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

Text Generation • 2B • Updated 9 days ago • 3.85k • 2

Note Base distillation. Instruct teacher → 1.7B student. BF16 H100.

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

Text Generation • 2B • Updated 9 days ago • 1.75k

Note Instruct teacher + SFT quantized. F16/Q4/Q5/Q8 available.

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

2B • Updated 9 days ago • 105

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

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

Text Generation • 0.8B • Updated 9 days ago • 3.65k

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 9 days ago • 3.81k • 2

Note The smallest model with Thinking teacher signal. 0.8B params.

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

Text Generation • 0.8B • Updated 9 days ago • 1.96k

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

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

Text Generation • 2B • Updated 9 days ago • 3.86k • 1

Note Different capability profile: hierarchical problem solving.

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

Text Generation • 2B • Updated 9 days ago • 1.9k • 2

Note Coder pipeline quantized. F16/Q4/Q5/Q8.

reaperdoesntknow/DistilQwen3-1.7B-uncensored

Text Generation • 2B • Updated 9 days ago • 2.9k

Note Starting point for custom SFT pipelines.

reaperdoesntknow/TopologicalQwen

Text Generation • 2B • Updated 9 days ago • 4.62k • 1

Note The model that proved ghost imprinting — literary from physics data.

reaperdoesntknow/DiStil-Qwen3-1.7B-uncensored

2B • Updated 9 days ago • 384 • 1

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

reaperdoesntknow/Disctil-Qwen3-1.7B

Text Generation • 2B • Updated 9 days ago • 2.64k • 1

Note Key link in the chain: DiStil → Disctil → TopologicalQwen.

reaperdoesntknow/DistilQwen3-1.7B-uncensored-GGUF

2B • Updated 9 days ago • 2.24k • 3

Note Edge deployment for research. No alignment filtering. Apache 2.0.

reaperdoesntknow/Qwen3-1.7B-Thinking-Distil

Text Generation • 2B • Updated 9 days ago • 3.96k • 2

Note Extended deliberation from 30B-Thinking → 1.7B student.

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

Text Generation • 1B • Updated 9 days ago • 2.96k

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

reaperdoesntknow/Discrepancy_Calculus

Updated 9 days ago

Note Continuous Thought Dynamics — mathematical backbone of DualMind.