Transformers publisherfork · unknown
publisher-documented, not executed source
pip install "transformers[torch,vision,audio] @ git+https://github.com/swiss-ai/transformers.git@3797303dda74844e3d1f8977ff5518bb91f818b4"
import torch
from transformers import AutoModelForMultimodalLM, AutoProcessor
MODEL_ID = "swiss-ai/Apertus-v1.5-8B" # or "swiss-ai/Apertus-v1.5-70B"
processor = AutoProcessor.from_pretrained(MODEL_ID)
model = AutoModelForMultimodalLM.from_pretrained(
MODEL_ID, dtype="auto", device_map="auto"
).eval()
def generate(messages, max_new_tokens=256, **template_kwargs):
inputs = processor.apply_chat_template(
messages,
add_generation_prompt=True,
tokenize=True,
return_dict=True,
return_tensors="pt",
**template_kwargs,
).to(model.device)
with torch.inference_mode():
output_ids = model.generate(**inputs, max_new_tokens=max_new_tokens)
return processor.decode(
output_ids[0, inputs["input_ids"].shape[-1]:], skip_special_tokens=True
)Prerequisites: See source setup/dependencies; these snippets were inspected, not executed.
- Pinned transformers 3797303dda74844e3d1f8977ff5518bb91f818b4; upstreaming in progress in card.
- Multimodal processor/custom format; auto-generated HF deployment widgets are insufficient verification.