--- tags: - text-generation-inference - transformers - unsloth - qwen3_5 - openclaw - agentscope - opus - opus-4.6 - qwen - reasoning - chain-of-thought - conversational - unsloth - lora - agentic - tool-use - text-generation license: apache-2.0 language: - en - ar - es - la - tr - de - cs - ch - zh datasets: - nohurry/Opus-4.6-Reasoning-3000x-filtered - Roman1111111/claude-opus-4.6-10000x - ykarout/open-r1-sampled - ykarout/Opus-4.6-reasoning-sft-12k base_model: - ykarout/Qwen3.5-9b-Opus-Openclaw-Distilled - Qwen/Qwen3.5-9B - agentscope-ai/CoPaw-Flash-9B library_name: transformers --- # Uploaded finetuned model - **Developed by:** ykarout - **License:** apache-2.0 This qwen3_5 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library. [](https://github.com/unslothai/unsloth) # Qwen3.5-9B-Opus-OpenClaw-Distilled **Qwen3.5-9B-Opus-OpenClaw-Distilled** is a reasoning-first, agentically-tuned derivative of **Qwen3.5-9b**, built to fuse two strengths into one model identity: - **OpenClaw & CoPaw’s operational / agentic instincts** - **Claude Opus-style structured reasoning distillation** The goal is simple: Use a strong base mode --> tune for agentic harness like openclaw and agentscope --> distill opus-4.6 level reasoning --> best of both worlds ## TL;DR It is designed for users who want: - preserved chat + strong agentic usefulness from the Openclaw / CoPaw lineage - a model that feels more “planner + operator” than just “chatbot” Recommended sampling parameters: - `temperature=0.6` - `top_p=0.95` - `min_p=0.0` - `top_k=20` - `repeat_penalty=1.0` - `presence_penalty=0.0` ## Special Instructions for Ollama Only The GGUF that works correctly with Ollama is the vision-merged file as Ollama only accepts a single GGUF for loading from Modelfile - `Qwen3.5-9b-Opus-Openclaw-Distilled-vision-merged-Q6_K.gguf` This file already has the multimodal weights merged into the main GGUF, so you should use it directly as the `FROM` target in your `Modelfile`. ### 1. Download the GGUF If you want to download it manually from this repo: ```bash huggingface-cli download ykarout/Qwen3.5-9b-Opus-Openclaw-Distilled-GGUF Qwen3.5-9b-Opus-Openclaw-Distilled-vision-merged-Q6_K.gguf --local-dir . ``` ### 2. Create a `Modelfile` Save the following as `Modelfile` in the same folder as the GGUF: ```text FROM ./Qwen3.5-9b-Opus-Openclaw-Distilled-vision-merged-Q6_K.gguf TEMPLATE {{ .Prompt }} RENDERER qwen3.5 PARSER qwen3.5 PARAMETER temperature 0.6 PARAMETER top_p 0.95 PARAMETER min_p 0.0 PARAMETER top_k 20 PARAMETER repeat_penalty 1.0 PARAMETER presence_penalty 0.0 ``` ### 3. Create the Ollama model ```bash ollama create qwen3.5-9b-opus-openclaw:Q6_K -f Modelfile ``` ### 4. Run it ```bash ollama run qwen3.5-9b-opus-openclaw:Q6_K ``` ### Notes - Use the `vision-merged` GGUF is for Ollama only. - All other GGUFs work out of the box with LMStudio and llama.cpp with text + vision ## Why this model exists `CoPaw-Flash-9B` is already a highly interesting Qwen3.5-based model family member with explicit optimization for agentic behavior such as tool invocation, command execution, memory management, and multi-step planning. Opus builds on top of that foundation instead of starting from a plain base model. The idea is to preserve that practical “gets things done” behavior while injecting denser and more structured reasoning traces through supervised fine-tuning. At the same time, the inspiration for the reasoning side of this model comes from recent Qwen3.5 reasoning distillations trained with Opus-derived trajectories. In particular, models like `Jackrong/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled` emphasize ``-structured reasoning, response-only training, and normalized reasoning/answer formatting. ## Model identity The Model is intended to sit at the intersection of: - **agentic chat utility** - **structured reasoning** - **practical local deployment** - **Qwen3.5 ecosystem compatibility** The intended vibe is: > **Qwen3.5 + OpenClaw reflexes + Opus-style reasoning scaffolds** In practice, that means the model is aimed at tasks like: - analytical QA - coding support - workflow planning - terminal / tool-oriented prompting - multi-step decomposition - logic-heavy conversations - “think first, answer second” style interactions ## Base model - **Base family:** Qwen3.5-9b - **Immediate base:** `CoPaw-Flash-9B` --> A fine-tune that exhibits much higher agentic capabilities in harnesses like OpenClaw and AgentScope ## Training concept This model was trained as a **text-only reasoning SFT** derivative focused on preserving and reinforcing the format: ```text ... final answer ``` The overall training philosophy is aligned with reasoning-distillation approaches that emphasize: - response-only loss masking - explicit `` formatting - structured step-by-step reasoning before the final answer ## Datasets The training recipe is centered on a unified reasoning dataset built from: - `Roman1111111/claude-opus-4.6-10000x` - `Crownelius/Opus-4.6-Reasoning-3300x` These were normalized into a single conversational SFT dataset: - `ykarout/Opus-4.6-reasoning-sft-12k` ### Dataset processing highlights The dataset was cleaned and unified so both sources follow the same final structure: - `messages`-based conversational schema - assistant output normalized into: - ` ... ` - followed by the final answer - generic repeated system prompts removed where appropriate - token-length profile measured after rendering with the target tokenizer chat template This makes the training corpus more consistent and more directly usable in TRL / Unsloth conversational SFT pipelines. ## Training recipe High-level recipe: - **Framework:** Unsloth - **Method:** LoRA SFT - **Objective:** improve structured reasoning while retaining CoPaw-style usefulness - **Loss behavior:** train on assistant responses / completions only - **Format target:** explicit `` reasoning followed by answer - **Text-only setup:** no vision-layer fine-tuning path used ## What changed versus CoPaw-Flash-9B This is not presented as a replacement for CoPaw-Flash-9B’s original design goals. Instead, it pushes the model further toward: - more explicit reasoning traces - more deliberate planning language - cleaner internal decomposition on complex tasks - stronger “reason-then-answer” behavior ## Intended use Model is best suited for: - Agentic harnesses like OpenClaw, Claude Code, OpenCode, AgentScope etc.. - deep analytical prompting - code and debugging assistance - local agent workflows - logic / math / structured breakdown tasks It is a particularly natural fit for prompts where you want the model to: 1. parse the task carefully 2. build a plan 3. utilize different tools 4. then produce a clean answer or action ## Limitations - This is still an autoregressive language model and can hallucinate. - Strong reasoning style does not guarantee factual correctness. - More visible reasoning can sometimes increase verbosity. - Distillation can improve structure without perfectly reproducing frontier-model judgment. - Depending on the prompt mix, some behaviors may lean more “reasoning-first” than “tool-first.” ## Acknowledgements Huge credit goes to the upstream work that made this possible: - `agentscope-ai/CoPaw-Flash-9B` - `Roman1111111/claude-opus-4.6-10000x` - `Crownelius/Opus-4.6-Reasoning-3300x` - `Jackrong/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled` - the broader Qwen / Unsloth ecosystem ## Citation / lineage notes If you use this model, please also acknowledge the upstream projects and datasets it builds on. **Qwen3.5-9B-Opus-OpenClaw-Distilled** is for people who want a model that doesn’t just answer — it **locks in, thinks cleanly, and then strikes.**