How to use OpenNMT/Mistral-7B-v0.1-instruct-ct2-int8 with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("OpenNMT/Mistral-7B-v0.1-instruct-ct2-int8", device_map="auto")
https://huggingface.co/OpenNMT/Mistral-7B-v0.1-instruct-ct2-int8/resolve/main/config.json
hf download hf://OpenNMT/Mistral-7B-v0.1-instruct-ct2-int8/config.json
curl -L -o config.json https://huggingface.co/OpenNMT/Mistral-7B-v0.1-instruct-ct2-int8/resolve/main/config.json
