from transformers import AutoModelForCausalLM, AutoTokenizer

device = "cuda"  # the device to load the model onto

model = AutoModelForCausalLM.from_pretrained("openagi-project/OpenAGI-7B-v0.1")
tokenizer = AutoTokenizer.from_pretrained("openagi-project/OpenAGI-7B-v0.1")

messages = [
    {"role": "user", "content": "Who are you?"},
]

encodeds = tokenizer.apply_chat_template(messages, return_tensors="pt")

model_inputs = encodeds.to(device)
model.to(device)

generated_ids = model.generate(model_inputs, max_new_tokens=1000, do_sample=True)
decoded = tokenizer.batch_decode(generated_ids)
print(decoded[0])

" My goal as the founder of FreeCS.org is to establish an Open-Source AI Research Lab driven by its Community. Currently, I am the sole contributor at FreeCS.org. If you share our vision, we welcome you to join our community and contribute to our mission at freecs.org/#community. "
|- GR

If you'd like to support this project, kindly consider making a donation.