How to use zai-org/chatglm2-6b-int4 with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("zai-org/chatglm2-6b-int4", trust_remote_code=True, device_map="auto")
https://huggingface.co/zai-org/chatglm2-6b-int4/resolve/main/quantization.py
hf download hf://zai-org/chatglm2-6b-int4/quantization.py
curl -L -o quantization.py https://huggingface.co/zai-org/chatglm2-6b-int4/resolve/main/quantization.py
