FLCgeigeigei/tinyvision-vlm
archived · low-signalmodel
Image text to text model from FLCgeigeigei (HF pipeline tag; the card has no one-line description). Mixture-of-experts, 65M active (4 experts, 1 per token). Context: 32K tokens (config). License: apache-2.0. Vendor-reported: "Two variants: Dense (65.09M language parameters) and MoE (199.60M total / 65.12M activated per token, 4 experts with Top-1 routing)"
- Vendor-reported: Two variants: Dense (65.09M language parameters) and MoE (199.60M total / 65.12M activated per token, 4 experts with Top-1 routing)
- Org
- FLCgeigeigei
- Released
- 2026-11-12
- Status
- archived · low-signal
- License
- apache-2.0 (permissive)
- Parameters
- total, 65M active
- Architecture
- MoE · 4 experts, 1/token · TinyVisionVLM
- Context
- 32,768 tokens (config.json)
- Task
- image-text-to-text · vision
- Signal
- 2 HF likes · 228 downloads
- Archived
- 2026-11-16 (no longer listed by the collector; stats as last seen)
Links
First published here 2026-11-12 · updated 2026-11-16 · markdown · JSON