Instructions to use ModelFarm/wisp-1.5b-engram-evoked with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ModelFarm/wisp-1.5b-engram-evoked with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("ModelFarm/wisp-1.5b-engram-evoked", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download runtime_config.json from ModelFarm/wisp-1.5b-engram-evoked: direct link, hf CLI and curl.
- Browser
- Download file 212 Bytes
-
https://huggingface.co/ModelFarm/wisp-1.5b-engram-evoked/resolve/main/runtime_config.json
- Command line
-
hf download hf://ModelFarm/wisp-1.5b-engram-evoked/runtime_config.json
-
curl -L -o runtime_config.json https://huggingface.co/ModelFarm/wisp-1.5b-engram-evoked/resolve/main/runtime_config.json
212 Bytes
| { | |
| "method": "engram", | |
| "base_model": "Qwen/Qwen2.5-1.5B-Instruct", | |
| "persona": "Wisp the Friendly Ghost", | |
| "system_prompt": null, | |
| "vector_file": "persona_vector.pt", | |
| "alpha": 1.0, | |
| "layer": 20 | |
| } |