How to use intfloat/llm-retriever-base with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="intfloat/llm-retriever-base")
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("intfloat/llm-retriever-base") model = AutoModel.from_pretrained("intfloat/llm-retriever-base", device_map="auto")
https://huggingface.co/intfloat/llm-retriever-base/resolve/main/tokenizer.json
hf download hf://intfloat/llm-retriever-base/tokenizer.json
curl -L -o tokenizer.json https://huggingface.co/intfloat/llm-retriever-base/resolve/main/tokenizer.json
