reaperdoesntknow/Qwen3-1.7B-Distilled-30B-A3B

Text Generation • 2B • Updated about 7 hours ago • 5.5k • 1

Note 30B teacher, 1.7B student. Proof-weighted KD at 2.25× on reasoning.

reaperdoesntknow/Qwen3-1.7B-Distilled-30B-A3B-SFT-GGUF

Text Generation • 2B • Updated about 7 hours ago • 1.63k

Note Most downloaded GGUF in the collection. CPU-friendly.

reaperdoesntknow/Qwen3-1.7B-Distilled-30B-A3B-SFT

2B • Updated about 7 hours ago • 1.14k

Note Second stage: distil → SFT on instruction-following data.

reaperdoesntknow/Qwen3-0.6B-Distilled-30B-A3B

Text Generation • 0.8B • Updated about 7 hours ago • 5.29k

Note 0.6B student. Proves the methodology works at extreme scales.

reaperdoesntknow/Qwen3-0.6B-Distilled-30B-A3B-Thinking-SFT

Text Generation • 0.8B • Updated about 7 hours ago • 5.35k • 2

Note Higher-entropy teacher distributions → richer student representations.

reaperdoesntknow/Qwen3-0.6B-Distilled-30B-A3B-Thinking-SFT-GGUF

Text Generation • 0.8B • Updated about 7 hours ago • 1.65k

Note mradermacher also auto-quantized this one — 420+ shadow downloads.

reaperdoesntknow/Qwen3-1.7B-Coder-Distilled-SFT

Text Generation • 2B • Updated about 7 hours ago • 5.79k • 1

Note Different capability profile: hierarchical problem solving.

reaperdoesntknow/Qwen3-1.7B-Coder-Distilled-SFT-GGUF

Text Generation • 2B • Updated about 7 hours ago • 2.12k

Note Structured reasoning for edge deployment. Apache 2.0.

reaperdoesntknow/DistilQwen3-1.7B-uncensored

Text Generation • 2B • Updated about 7 hours ago • 5.57k

Note Uncensored base distillation. No alignment filtering.

reaperdoesntknow/TopologicalQwen

Text Generation • 2B • Updated about 7 hours ago • 6.67k

Note TKD flagship. BV decomposition → jump detection → curriculum.

reaperdoesntknow/DiStil-Qwen3-1.7B-uncensored

2B • Updated about 7 hours ago • 1.92k

Note DISC-informed distillation. Uncensored. Research-focused.

reaperdoesntknow/Disctil-Qwen3-1.7B

Text Generation • 2B • Updated about 7 hours ago • 5.18k

Note DISC-refined. Discrepancy-aware training produces cleaner signal.

reaperdoesntknow/DistilQwen3-1.7B-uncensored-GGUF

2B • Updated about 7 hours ago • 2.11k • 1

Note Community validated — third-party quantizations exist.

reaperdoesntknow/Qwen3-1.7B-Thinking-Distil

Text Generation • 2B • Updated about 7 hours ago • 6.47k • 1

Note The most popular model. Thinking teacher = richest signal.

reaperdoesntknow/LFM2.5-1.2B-Distilled-SFT

Text Generation • 1B • Updated about 7 hours ago • 1.33k

Note Proves TKD works across architecture families, not just within Qwen.

reaperdoesntknow/Discrepancy_Calculus

Updated about 7 hours ago

Note Continuous Thought Dynamics — mathematical backbone of DualMind.