Token Classification
Transformers
Safetensors
qwen2
Generated from Trainer
trl
stepwise-reward-trainer
text-generation-inference
Instructions to use plaguss/Qwen2.5-0.5B-Math-Shepherd-PRM-0.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use plaguss/Qwen2.5-0.5B-Math-Shepherd-PRM-0.1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="plaguss/Qwen2.5-0.5B-Math-Shepherd-PRM-0.1")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForTokenClassification tokenizer = AutoTokenizer.from_pretrained("plaguss/Qwen2.5-0.5B-Math-Shepherd-PRM-0.1") model = AutoModelForTokenClassification.from_pretrained("plaguss/Qwen2.5-0.5B-Math-Shepherd-PRM-0.1", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download eval_results.json from plaguss/Qwen2.5-0.5B-Math-Shepherd-PRM-0.1: direct link, hf CLI and curl.
- Browser
- Download file 221 Bytes
-
https://huggingface.co/plaguss/Qwen2.5-0.5B-Math-Shepherd-PRM-0.1/resolve/main/eval_results.json
- Command line
-
hf download hf://plaguss/Qwen2.5-0.5B-Math-Shepherd-PRM-0.1/eval_results.json
-
curl -L -o eval_results.json https://huggingface.co/plaguss/Qwen2.5-0.5B-Math-Shepherd-PRM-0.1/resolve/main/eval_results.json
221 Bytes
| { | |
| "epoch": 0.9998485078018482, | |
| "eval_accuracy": 0.9966811407126216, | |
| "eval_loss": 0.007363918237388134, | |
| "eval_runtime": 104.8675, | |
| "eval_samples_per_second": 212.001, | |
| "eval_steps_per_second": 6.627 | |
| } |