Instructions to use infosave/Nanbeige4.2-3Bcmf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- cortiq
How to use infosave/Nanbeige4.2-3Bcmf with cortiq:
# one Rust binary, no additional dependencies cargo install cortiq-cli # or a prebuilt binary from github.com/infosave2007/cmf/releases hf download infosave/Nanbeige4.2-3Bcmf --include "*.cmf" --local-dir . ls *.cmf # some repos ship more than one quantization
cortiq run FILE.cmf --prompt "What is the capital of France?"
cortiq serve FILE.cmf --port 8080 # OpenAI-compatible server
- Notebooks
- Google Colab
- Kaggle
Add Cortiq model metadata
Browse filesExplicitly classify this CMF conversion and expose its Cortiq task.
README.md
CHANGED
|
@@ -10,6 +10,7 @@ tags:
|
|
| 10 |
- looped-transformer
|
| 11 |
- reasoning
|
| 12 |
- quantized
|
|
|
|
| 13 |
---
|
| 14 |
|
| 15 |
# Nanbeige 4.2 3B — CMF q4t (2.4 GB, one file, no Python)
|
|
|
|
| 10 |
- looped-transformer
|
| 11 |
- reasoning
|
| 12 |
- quantized
|
| 13 |
+
base_model_relation: quantized
|
| 14 |
---
|
| 15 |
|
| 16 |
# Nanbeige 4.2 3B — CMF q4t (2.4 GB, one file, no Python)
|