reaperdoesntknow/Qwen3-1.7B-Distilled-30B-A3B
Text Generation • 2B • Updated • 3.57k • • 2
DistilQwen
H100 BF16. 30B→1.7B/0.6B TKD. Three teachers. 15 models + DISC paper. 10K+ downloads. DOI: 10.57967/hf/8165 & 10.57967/hf/8194
Note First in the DistilQwen chain. Foundation for all downstream models.
reaperdoesntknow/Qwen3-1.7B-Distilled-30B-A3B-SFT-GGUF
Text Generation • 2B • Updated • 2.96kNote Edge deployment of the full Instruct pipeline. Apache 2.0.
reaperdoesntknow/Qwen3-1.7B-Distilled-30B-A3B-SFT
2B • Updated • 353Note Instruct distillation + SFT. Full precision. BF16 H100.
reaperdoesntknow/Qwen3-0.6B-Distilled-30B-A3B
Text Generation • 0.8B • Updated • 3.41k •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 • 3.41k • • 2Note Thinking teacher + SFT at 0.6B. Extended deliberation traces.
reaperdoesntknow/Qwen3-0.6B-Distilled-30B-A3B-Thinking-SFT-GGUF
Text Generation • 0.8B • Updated • 3kNote Thinking-SFT at 0.6B quantized. Runs on anything.
reaperdoesntknow/Qwen3-1.7B-Coder-Distilled-SFT
Text Generation • 2B • Updated • 3.45k • 1Note Coder teacher produces uniquely structured distributions.
reaperdoesntknow/Qwen3-1.7B-Coder-Distilled-SFT-GGUF
Text Generation • 2B • Updated • 3.28k • 1Note Pair with Thinking variant for comparative analysis.
reaperdoesntknow/DistilQwen3-1.7B-uncensored
Text Generation • 2B • Updated • 2.67k •Note Uncensored base distillation. No alignment filtering.
reaperdoesntknow/TopologicalQwen
Text Generation • 2B • Updated • 4.04k • • 1Note TKD flagship. BV decomposition → jump detection → curriculum.
reaperdoesntknow/DiStil-Qwen3-1.7B-uncensored
2B • Updated • 344 • 1Note Named for Discrepancy Calculus influence on training signal.
reaperdoesntknow/Disctil-Qwen3-1.7B
Text Generation • 2B • Updated • 2.65k •Note Structural refinement via DISC operator before TKD stage.
reaperdoesntknow/DistilQwen3-1.7B-uncensored-GGUF
2B • Updated • 2.69k • 1Note Edge deployment for research. No alignment filtering. Apache 2.0.
reaperdoesntknow/Qwen3-1.7B-Thinking-Distil
Text Generation • 2B • Updated • 3.61k • • 2Note Extended deliberation from 30B-Thinking → 1.7B student.
reaperdoesntknow/LFM2.5-1.2B-Distilled-SFT
Text Generation • 1B • Updated • 2.86kNote Proves TKD works across architecture families, not just within Qwen.
reaperdoesntknow/Discrepancy_Calculus
UpdatedNote Continuous Thought Dynamics — mathematical backbone of DualMind.