تشغيل Gemma مع ميزة "تحوُّل الوجوه إلى تعابير"

# Install Pytorch
%pip install torch

# Install a transformers
%pip install transformers

from transformers import pipeline

MODEL_ID = "google/gemma-4-E2B-it"

pipe = pipeline(
    task="any-to-any",
    model=MODEL_ID,
    device_map="auto",
    dtype="auto"
)

config.json: 0.00B [00:00, ?B/s]
model.safetensors:   0%|          | 0.00/10.2G [00:00<?, ?B/s]
Loading weights:   0%|          | 0/2011 [00:00<?, ?it/s]
generation_config.json:   0%|          | 0.00/208 [00:00<?, ?B/s]
processor_config.json: 0.00B [00:00, ?B/s]
chat_template.jinja: 0.00B [00:00, ?B/s]
tokenizer_config.json: 0.00B [00:00, ?B/s]
tokenizer.json:   0%|          | 0.00/32.2M [00:00<?, ?B/s]

pipe(text="<|turn>user\nroses are red<turn|>\n<|turn>model\n")

Both `max_new_tokens` (=256) and `max_length`(=20) seem to have been set. `max_new_tokens` will take precedence. Please refer to the documentation for more information. (https://huggingface.co/docs/transformers/main/en/main_classes/text_generation)
[{'input_text': '<|turn>user\nroses are red<turn|>\n<|turn>model\n',
  'generated_text': '<|turn>user\nroses are red<turn|>\n<|turn>model\nThat\'s a classic phrase, often used to highlight a contrast or a truth.\n\n**"Roses are red"** is a very popular, simple, and sweet arrangement.\n\nWhat would you like to do with this phrase? Are you looking for:\n\n1. **More rhymes or phrases?**\n2. **A continuation of a thought?**\n3. **Just appreciating the simplicity?**'}]

from transformers import GenerationConfig
config = GenerationConfig.from_pretrained(MODEL_ID)
config.max_new_tokens = 512
gen_kwargs = dict(generation_config=config)

messages = [
    {
        "role": "system",
        "content": [{"type": "text", "text": "You are a helpful assistant."}]
    },
    {
        "role": "user",
        "content": [{"type": "text", "text": "Roses are red..."}]
    },
]

pipe(messages, return_full_text=False, generate_kwargs=gen_kwargs)

[{'input_text': [{'role': 'system',
    'content': [{'type': 'text', 'text': 'You are a helpful assistant.'}]},
   {'role': 'user',
    'content': [{'type': 'text', 'text': 'Roses are red...'}]}],
  'generated_text': 'Roses are red,\nViolets are blue,\nHow lovely to see\nA beautiful view.'}]

from transformers import GenerationConfig
config = GenerationConfig.from_pretrained(MODEL_ID)
config.max_new_tokens = 512
gen_kwargs = dict(generation_config=config)

messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://ai.google.dev/static/gemma/docs/images/thali-indian-plate.jpg"},
            {"type": "text", "text": "What is shown in this image?"},
        ]
    },
    {
        "role": "assistant",
        "content": [
            {"type": "text", "text": "This image shows"},
        ],
    },
]

pipe(text=messages, return_full_text=False, generate_kwargs=gen_kwargs)

[{'input_text': [{'role': 'user',
    'content': [{'type': 'image',
      'url': 'https://ai.google.dev/static/gemma/docs/images/thali-indian-plate.jpg'},
     {'type': 'text', 'text': 'What is shown in this image?'}]},
   {'role': 'assistant',
    'content': [{'type': 'text', 'text': 'This image shows'}]}],
  'generated_text': " a platter of Indian food, likely a meal or an assortment of dishes.\n\nHere's a breakdown of what is visible:\n\n*   **Flatbread:** There is a large, golden-brown flatbread (possibly naan or roti) dominating the center of the platter.\n*   **Dips/Sides:** There are several small bowls containing various accompaniments:\n    *   A bowl of **yellow/mustard-colored dip** (perhaps a chutney or sauce).\n    *   A bowl of **white creamy dip** (like raita or yogurt sauce).\n    *   A portion of **white rice**.\n    *   Several bowls of **curries or sauces** in different colors:\n        *   An **orange/brown curry**.\n        *   A **deep yellow/orange sauce**.\n        *   A **green sauce** (likely a chutney).\n*   **Garnish/Side Item:** In the upper right corner, there appears to be some darker, textured items, possibly fried pieces or spices.\n*   **Platter:** The food is served on a metal platter.\n\nOverall, it looks like a traditional Indian meal setup featuring bread, rice, and various flavorful sauces/curries."}]

from transformers import GenerationConfig
config = GenerationConfig.from_pretrained(MODEL_ID)
config.max_new_tokens = 512
gen_kwargs = dict(generation_config=config)

messages = [
    {
        "role": "user",
        "content": [
            {"type": "text", "text": "Transcribe the following speech segment in its original language. Follow these specific instructions for formatting the answer:\n* Only output the transcription, with no newlines.\n* When transcribing numbers, write the digits, i.e. write 1.7 and not one point seven, and write 3 instead of three."},
            {"type": "audio", "audio": "https://ai.google.dev/gemma/docs/audio/roses-are.wav"},
        ]
    }
]

pipe(text=messages, return_full_text=False, generate_kwargs=gen_kwargs)

[{'input_text': [{'role': 'user',
    'content': [{'type': 'text',
      'text': 'Transcribe the following speech segment in its original language. Follow these specific instructions for formatting the answer:\n* Only output the transcription, with no newlines.\n* When transcribing numbers, write the digits, i.e. write 1.7 and not one point seven, and write 3 instead of three.'},
     {'type': 'audio',
      'audio': 'https://ai.google.dev/gemma/docs/audio/roses-are.wav'}]}],
  'generated_text': 'Roses are red, violets are blue.'}]