Qwen2

Qwen2 is a multilingual LLM family (dense and MoE) from 0.5B to 72B with GQA, RoPE, sliding-window/full attention mixes and long context (up to 131K tokens documented upstream).

Adapted for this playbook from the 🤗 Transformers documentation by Hugging Face. Official page: https://huggingface.co/docs/transformers/model_doc/qwen2. Images © Hugging Face (documentation-images) unless noted. This is not a substitute for the upstream docs — verify against the current version.

Covers Hugging Face pages: model_doc/qwen2

Executive summary

Qwen2 instruct checkpoints are strong defaults for multilingual assistants. Use chat messages with Pipeline or apply_chat_template, and verify licence terms for your deployment region.

Quick usage

from transformers import pipeline

pipe = pipeline(task="text-generation", model="Qwen/Qwen2-1.5B-Instruct")
messages = [
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "Tell me about the Qwen2 model family."},
]
out = pipe(messages, max_new_tokens=256, do_sample=True, temperature=0.7, top_p=0.95)
print(out[0]["generated_text"][-1]["content"])

Collection: Qwen2.

Official API

Qwen2 model doc.

What to do next

Phi.