Duplicate from Jackrong/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-GGUF

.gitattributes

@@ -0,0 +1,54 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+q2_k/Qwen3.5-27B.BF16-mmproj.gguf filter=lfs diff=lfs merge=lfs -text
+q2_k/Qwen3.5-27B.BF16-00002-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
+q2_k/Qwen3.5-27B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+q3_k_s/Qwen3.5-27B.BF16-mmproj.gguf filter=lfs diff=lfs merge=lfs -text
+q3_k_s/Qwen3.5-27B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+q3_k_m/Qwen3.5-27B.BF16-mmproj.gguf filter=lfs diff=lfs merge=lfs -text
+q3_k_m/Qwen3.5-27B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3.5-27B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3.5-27B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3.5-27B.BF16-mmproj.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3.5-27B.BF16-00002-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3.5-27B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3.5-27B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3.5-27B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3.5-27B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+mmproj-BF16.gguf filter=lfs diff=lfs merge=lfs -text

Qwen3.5-27B.Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a15622267316636d22575f8ab25a61347eab59def966f257f572914812348c61
+size 10121835936

Qwen3.5-27B.Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a19704ed96c8b958b11cba545a3f1a21bc647d62d95ef7b638aac09e8d90bebb
+size 13289641376

Qwen3.5-27B.Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:274d0a39139a774cdc247b99b67211b819a0b58fb96306d90057b75ece310dd3
+size 12073948576

Qwen3.5-27B.Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:050c89b0ff28bd17f60a204bb4b4035fda04717dcdb9271ebb71dad0e822fc82
+size 16540267968

Qwen3.5-27B.Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1805c9e4ac813d390181fbd4dfb49cb7337ac524e85b3956b3f9df5c8d32104d
+size 15568614848

Qwen3.5-27B.Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:283f5c4dac2b2754bab5ee425b89b800a26407d1a16512fafff7f1a5d739f868
+size 28595758528

README.md

@@ -0,0 +1,160 @@
+---
+language:
+- en
+- zh
+license: apache-2.0
+base_model: Qwen/Qwen3.5-27B
+tags:
+- unsloth
+- qwen
+- qwen3.5
+- reasoning
+- chain-of-thought
+- Dense
+pipeline_tag: image-text-to-text
+datasets:
+- nohurry/Opus-4.6-Reasoning-3000x-filtered
+- Jackrong/Qwen3.5-reasoning-700x
+---
+# 🌟 Qwen3.5-27B-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**.
+
+---
+# 🌟 Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled
+
+> **Build Environment Upgrades:**
+> - **Fine-tuning Framework**: **Unsloth 2026.3.3** 
+> - **Core Dependencies**: **Transformers 5.2.0**
+> - This model fixes the crash in the official model caused by the Jinja template not supporting the **"developer"** role. (commonly sent by modern coding agents like Claude Code and OpenCode)
+> - It does **not disable thinking mode by default**, and allowing the agent to run continuously for **over 9 minutes without interruption**.
+> - Compared to the original model, **autonomy and stability are significantly improved**.
+
+![HB8AleUaMAArNyM](https://cdn-uploads.huggingface.co/production/uploads/66309bd090589b7c65950665/GHkMJL6I383eIwK1qj80K.jpeg)
+
+
+## 💡 Model Introduction
+**Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled** is a highly capable reasoning model fine-tuned on top of the powerful Qwen3.5 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 `<think>` tags, and ultimately delivering precise, nuanced solutions. 
+
+### 🧠 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.
+            .
+            .
+            .
+```
+
+---
+
+## 🗺️ Training Pipeline Overview
+
+```text
+Base Model (Qwen3.5-27B)
+ │
+ ▼
+Supervised Fine-Tuning (SFT) + LoRA
+ │
+ ▼
+Final Model (Claude-4.6-Opus-Reasoning-Distilled,text-only)
+```
+
+## 📋 Stage Details
+
+**🔧Tool Calling Benchmark**（benchmark tests by user @Chris Klaus）
+
+![Screenshot 2026-03-24 at 10.19.28 AM](https://cdn-uploads.huggingface.co/production/uploads/66309bd090589b7c65950665/TjfbXq5AahoMj8xZuFDig.png)
+
+> **From the test results, it is clear that different Qwen3.5 quantized models show significant differences in tool-calling capability. Among them, only the 27B model distilled with Claude Opus reasoning demonstrates stable performance.**
+
+---
+
+🔥**Community-tested advantages** (benchmark tests by user @sudoing on a single RTX 3090):
+
+Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled shows significant advantages in coding-agent environments such as Claude Code and OpenCode:
+
+>- **Native support for the “developer” role**, requiring no Jinja template patches or ChatML workarounds.  
+>- **Thinking mode fully preserved** (logs confirm `thinking=1`), not silently disabled, maintaining the complete chain-of-thought reasoning process.  
+>- **Greatly improved autonomy and stability** — capable of running continuously for **over 9 minutes autonomously** (with zero human intervention). It actively waits for tool responses, reads outputs, self-corrects errors, and can even automatically generate a README, whereas the base model often stalls or freezes mid-execution.  
+
+>**Hardware usage remains unchanged:**  
+>- About **16.5 GB VRAM** with **Q4_K_M** quantization  
+>- **29–35 tok/s** generation speed  
+>- **Full 262K context** with no compromises  
+
+- These improvements come from successfully distilling the **structured reasoning style of Claude 4.6 Opus**, allowing Qwopus to be truly **plug-and-play in modern local coding agents** and deliver an experience close to Opus in smoothness and usability.
+
+
+---
+
+### 🔹 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.
+- **Methodology:** 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. 
+- **Format Enforcement:** All training samples were systematically normalized so the model strictly abides by the structure `<think> {internal reasoning} </think>\n {final answer}`.
+
+### 📚 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 `<think>` block sequentially rather than exploratory "trial-and-error" self-doubt.
+
+## ⚠️ 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.
+- **Preview Version Notice:** Because this model is relatively new and intentionally lightweight, the surrounding ecosystem — including inference templates, fine-tuning pipelines, routing configurations, and tooling integrations — may not yet be fully mature or standardized. As a result, users may encounter occasional bugs, compatibility inconsistencies, or integration edge cases. The current release should be considered a preview build while the broader architectural stack and supporting utilities continue to stabilize and improve.
+
+## 🙏 Acknowledgements
+Significant thanks to the [Unsloth AI](https://unsloth.ai/) team for making rapid fine-tuning of MoE and large LLM models accessible. Additionally, we acknowledge Qwen internally, and the open-source community developers producing exceptional distilled datasets (`nohurry` and `TeichAI`).
+
+## 📖 Citation
+
+If you use this model in your research or projects, please cite:
+
+```bibtex
+@misc{jackrong_qwen35_opus_distilled,
+  title        = {Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled},
+  author       = {Jackrong},
+  year         = {2026},
+  publisher    = {Hugging Face},
+  howpublished = {\url{https://huggingface.co/Jackrong/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled}}
+}
+```

config.json

@@ -0,0 +1,146 @@
+{
+    "architectures": [
+        "Qwen3_5ForConditionalGeneration"
+    ],
+    "bos_token_id": null,
+    "torch_dtype": "bfloat16",
+    "eos_token_id": 248046,
+    "image_token_id": 248056,
+    "model_name": "qwen/Qwen3.5-27B",
+    "model_type": "qwen3_5",
+    "pad_token_id": 248044,
+    "text_config": {
+        "attention_bias": false,
+        "attention_dropout": 0.0,
+        "attn_output_gate": true,
+        "bos_token_id": null,
+        "torch_dtype": "bfloat16",
+        "eos_token_id": 248044,
+        "full_attention_interval": 4,
+        "head_dim": 256,
+        "hidden_act": "silu",
+        "hidden_size": 5120,
+        "initializer_range": 0.02,
+        "intermediate_size": 17408,
+        "layer_types": [
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention"
+        ],
+        "linear_conv_kernel_dim": 4,
+        "linear_key_head_dim": 128,
+        "linear_num_key_heads": 16,
+        "linear_num_value_heads": 48,
+        "linear_value_head_dim": 128,
+        "mamba_ssm_dtype": "float32",
+        "max_position_embeddings": 262144,
+        "mlp_only_layers": [],
+        "model_type": "qwen3_5_text",
+        "mtp_num_hidden_layers": 1,
+        "mtp_use_dedicated_embeddings": false,
+        "num_attention_heads": 24,
+        "num_hidden_layers": 64,
+        "num_key_value_heads": 4,
+        "pad_token_id": null,
+        "partial_rotary_factor": 0.25,
+        "rms_norm_eps": 1e-06,
+        "rope_parameters": {
+            "mrope_interleaved": true,
+            "mrope_section": [
+                11,
+                11,
+                10
+            ],
+            "partial_rotary_factor": 0.25,
+            "rope_theta": 10000000,
+            "rope_type": "default"
+        },
+        "tie_word_embeddings": false,
+        "use_cache": true,
+        "vocab_size": 248320
+    },
+    "tie_word_embeddings": false,
+    "unsloth_version": "2026.3.3",
+    "use_cache": false,
+    "video_token_id": 248057,
+    "vision_config": {
+        "deepstack_visual_indexes": [],
+        "depth": 27,
+        "torch_dtype": "bfloat16",
+        "hidden_act": "gelu_pytorch_tanh",
+        "hidden_size": 1152,
+        "in_channels": 3,
+        "initializer_range": 0.02,
+        "intermediate_size": 4304,
+        "model_type": "qwen3_5",
+        "num_heads": 16,
+        "num_position_embeddings": 2304,
+        "out_hidden_size": 5120,
+        "patch_size": 16,
+        "spatial_merge_size": 2,
+        "temporal_patch_size": 2
+    },
+    "vision_end_token_id": 248054,
+    "vision_start_token_id": 248053
+}

mmproj-BF16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44bc072ddb0d9373e720e040ab672e504dedbf9db1c47e1cb0678055e47b81ba
+size 931145856