dgpl/dgpl-experimental-1
just landedmodel
Text generation model from dgpl (HF pipeline tag; the card has no one-line description). Mixture-of-experts, 145M active (16 experts, 2 per token). Context: 1M tokens (config). License: apache-2.0. Vendor-reported: "Active Compute: $\le 144.71\text{M}$ parameters per token (Top-2 Routed of 15 SwiGLU Experts + 1 Shared Expert)."
- Vendor-reported: Active Compute: $\le 144.71\text{M}$ parameters per token (Top-2 Routed of 15 SwiGLU Experts + 1 Shared Expert).
- Org
- dgpl
- Released
- 2026-09-30
- Status
- just landed
- License
- apache-2.0 (permissive)
- Parameters
- total, 145M active
- Architecture
- MoE · 16 experts, 2/token · SparkXForCausalLM
- Context
- 1,048,576 tokens
- Task
- text-generation · text
- Signal
- 0 HF likes · 45194 downloads
Links
First published here 2026-09-30 · updated 2026-10-25 · markdown · JSON