THUDM

/

glm-4v-9b

like 234

Follow

Knowledge Engineering Group (KEG) & Data Mining at Tsinghua University 1.33k

I am using the code in the model car in colab with a100 gpu.
I have run pip install accelerate successfully but still I get the error message in the subject of this discussion:
Using low_cpu_mem_usage=True or a device_map requires Accelerate: pip install accelerate

This is an error that I keep getting for other models too. Somebody help me please.

import torch
from PIL import Image
from transformers import AutoModelForCausalLM, AutoTokenizer

device = "cuda"

tokenizer = AutoTokenizer.from_pretrained("THUDM/glm-4v-9b", trust_remote_code=True)

query = 'describe the image'
image = Image.open("/content/drive/MyDrive/car.jpg").convert('RGB')
inputs = tokenizer.apply_chat_template([{"role": "user", "image": image, "content": query}],
add_generation_prompt=True, tokenize=True, return_tensors="pt",
return_dict=True) # chat mode

inputs = inputs.to(device)
model = AutoModelForCausalLM.from_pretrained(
"THUDM/glm-4v-9b",
torch_dtype=torch.bfloat16,
low_cpu_mem_usage=True,
trust_remote_code=True
).to(device).eval()

gen_kwargs = {"max_length": 2500, "do_sample": True, "top_k": 1}
with torch.no_grad():
outputs = model.generate(**inputs, **gen_kwargs)
outputs = outputs[:, inputs['input_ids'].shape[1]:]
print(tokenizer.decode(outputs[0]))