Instructions to use Meanblock/JEV-CPU with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Meanblock/JEV-CPU with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("zero-shot-classification", model="Meanblock/JEV-CPU")# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Meanblock/JEV-CPU", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download tests/test_serial.py from Meanblock/JEV-CPU: direct link, hf CLI and curl.
- Browser
- Download file 735 Bytes
-
https://huggingface.co/Meanblock/JEV-CPU/resolve/main/tests/test_serial.py
- Command line
-
hf download hf://Meanblock/JEV-CPU/tests/test_serial.py
-
curl -L -o test_serial.py https://huggingface.co/Meanblock/JEV-CPU/resolve/main/tests/test_serial.py
735 Bytes
| from semif_phase1.serial import _state_prefix | |
| class Tokenizer: | |
| def apply_chat_template(self, turns, tokenize=False, add_generation_prompt=True, enable_thinking=False): | |
| assert tokenize is False and add_generation_prompt is True and enable_thinking is False | |
| return "HEADER\n" + turns[-1]["content"] + "\nASSISTANT" | |
| def encode(self, text, add_special_tokens=False): | |
| assert add_special_tokens is False | |
| return list(text.encode()) | |
| def test_state_prefix_stops_before_runtime_question_and_options(): | |
| prefix = bytes(_state_prefix(Tokenizer(), "owned state")).decode() | |
| assert "owned state" in prefix | |
| assert "prefix boundary placeholder" not in prefix | |
| assert '"options"' not in prefix | |