Text Classification
Transformers
Safetensors
English
gemma3_text
gemma3
tunix
candidate-scoring
gemmajev
text-embeddings-inference
Instructions to use bzantium/gemma-3-270m-jev with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use bzantium/gemma-3-270m-jev with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="bzantium/gemma-3-270m-jev")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("bzantium/gemma-3-270m-jev") model = AutoModelForSequenceClassification.from_pretrained("bzantium/gemma-3-270m-jev", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download validation.json from bzantium/gemma-3-270m-jev: direct link, hf CLI and curl.
- Browser
- Download file 402 Bytes
-
https://huggingface.co/bzantium/gemma-3-270m-jev/resolve/main/validation.json
- Command line
-
hf download hf://bzantium/gemma-3-270m-jev/validation.json
-
curl -L -o validation.json https://huggingface.co/bzantium/gemma-3-270m-jev/resolve/main/validation.json
402 Bytes
| { | |
| "status": "passed", | |
| "reference_questions": 40, | |
| "changed_decisions": 0, | |
| "max_probability_difference": 2.9895792783563024e-06, | |
| "probability_tolerance": 0.0001, | |
| "precision": "float32", | |
| "versions": { | |
| "torch": "2.9.1+cpu", | |
| "transformers": "4.57.6" | |
| }, | |
| "scope": "40 fixed validation questions: 32 Maze movement and 8 ViZDoom. Runtime conversion check, not a new task benchmark." | |
| } | |