Instructions to use amirdnc/HeQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use amirdnc/HeQ with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "question-answering" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # pip install "transformers<5.0.0" from transformers import pipeline pipe = pipeline("question-answering", model="amirdnc/HeQ")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForQuestionAnswering tokenizer = AutoTokenizer.from_pretrained("amirdnc/HeQ") model = AutoModelForQuestionAnswering.from_pretrained("amirdnc/HeQ", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download eval_results.json from amirdnc/HeQ: direct link, hf CLI and curl.
- Browser
- Download file 115 Bytes
-
https://huggingface.co/amirdnc/HeQ/resolve/main/eval_results.json
- Command line
-
hf download hf://amirdnc/HeQ/eval_results.json
-
curl -L -o eval_results.json https://huggingface.co/amirdnc/HeQ/resolve/main/eval_results.json
115 Bytes
| { | |
| "epoch": 15.0, | |
| "eval_samples": 1666, | |
| "exact_match": 61.359093937375086, | |
| "f1": 70.77972929660706 | |
| } |