openbmb

/

MiniCPM-Llama3-V-2_5

like 1.37k

Follow

OpenBMB 339

I was just running this piece standard code:

`from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model = AutoModelForCausalLM.from_pretrained(
"openbmb/MiniCPM-Llama3-V-2_5",
trust_remote_code=True
).to("cuda")
tokenizer = AutoTokenizer.from_pretrained(
"openbmb/MiniCPM-Llama3-V-2_5",
trust_remote_code=True
)

image = Image.open("path/to/image.jpg")
prompt = "What is the main object shown in the image?"

chat = model.chat(
image=image,
question=prompt,
tokenizer=tokenizer,
generate_args={"temperature": 0.8}
)

print(chat)`

I have tried python version 3.8, 3.9, and now as suggested 3.10.
The kernel just died every time at around the same place. Is this a glitch?