mrleo1nid/gpu-rent
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Seed Assistent personas from a shelf folder instead of yaml prompts.

Browse Source 
Push assistent-personas/ JSON overlays without wiping VM clones or exact.controls.

Co-authored-by: Cursor <cursoragent@cursor.com>
This commit is contained in:
Leonid Pershin
2026-08-22 01:48:01 +03:00
co-authored by Cursor
parent 03ba4cb6ed
commit 7be2c27a67
13 changed files with 187 additions and 129 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/llm.md
+1 -1
View File
@@ -113,7 +113,7 @@ Unit `gpu-rent-ollama` читает `/mnt/swarm_data/.gpu-rent-gpu.json`:
\*Flash на Ampere+ (compute ≥ 8.0). `NUM_PARALLEL=2`, `MAX_LOADED_MODELS=2` (chat VL + memory embed). Memory models use `use: memory` and a CPU Modelfile (`num_gpu 0`) so embed does not steal VRAM from the chat model. Ollama default `num_ctx` is 4096; we set `OLLAMA_CONTEXT_LENGTH` so Assistent + vision fits. Mid/high keep-alive is **5m** because Assistent parks the chat model before Generate (`AssistentParkLlm`) and warms after. Env: `/mnt/swarm_data/.gpu-rent-ollama.env`.
Personas: laptop `assistent-personas.yaml` → on `up` / `seed-personas` overlay folders under `/mnt/swarm_data/Assistent/personas/<id>/` (+ `_base/assistant.json` with `default_persona` / `num_ctx`). See [extensions.md](extensions.md).
Personas: laptop `assistent-personas/` → on `up` / `seed-personas` overlay folders under `/mnt/swarm_data/Assistent/personas/<id>/` (+ `_base/assistant.json` with `default_persona` / `num_ctx`). Shelves are short JSON files (not a long prompt). See [extensions.md](extensions.md).
`ollama-models.yaml` entries: