How to use KwangHwi/quantization with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="KwangHwi/quantization", trust_remote_code=True)
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("KwangHwi/quantization", trust_remote_code=True, device_map="auto")
https://huggingface.co/KwangHwi/quantization/resolve/main/__pycache__/llama_bidirectional_model.cpython-312.pyc
hf download hf://KwangHwi/quantization/__pycache__/llama_bidirectional_model.cpython-312.pyc
curl -L -o llama_bidirectional_model.cpython-312.pyc https://huggingface.co/KwangHwi/quantization/resolve/main/__pycache__/llama_bidirectional_model.cpython-312.pyc
