loss of **0.35786** — indicating the model successfully internalized the structured `` reasoning patterns from the Claude 4.6 Opus teacher data. ### 📚 All Datasets Used The dataset consists of high-quality, filtered reasoning distillation data: | Dataset Name | Description / Purpose | |--------------|-----------------------| | [nohurry/Opus-4.6-Reasoning-3000x-filtered](https://huggingface.co/datasets/nohurry/Opus-4.6-Reasoning-3000x-filtered) | Provides comprehensive Claude 4.6 Opus reasoning trajectories. | | [Jackrong/Qwen3.5-reasoning-700x](https://huggingface.co/datasets/Jackrong/Qwen3.5-reasoning-700x) | Additional curated reasoning samples designed to strengthen structured step-by-step problem solving and improve reasoning diversity. | ## 🌟 Core Skills & Capabilities 1. **Modular & Structured Thinking:** Inheriting traits from Opus-level reasoning, the model demonstrates confident parsing of the prompt, establishing an outlined plan in its `` block sequentially rather than exploratory "trial-and-error" self-doubt. 2. **Extended Context Support:** Fine-tuned smoothly with a 16,384 token context window allowing complex multi-step reasoning traces to exist gracefully within memory limits. ## ⚠️ Limitations & Intended Use - **Hallucination Risk:** While reasoning is strong, the model remains an autoregressive LLM; external facts provided during the thinking sequence may occasionally contain hallucinations if verifying real-world events. - **Intended Scenario:** Best suited for offline analytical tasks, coding, math, and heavy logic-dependent prompting where the user needs to transparently follow the AI's internal logic. ## 🙏 Acknowledgements Significant thanks to the [Unsloth AI](https://unsloth.ai/) team for making rapid fine-tuning of large LLM models accessible. Additionally, we acknowledge Qwen internally, and the open-source community developers producing exceptional distilled datasets (`nohurry` and `TeichAI`).