Parameter	Value
start_layer_index	2
end_layer_index	12
preserve_good_behavior_weight	0.0192
steer_bad_behavior_weight	0.6489
overcorrect_relative_weight	0.1830
neighbor_count	1

Performance

Metric	This model	Original model (Jackrong/Qwen3.5-0.8B-Claude-4.6-Opus-Reasoning-Distilled)
KL divergence	0.0446	0 (by definition)
Refusals	6/100	73/100

🌟 Qwen3.5-0.8B-Claude-4.6-Opus-Reasoning-Distilled

💡 Model Introduction

Qwen3.5-2B-Claude-4.6-Opus-Reasoning-Distilled is a highly capable reasoning model fine-tuned on top of the Qwen3.5-0.8B 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 <think> tags, and ultimately delivering precise, nuanced solutions.

🗺️ Training Pipeline Overview

text

Base Model (Qwen3.5-0.8B)
 │
 ▼
Supervised Fine-Tuning (SFT) + LoRA
(Response-Only Training masked on "<|im_start|>assistant\n<think>")
 │
 ▼
Final Model Text Only (Qwen3.5-0.8B-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 <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 (2,516 samples total after filtering):

Dataset Name	Description / Purpose
nohurry/Opus-4.6-Reasoning-3000x-filtered	Provides comprehensive Claude 4.6 Opus reasoning trajectories.
TeichAI/claude-4.5-opus-high-reasoning-250x	Injecting high-intensity, structured reasoning instances.
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

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.
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.
This model is a test version intended solely for learning and demonstration purposes, and is for academic research and technical exploration use only.

🙏 Acknowledgements

Significant thanks to the 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).

dalatexcoder/Qwen3.5-0.8B-Claude-4.6-Opus-Reasoning-Distilled-heretic

This is a decensored version of Jackrong/Qwen3.5-0.8B-Claude-4.6-Opus-Reasoning-Distilled, made using Heretic v1.2.0 with the Arbitrary-Rank Ablation (ARA) method (with row-norm preservation)

Abliteration parameters