魔搭社区每周速递（12.22-12.28）

from modelscope import Qwen2VLForConditionalGeneration, AutoTokenizer, AutoProcessor
from qwen_vl_utils import process_vision_info
# default: Load the model on the available device(s)
model = Qwen2VLForConditionalGeneration.from_pretrained(
    "Qwen/QVQ-72B-Preview", torch_dtype="auto", device_map="auto"
)
# default processer
processor = AutoProcessor.from_pretrained("Qwen/QVQ-72B-Preview")
# The default range for the number of visual tokens per image in the model is 4-16384. You can set min_pixels and max_pixels according to your needs, such as a token count range of 256-1280, to balance speed and memory usage.
# min_pixels = 256*28*28
# max_pixels = 1280*28*28
# processor = AutoProcessor.from_pretrained("Qwen/QVQ-72B-Preview", min_pixels=min_pixels, max_pixels=max_pixels)
messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. Answer in the language of the question. You should think step-by-step."}
        ],
    },
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": "https://qianwen-res.oss-accelerate-overseas.aliyuncs.com/QVQ/demo.png",
            },
            {"type": "text", "text": "What value should be filled in the blank space?"},
        ],
    }
]
# Preparation for inference
text = processor.apply_chat_template(
    messages, tokenize=False, add_generation_prompt=True
)
image_inputs, video_inputs = process_vision_info(messages)
inputs = processor(
    text=[text],
    images=image_inputs,
    videos=video_inputs,
    padding=True,
    return_tensors="pt",
)
inputs = inputs.to("cuda")
# Inference: Generation of the output
generated_ids = model.generate(**inputs, max_new_tokens=8192)
generated_ids_trimmed = [
    out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
]
output_text = processor.batch_decode(
    generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
)
print(output_text)

!pip install git+https://github.com/huggingface/transformers.git

from transformers import AutoTokenizer, AutoModelForMaskedLM
from modelscope import snapshot_download
model_id = snapshot_download("answerdotai/ModernBERT-base")
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForMaskedLM.from_pretrained(model_id)
text = "The capital of France is [MASK]."
inputs = tokenizer(text, return_tensors="pt")
outputs = model(**inputs)
# To get predictions for the mask:
masked_index = inputs["input_ids"][0].tolist().index(tokenizer.mask_token_id)
predicted_token_id = outputs.logits[0, masked_index].argmax(axis=-1)
predicted_token = tokenizer.decode(predicted_token_id)
print("Predicted token:", predicted_token)
# Predicted token:  Paris

import torch
from transformers import pipeline
from pprint import pprint
pipe = pipeline(
    "fill-mask",
    model="answerdotai/ModernBERT-base",
    torch_dtype=torch.bfloat16,
)
input_text = "He walked to the [MASK]."
results = pipe(input_text)
pprint(results)