reaperdoesntknow/Qwen3-1.7B-Distilled-30B-A3B
Text Generation • 2B • Updated • 4.63k
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 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 • 1.48kNote Most downloaded GGUF in the collection. CPU-friendly.
reaperdoesntknow/Qwen3-1.7B-Distilled-30B-A3B-SFT
2B • Updated • 1.13kNote Source model for the SFT-GGUF quantizations.
reaperdoesntknow/Qwen3-0.6B-Distilled-30B-A3B
Text Generation • 0.8B • Updated • 4.42kNote 0.6B student. Proves the methodology works at extreme scales.
reaperdoesntknow/Qwen3-0.6B-Distilled-30B-A3B-Thinking-SFT
Text Generation • 0.8B • Updated • 4.45k • 2Note 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 • 1.53kNote Edge deployment of extended-thinking at 0.6B. Apache 2.0.
reaperdoesntknow/Qwen3-1.7B-Coder-Distilled-SFT
Text Generation • 2B • Updated • 5.15k • 1Note Coder teacher produces uniquely structured distributions.
reaperdoesntknow/Qwen3-1.7B-Coder-Distilled-SFT-GGUF
Text Generation • 2B • Updated • 1.86kNote Pair with Thinking variant for comparative analysis.
reaperdoesntknow/DistilQwen3-1.7B-uncensored
Text Generation • 2B • Updated • 4.85kNote Starting point for custom SFT pipelines.
reaperdoesntknow/TopologicalQwen
Text Generation • 2B • Updated • 5.57kNote Topology-aware distillation from 30B-Thinking on physics CoT.
reaperdoesntknow/DiStil-Qwen3-1.7B-uncensored
2B • Updated • 1.81kNote Bridge between base distil and topology-aware models.
reaperdoesntknow/Disctil-Qwen3-1.7B
Text Generation • 2B • Updated • 4.38kNote Key link in the chain: DiStil → Disctil → TopologicalQwen.
reaperdoesntknow/DistilQwen3-1.7B-uncensored-GGUF
2B • Updated • 1.57kNote Edge deployment for research. No alignment filtering. Apache 2.0.
reaperdoesntknow/Qwen3-1.7B-Thinking-Distil
Text Generation • 2B • Updated • 5.46k • 1Note Extended deliberation from 30B-Thinking → 1.7B student.
reaperdoesntknow/LFM2.5-1.2B-Distilled-SFT
Text Generation • 1B • Updated • 1.31kNote Proves TKD works across architecture families, not just within Qwen.
reaperdoesntknow/Discrepancy_Calculus
UpdatedNote Continuous Thought Dynamics — mathematical backbone of DualMind.