xtools-at

DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic

README

License: apache-2.0

Arbitrary-Rank Ablation (ARA) parameters

Table with columns: Parameter, Value
Parameter	Value
start_layer_index	9
end_layer_index	24
preserve_good_behavior_weight	0.8264
steer_bad_behavior_weight	0.0003
overcorrect_relative_weight	0.9645
neighbor_count	12

Performance

Table with columns: Metric, This model, Original model (a model)
Metric	This model	Original model (a model)
Refusals	3/100	100/100
KL divergence	0.0422	0 (by definition)

🤝 Collaboration & Training Support

🔬 1. Distillation & Training Data

📊 2. Benchmark Results

2.1 GSM8K

The NVFP4 checkpoint was evaluated on GSM8K four times, and the resulting scores were averaged. Its four-run mean accuracy is 94.50% under vLLM. In the comparison supplied with this release, the 9B student slightly exceeds the reported DeepSeek-V4-Pro teacher result and approaches the Llama-3.3-70B-Instruct reference.

2.2 MMLU-Pro: Math, Physics & Chemistry

Each model was evaluated on 500 questions from each of three MMLU-Pro subsets—Math, Physics, and Chemistry—for 1,500 questions per model. In this reported comparison, DeepSeek-V4-Pro-Qwen3.5-9B achieves the highest average at 90.53%. Its compact 4B sibling is now included alongside the Qwen and Claude Mythos-distilled references.

2.3 Inference Efficiency

🛠️ 3. Generalization Beyond the Training Mix

✅ 4. Instruction Following & Output-Format Compliance

🎮 Game Showcase: Star Skip by Kyle

🎯 5. Recommended Uses

Mathematical problem solving and step-by-step derivation
Physics, chemistry, and broader STEM question answering
Structured reasoning and analytical instruction following
Research on reasoning distillation and cross-domain SFT transfer
Experimental tool-calling or programming workflows where outputs are independently validated

⚠️ 6. Limitations

This is an experimental 9B community model and remains subject to hallucinations, reasoning errors, and unstable behavior on difficult or underspecified tasks.
The reported MMLU-Pro results are based on 500 randomly sampled questions from each of the Math, Physics, and Chemistry subsets, rather than the complete subsets; they are not a comprehensive capability or safety evaluation.
GSM8K and MMLU-Pro used different inference builds and backends, so their scores should not be used to infer quantization equivalence.
Programming and tool-use gains were observed without direct coding supervision but are described only as small, preliminary generalization gains.
Users should independently verify high-stakes mathematical, scientific, or factual outputs.

📚 7. Resources, Acknowledgements & Citation

Available on FriendliAI

Dedicated Endpoints

Run this model inference on single tenant GPU with unmatched speed and reliability at scale.

Learn more

Model Details

Model Provider

xtools-at

Model Tree

Base

Jackrong/DeepSeek-V4-Pro-Qwen3.5-9B

Fine-tuned

this model

Input Modalities

TextImageVideo

Output Modalities

Text

Supported Functionality