Model · Hugging Face
Davd-b01/qwen3.8-flash-next-40b-prune-research
| Author / organization | Davd-b01 |
|---|---|
| License (as declared) | apache-2.0 |
| Downloads | 2.4K (as reported by Hugging Face) |
| Likes | 5 |
| Task | text-generation |
| Library | transformers |
| Created | 19 September 2026 |
| Last updated at source | — |
Popularity, last 3 days
2,441 now (+42 since 2026-10-16). Counts as reported by the source, snapshotted daily by Silytics.
Connected in the knowledge graph
- Qwen/Qwen3.8-Flash-NextModel · trained on
- Davd-b01/thinking-cap-tier-lima-denseDataset · trained on
- Davd-b01/thinking-cap-tier-raw-tracesDataset · trained on
- Training-Free Halving of Activated Experts in Fine-Grained Mixture-of-Experts ModelsPaper · cites
- Half the Experts, All the Code: One-Shot Domain Pruning of Mixture-of-Experts LLMs for CodingPaper · cites
- Davd-b01/thinking-cap-tier-curricula-completeDataset · trained on
- UMoE:Unlocking Every Expert in Domain-Specific TrainingPaper · cites
- When Load-Balancing Goes Too Far: Expert Pruning in Over-Dispersed Mixture-of-Experts ModelsPaper · cites
- MAPLE: MoE Adaptive Plug-and-play Layer-wise Expert allocationPaper · cites
- Is MoE Routing a Huffman Code? Discovering the Frequency-Diversity Law in Chain-of-ThoughtPaper · cites
- Benchmarking Composable Compression Techniques in Mixture-of-Experts LLMsPaper · cites
- Rebalancing Token Importance in Language Models with TF-IDF Weighted Cross-Entropy LossPaper · cites
Related papers
More from Davd-b01
Silytics shows public metadata from Hugging Face and links to the original. Information may be incomplete or out of date. Last refreshed 18 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.