Instructions to use davidkhjo/Tars with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use davidkhjo/Tars with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("davidkhjo/Tars", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download eval_results.json from davidkhjo/Tars: direct link, hf CLI and curl.
- Browser
- Download file 326 Bytes
-
https://huggingface.co/davidkhjo/Tars/resolve/main/eval_results.json
- Command line
-
hf download hf://davidkhjo/Tars/eval_results.json
-
curl -L -o eval_results.json https://huggingface.co/davidkhjo/Tars/resolve/main/eval_results.json
326 Bytes
| { | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.9172223210334778, | |
| "eval_margin": 0.109375, | |
| "eval_max_reward": 2.6875, | |
| "eval_mean_reward": 2.6328125, | |
| "eval_min_reward": 2.578125, | |
| "eval_num_tokens": 1778.0, | |
| "eval_runtime": 0.7199, | |
| "eval_samples_per_second": 1.389, | |
| "eval_steps_per_second": 1.389 | |
| } |