How to use Tevatron/AgentIR-4B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="Tevatron/AgentIR-4B")
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("Tevatron/AgentIR-4B") model = AutoModel.from_pretrained("Tevatron/AgentIR-4B", device_map="auto")
https://huggingface.co/Tevatron/AgentIR-4B/resolve/main/vocab.json
hf download hf://Tevatron/AgentIR-4B/vocab.json
curl -L -o vocab.json https://huggingface.co/Tevatron/AgentIR-4B/resolve/main/vocab.json
