Instructions to use macmacmacmac/Sev-4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use macmacmacmac/Sev-4B with PEFT:
from peft import PeftModel from transformers import AutoModel base_model = AutoModel.from_pretrained("Qwen/Qwen3.5-4B-Base") model = PeftModel.from_pretrained(base_model, "macmacmacmac/Sev-4B") - Notebooks
- Google Colab
- Kaggle
Download training_metrics.json from macmacmacmac/Sev-4B: direct link, hf CLI and curl.
- Browser
- Download file 318 Bytes
-
https://huggingface.co/macmacmacmac/Sev-4B/resolve/main/training_metrics.json
- Command line
-
hf download hf://macmacmacmac/Sev-4B/training_metrics.json
-
curl -L -o training_metrics.json https://huggingface.co/macmacmacmac/Sev-4B/resolve/main/training_metrics.json
318 Bytes
| { | |
| "wall_seconds": 232.53715324401855, | |
| "records_seen": 615, | |
| "requested_records": 615, | |
| "truncated_records": 0, | |
| "rejected_records": 0, | |
| "optimizer_steps": 80, | |
| "forward_tokens": 209595, | |
| "peak_device_bytes": 20358582784, | |
| "device": "cuda", | |
| "dtype": "bf16", | |
| "batch": 4, | |
| "peak_rss_bytes": 31542779904 | |
| } | |