How to use zai-org/glm-10b-chinese with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="zai-org/glm-10b-chinese", trust_remote_code=True)
# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("zai-org/glm-10b-chinese", trust_remote_code=True) model = AutoModel.from_pretrained("zai-org/glm-10b-chinese", trust_remote_code=True)
Hi, would you like to release the quantized version of glm 10B, this would allow to run on a 16GB card which is great
Hi, you can check out my PR which allows for in8 quantization. I haven't tested for in4.
· Sign up or log in to comment
