Token Classification
Transformers
Safetensors
llama
Generated from Trainer
trl
stepwise-reward-trainer
text-generation-inference
Instructions to use plaguss/Llama-3.1-8B-Math-Shepherd-PRM-0.2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use plaguss/Llama-3.1-8B-Math-Shepherd-PRM-0.2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="plaguss/Llama-3.1-8B-Math-Shepherd-PRM-0.2")# Load model directly from transformers import AutoTokenizer, AutoModelForTokenClassification tokenizer = AutoTokenizer.from_pretrained("plaguss/Llama-3.1-8B-Math-Shepherd-PRM-0.2") model = AutoModelForTokenClassification.from_pretrained("plaguss/Llama-3.1-8B-Math-Shepherd-PRM-0.2", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "epoch": 0.9998485078018482, | |
| "eval_accuracy": 0.8658686686196745, | |
| "eval_loss": 0.3011157810688019, | |
| "eval_runtime": 142.4653, | |
| "eval_samples_per_second": 156.052, | |
| "eval_steps_per_second": 4.878 | |
| } |