How to use macadeliccc/dolphin-2.9-llama3-8b-emb with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("macadeliccc/dolphin-2.9-llama3-8b-emb") model = AutoModel.from_pretrained("macadeliccc/dolphin-2.9-llama3-8b-emb", device_map="auto")
dqdw