How to use mmmtf/mistral-v4 with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("mmmtf/mistral-v4", device_map="auto")
https://huggingface.co/mmmtf/mistral-v4/resolve/main/tokenizer.json
hf download hf://mmmtf/mistral-v4/tokenizer.json
curl -L -o tokenizer.json https://huggingface.co/mmmtf/mistral-v4/resolve/main/tokenizer.json
