bzuccaro/LLM-Labs-Local
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Align installer with updated lab models

Browse Source
This commit is contained in:
OpenCode
2026-04-24 20:08:56 -06:00
parent 7360cd040a
commit e915d87ec6
6 changed files with 16 additions and 52 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+6 -5
View File
@@ -23,15 +23,16 @@ This project builds a student-friendly local lab environment for the courseware
Lab 1 is now provisioned directly by the installer:
- The `Qwen3-0.6B-Q8_0.gguf` and `Llama-3.2-1B.Q4_K_M.gguf` files are mirrored into `state/models/lab1/`.
- The Qwen GGUF is pre-registered in Ollama as `lab1-qwen3-0.6b-q8_0`.
- The wiki serves same-host download links for both GGUFs through `/api/lab1/models/...`.
- The `Llama-3.2-1B.Q4_K_M.gguf` file is mirrored into `state/models/lab1/`.
- The Lab 1 confidence widget uses the pre-pulled Gemma 4 E2B Q4 Ollama model, `batiai/gemma4-e2b:q4`.
- The wiki serves a same-host download link for the Llama GGUF through `/api/lab1/models/...`.
- Lab 1 confidence visualization requires Ollama `0.12.11` or newer because it depends on logprobs.
## Lab 2 Defaults
`./labctl up` now pre-pulls the Lab 2 Gemma 4 E2B Ollama variants used by the wiki widget:
`./labctl up` now pre-pulls the Gemma 4 E2B Ollama variants used by the wiki widgets:
- `cajina/gemma4_e2b-q2_k_xl:v01`
- `batiai/gemma4-e2b:q4`
- `batiai/gemma4-e2b:q6`
@@ -97,7 +98,7 @@ If CUDA is already mounted or preinstalled outside `PATH`, the installer detects
- The default deployment is centered on Ollama-backed local inference and browser-based tools such as Netron and the wiki.
- Netron is installed into a managed Python virtual environment and served locally instead of being provisioned as a desktop package.
- Lab 1 model downloads are mirrored locally during `./labctl up`, so students do not have to fetch them manually from the original source.
- Lab 1's Llama GGUF download is mirrored locally during `./labctl up`, so students do not have to fetch it manually from the original source.
- WhiteRabbitNeo assets remain a separate Lab 2 flow and are still handled outside the default `./labctl up` run.
- Run `./labctl assets lab2` when you want to populate repo-local Lab 2 assets in `assets/lab2/` from Hugging Face.
- After base setup, run `state/lab2/download_whiterabbitneo-gguf.sh` to fetch only the `Q4_K_M`, `Q8_0`, and `IQ2_M` files from `bartowski/WhiteRabbitNeo_WhiteRabbitNeo-V3-7B-GGUF` and register local Ollama models `WhiteRabbitNeo`, `WhiteRabbitNeo-Q4`, `WhiteRabbitNeo-Q8`, and `WhiteRabbitNeo-IQ2`.