MLX
English
nima_joint_schema
tool-routing
decision-model
frozen-backbone
joint-schema
custom-code
research
Instructions to use neimand/nima with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use neimand/nima with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download neimand/nima --local-dir nima
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Download training_protocol.json from neimand/nima: direct link, hf CLI and curl.
- Browser
- Download file 391 Bytes
-
https://huggingface.co/neimand/nima/resolve/main/training_protocol.json
- Command line
-
hf download hf://neimand/nima/training_protocol.json
-
curl -L -o training_protocol.json https://huggingface.co/neimand/nima/resolve/main/training_protocol.json
391 Bytes
| { | |
| "protocol_id": "head-only-generalization-v2", | |
| "seed": 42, | |
| "train_views": 4, | |
| "selection_views": 2, | |
| "epochs": 80, | |
| "batch_size": 8, | |
| "learning_rate": 0.0003, | |
| "weight_decay": 0.01, | |
| "temperature": 1.0, | |
| "selection": "minimum mean cross-entropy over the predeclared selection views", | |
| "full_training_requires": "family-separated frozen dataset including confirmation split" | |
| } | |