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

Text Generation • 2B • Updated 4 days ago • 3.25k • 2

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 4 days ago • 1.79k

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

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

2B • Updated 4 days ago • 96

Note Instruct distillation + SFT. Full precision. BF16 H100.

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

Text Generation • 0.8B • Updated 4 days ago • 3.06k

Note 50× compression: 30B → 0.6B. Smallest in the distil family.

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

Text Generation • 0.8B • Updated 4 days ago • 3.19k • 2

Note Higher-entropy teacher distributions → richer student representations.

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

Text Generation • 0.8B • Updated 4 days ago • 1.82k

Note Thinking-SFT at 0.6B quantized. Runs on anything.

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

Text Generation • 2B • Updated 4 days ago • 3.52k • 1

Note Coder teacher. Structured decomposition → STEM derivation.

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

Text Generation • 2B • Updated 4 days ago • 2.12k • 3

Note Structured reasoning for edge deployment. Apache 2.0.

reaperdoesntknow/DistilQwen3-1.7B-uncensored

Text Generation • 2B • Updated 4 days ago • 2.4k

Note Uncensored base distillation. No alignment filtering.

reaperdoesntknow/TopologicalQwen

Text Generation • 2B • Updated 4 days ago • 3.89k • 1

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

reaperdoesntknow/DiStil-Qwen3-1.7B-uncensored

2B • Updated 4 days ago • 330 • 1

Note Bridge between base distil and topology-aware models.

reaperdoesntknow/Disctil-Qwen3-1.7B

Text Generation • 2B • Updated 4 days ago • 2.2k • 1

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

reaperdoesntknow/DistilQwen3-1.7B-uncensored-GGUF

2B • Updated 4 days ago • 1.78k • 3

Note Uncensored base quantized. mradermacher also quantized — 411 downloads.

reaperdoesntknow/Qwen3-1.7B-Thinking-Distil

Text Generation • 2B • Updated 4 days ago • 3.34k • 2

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

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

Text Generation • 1B • Updated 4 days ago • 2.47k

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

reaperdoesntknow/Discrepancy_Calculus

Updated 4 days ago

Note Continuous Thought Dynamics — mathematical backbone of DualMind.