How to use openbmb/MiniCPM-Llama3-V-2_5-int4 with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "visual-question-answering" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # pip install "transformers<5.0.0" from transformers import pipeline pipe = pipeline("visual-question-answering", model="openbmb/MiniCPM-Llama3-V-2_5-int4", trust_remote_code=True)
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("openbmb/MiniCPM-Llama3-V-2_5-int4", trust_remote_code=True, device_map="auto")
https://huggingface.co/openbmb/MiniCPM-Llama3-V-2_5-int4/resolve/main/tokenizer.json
hf download hf://openbmb/MiniCPM-Llama3-V-2_5-int4/tokenizer.json
curl -L -o tokenizer.json https://huggingface.co/openbmb/MiniCPM-Llama3-V-2_5-int4/resolve/main/tokenizer.json
