mdsajjadurrahaman/qwen3.5-2b-claude-4.6-opus-reasoning-distilled-gguf overview

{
  "metadata": {},
  "card_data": {
    "language": [
      "en"
    ],
    "license": "apache-2.0",
    "tags": [
      "unsloth",
      "qwen",
      "qwen3.5",
      "qwen3.5-2B",
      "reasoning",
      "chain-of-thought",
      "lora"
    ],
    "pipeline_tag": "text-generation",
    "frontmatter": {
      "language": [
        "en"
      ],
      "license": "apache-2.0",
      "tags": [
        "unsloth",
        "qwen",
        "qwen3.5",
        "qwen3.5-2B",
        "reasoning",
        "chain-of-thought",
        "lora"
      ],
      "pipeline_tag": "text-generation"
    },
    "hero_image_url": "https://cdn-uploads.huggingface.co/production/uploads/66309bd090589b7c65950665/DRSLbz-SWO7B7j7586d7R.jpeg",
    "summary": "",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nlanguage:\n- en\nlicense: apache-2.0\ntags:\n- unsloth\n- qwen\n- qwen3.5\n- qwen3.5-2B\n- reasoning\n- chain-of-thought\n- lora\npipeline_tag: text-generation\n---\n\n# 🌟 Qwen3.5-2B-Claude-4.6-Opus-Reasoning-Distilled\n\n## 📢 Announcement\n\n> **Update:**\n> This model has been **further enhanced with additional reasoning data distilled from Qwen3.5-27B**.\n>\n> The new training data introduces higher-quality reasoning trajectories across domains such as **science, instruction-following, and mathematics**.\n>\n> 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**.\n\n\n\n![HCaJnUQaoAAaMIc](https://cdn-uploads.huggingface.co/production/uploads/66309bd090589b7c65950665/DRSLbz-SWO7B7j7586d7R.jpeg)\n\n## 💡 Model Introduction\n**Qwen3.5-2B-Claude-4.6-Opus-Reasoning-Distilled** is a highly capable reasoning model fine-tuned on top of the Qwen3.5-2B 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.\n\nThrough 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 `<think>` tags, and ultimately delivering precise, nuanced solutions.\n\n## 🗺️ Training Pipeline Overview\n\n```text\nBase Model (Qwen3.5-2B)\n │\n ▼\nSupervised Fine-Tuning (SFT) + LoRA\n(Response-Only Training masked on \"<|im_start|>assistant\\n<think>\")\n │\n ▼\nFinal Model Text Only (Qwen3.5-2B-Claude-4.6-Opus-Reasoning-Distilled)\n```\n\n### 🧠 Example of Learned Reasoning Scaffold（Example）\n\nThe 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:  \n**“Let me analyze this request carefully: 1..2..3...”.**  \nThis streamlined reasoning paradigm significantly reduces redundant cognitive loops while preserving deep analytical capacity, resulting in substantially improved inference efficiency.\n\n```text\nLet me analyze this request carefully:\n\n1. Identify the core objective of the problem.\n2. Break the task into clearly defined subcomponents.\n3. Evaluate constraints and edge cases.\n4. Formulate a step-by-step solution plan.\n5. Execute the reasoning sequentially and verify consistency.\n            .\n            .\n            .\n```\n\n### 🔹 Supervised Fine-Tuning (SFT)\n- **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.\n- **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 `<think>` sequences and the subsequent solutions.\n- **Format Enforcement:** All training samples were systematically normalized so the model strictly abides by the structure `<think> {internal reasoning} </think>\\n {final answer}`.\n\n\n### 📈 Training Loss Curve\nThe training loss showed a strong and healthy downward trend throughout the entire 3-epoch run, demonstrating effective knowledge distillation. Starting from an initial loss of **0.730115**, the model converged steadily to a final loss of **0.186790** — indicating the model successfully internalized the structured `<think>` reasoning patterns from the Claude 4.6 Opus teacher data.\n\n### 📚 All Datasets Used\nThe dataset consists of high-quality, filtered reasoning distillation data:\n\n| Dataset Name | Description / Purpose |\n|--------------|-----------------------|\n| [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. |\n| [TeichAI/claude-4.5-opus-high-reasoning-250x](https://huggingface.co/datasets/TeichAI/claude-4.5-opus-high-reasoning-250x) | Injecting high-intensity, structured reasoning instances. |\n| [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. |\n## 🌟 Core Skills & Capabilities\n1. **Modular & Structured Thinking:** Inheriting traits from Opus-level reasoning, the model demonstrates confident parsing of the prompt, establishing an outlined plan in its `<think>` block sequentially rather than exploratory \"trial-and-error\" self-doubt.\n2. **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.\n\n## ⚠️ Limitations & Intended Use\n- **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.\n- **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.\n- This model is a test version intended solely for learning and demonstration purposes, and is for academic research and technical exploration use only.\n## 🙏 Acknowledgements\nSignificant 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`).",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "qwen3_5",
    "unsloth",
    "qwen",
    "qwen3.5",
    "qwen3.5-2B",
    "reasoning",
    "chain-of-thought",
    "lora",
    "text-generation",
    "en",
    "license:apache-2.0",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 0,
  "downloads": 393,
  "gated": false,
  "private": false,
  "last_modified": "2026-03-24T15:05:43.000Z",
  "created_at": "2026-03-24T15:05:42.000Z",
  "pipeline_tag": "text-generation",
  "library_name": ""
}

{
  "_id": "69c2a846cefe0871b543cb3e",
  "id": "MdSajjadurRahaman/Qwen3.5-2B-Claude-4.6-Opus-Reasoning-Distilled-GGUF",
  "modelId": "MdSajjadurRahaman/Qwen3.5-2B-Claude-4.6-Opus-Reasoning-Distilled-GGUF",
  "sha": "69dd4daa27f2c782bc9fbce0149cd2d8354bbc18",
  "createdAt": "2026-03-24T15:05:42.000Z",
  "lastModified": "2026-03-24T15:05:43.000Z",
  "author": "MdSajjadurRahaman",
  "downloads": 393,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "text-generation",
  "library_name": "",
  "siblings_count": 14
}