{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreicfkidcu3ossovjckwzw37mgtgp5wbpp6pjcvjudin2uqkuai47zy",
    "uri": "at://did:plc:pgryn3ephfd2xgft23qokfzt/app.bsky.feed.post/3mie4nbszsmy2"
  },
  "path": "/t/pipeline-tutorial-summarization-doesnt-work/174833#post_2",
  "publishedAt": "2026-03-31T09:47:42.000Z",
  "site": "https://discuss.huggingface.co",
  "tags": [
    "version incompatibility between Transformers v4 and v5"
  ],
  "textContent": "Yeah. It’s real version incompatibility between Transformers v4 and v5.\n\nIf go with v5, try without pipeline:\n\n\n    from transformers import AutoTokenizer, AutoModelForSeq2SeqLM\n\n    model_id = \"google-t5/t5-small\"   # or your finetuned summarization checkpoint\n    tokenizer = AutoTokenizer.from_pretrained(model_id)\n    model = AutoModelForSeq2SeqLM.from_pretrained(model_id)\n\n    inputs = tokenizer(\n        \"summarize: \" + text,\n        return_tensors=\"pt\",\n        truncation=True\n    ).input_ids\n\n    outputs = model.generate(inputs, max_new_tokens=100, do_sample=False)\n    summary = tokenizer.decode(outputs[0], skip_special_tokens=True)\n    print(summary)\n\n\nOr try another supported pipeline:\n\n\n    from transformers import pipeline\n\n    summarizer = pipeline(\"text-generation\", model=\"Qwen/Qwen3-4B-Instruct-2507\")\n\n    messages = [\n        {\n            \"role\": \"user\",\n            \"content\": \"Summarize the following text in 3 bullet points:\\n\\n\" + text\n        }\n    ]\n\n    out = summarizer(messages, max_new_tokens=200)\n    print(out[0][\"generated_text\"][-1][\"content\"])\n",
  "title": "Pipeline tutorial, summarization doesn't work"
}