base_model: Jackrong/DeepSeek-V4-Pro-Qwen3.5-9B
base_model_relation: finetune
tags:
- text-generation-inference
- transformers
- unsloth
- qwen3_5
- reasoning
- distillation
- deepseek
- sft
- rl
- gspo
- math
- stem
- tool-use
- function-calling
- mtp
- heretic
- uncensored
- decensored
- abliterated
license: apache-2.0
language: - en
- zh
- ko
- ja
- es
- ru
pipeline_tag: text-generation
This is a decensored version of Jackrong/DeepSeek-V4-Pro-Qwen3.5-9B, made using Heretic v2.0.0.dev0
Arbitrary-Rank Ablation (ARA) parameters
| 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
| 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.
| Model | Accuracy |
|---|---|
| MiMo-V2.5-Pro | 99.60% |
| Llama-3.1-405B-Instruct | 96.80% |
| Llama-3.3-70B-Instruct | 94.84% |
| DeepSeek-V4-Pro-Qwen3.5-9B | 94.50% |
| DeepSeek-V4-Pro | 92.60% |
| DeepSeek-V3 | 89.30% |
Evaluation configuration: DeepSeek-V4-Pro-Qwen3.5-9B-NVFP4 · NVFP4 (FP8 E4M3) · vLLM · four GSM8K test runs, with the final 94.50% reported as their arithmetic mean. The reference scores for the other models shown above are sourced from the openai/gsm8k repository.
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.
| Model | Evaluation Build | Math | Physics | Chemistry | Average |
|---|---|---|---|---|---|
| DeepSeek-V4-Pro-Qwen3.5-9B | MTP-Q8_0 GGUF | 92.40% | 89.40% | 89.80% | 90.53% |
| Qwen3.5-9B | MTP-Q8_0 GGUF | 90.60% | 89.00% | 89.20% | 89.60% |
| Claude Mythos-distilled 27B | MTP-Q8 GGUF | 88.40% | 87.60% | 82.60% | 86.20% |
| Claude Mythos-distilled 9B | MTP-Q8_0 GGUF | 86.00% | 78.60% | 78.60% | 81.07% |
| DeepSeek-V4-Pro-Qwen3.5-4B | MTP-Q8 GGUF | 80.40% | 74.20% | 74.80% | 76.47% |
📈 vs. Qwen3.5-9B
+1.80 points in Math, +0.40 in Physics, +0.60 in Chemistry, and +0.93 average points.
+1.80 points in Math, +0.40 in Physics, +0.60 in Chemistry, and +0.93 average points.
🧪 Evaluation setup
500 questions per subset · 1,500 total per model · llama.cpp. The 9B rows use MTP-Q8_0 GGUF at 8K context, the 4B student uses MTP-Q8 GGUF at 64K context, and Claude Mythos-distilled 27B uses MTP-Q8 GGUF at 32K context.
500 questions per subset · 1,500 total per model · llama.cpp. The 9B rows use MTP-Q8_0 GGUF at 8K context, the 4B student uses MTP-Q8 GGUF at 64K context, and Claude Mythos-distilled 27B uses MTP-Q8 GGUF at 32K context.
2.3 Inference Efficiency
| Model | Accuracy | Avg. Reasoning Tokens / Question |
Median | Tokens / Correct Answer |
Correct Answers / 1M Tokens |
|---|---|---|---|---|---|
| DeepSeek-V4-Pro-Qwen3.5-9B | 90.53% | 2,858 | 676 | 3,157 | 316.8 |
| Qwen3.5-9B | 89.60% | 4,425 | 3,214 | 4,938 | 202.5 |
| Claude Mythos-distilled 9B | 81.07% | 3,310 | 639 | 4,083 | 244.9 |
Metric notes: MMLU-Pro efficiency uses 1,500 questions per model and the supplied composite score for the final correct-answer total. “Tokens per correct answer” is total reasoning tokens divided by correct answers; “correct answers per 1M tokens” is the inverse throughput measure. Lower is better for token-cost metrics; higher is better for accuracy and correct-answer throughput. Comparison deltas follow the supplied composite-result calculations, so recomputing them only from the rounded display values may produce a 0.01-point difference. GSM8K statistics summarize the currently available NVFP4 raw trajectories and are reported separately from the MMLU-Pro MTP-Q8_0 comparison.
🛠️ 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.