Downloads · 30 days
0
virgil-meeting-e4b-a_v41
lightsofapollo/virgil-meeting-e4b-a_v41
virgil-meeting-e4b-a_v41 is a machine learning model from lightsofapollo. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Meeting-synthesis split-LoRA bundle for the Virgil desktop in-process engine.
Access
Public
Updated Jun 11, 2026
Repo size
339 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors339 MB · 100%
At a glance
- Access
- Public
- Created
- Jun 11, 2026
- Updated
- Jun 11, 2026
- SHA
- 1d31fd09
Base models
Model card
From the Hugging Face model README
virgil-meeting-e4b-a_v41
Meeting-synthesis split-LoRA bundle for the Virgil desktop in-process engine.
adapters/primary— EXTRACT, A_v41: trained on the KV-prefix-cache-friendly prompt order (participants, recent_context, open_state_items, writable_new_chunk). A_v39's exact recipe; only the section layout differs. Pairs withrender_extract_promptas of runpod-jobs commit 68401685f — renderer and adapter must ship together (either alone is off-format).adapters/fallback— RECONCILE, unchanged from the a_v32 bundle (a_v30 reconcile). The format change does not touch the reconcile prompt.
- Created
- Jun 11, 2026
- Updated
- Jun 11, 2026