Instructions to use Hodfa71/llama-3.2-1b-da-saga-delta-dpo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use Hodfa71/llama-3.2-1b-da-saga-delta-dpo with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-3.2-1B") model = PeftModel.from_pretrained(base_model, "Hodfa71/llama-3.2-1b-da-saga-delta-dpo") - Notebooks
- Google Colab
- Kaggle
llama-3.2-1b-da-saga-delta-dpo
Llama-3.2-1B DA Delta-DPO (Danish grammar, Emil Wiman)
Part of the SAGA project.
Results
| Metric | Base | + Δ-DPO |
|---|---|---|
| Parse success | 77.0% | (pending eval) |
- Downloads last month
- -
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for Hodfa71/llama-3.2-1b-da-saga-delta-dpo
Base model
meta-llama/Llama-3.2-1B