<|im_start|>system
You are a helpful assistant.<|im_end|>
<|im_start|>user
Hello, who are you?<|im_end|>
<|im_start|>assistant
I am a language model called Qwen, created by Alibaba Cloud.<|im_end|>

from transformers import AutoModelForCausalLM, AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained(
    "Qwen/Qwen-7B-Chat",
    trust_remote_code=True
)

model = AutoModelForCausalLM.from_pretrained(
    "Qwen/Qwen-7B-Chat",
    device_map="auto",
    trust_remote_code=True
).eval()

# First turn
response, history = model.chat(tokenizer, "你好", history=None)
print(response)
# Output: 你好！很高兴为你提供帮助。

# Second turn (with history)
response, history = model.chat(
    tokenizer,
    "给我讲一个年轻人奋斗创业最终取得成功的故事。",
    history=history
)
print(response)
# Output: 这是一个关于一个年轻人奋斗创业最终取得成功的故事...

# Third turn
response, history = model.chat(
    tokenizer,
    "给这个故事起一个标题",
    history=history
)
print(response)
# Output: 《奋斗创业：一个年轻人的成功之路》

response, _ = model.chat(
    tokenizer,
    "Write a Python function to calculate the Fibonacci sequence",
    history=None
)
# Model generates complete, working Python code

# Using system prompts for behavior control
messages = [
    {"role": "system", "content": "You are a helpful assistant that speaks like a pirate."},
    {"role": "user", "content": "Tell me about the weather"}
]

response, _ = model.chat(tokenizer, messages)
# Model will respond in pirate-speak style

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
from qwen_generation_utils import make_context, decode_tokens

tokenizer = AutoTokenizer.from_pretrained(
    'Qwen/Qwen-7B-Chat',
    pad_token='<|extra_0|>',
    eos_token='<|endoftext|>',
    padding_side='left',
    trust_remote_code=True
)

model = AutoModelForCausalLM.from_pretrained(
    'Qwen/Qwen-7B-Chat',
    pad_token_id=tokenizer.pad_token_id,
    device_map="auto",
    trust_remote_code=True
).eval()

questions = [
    "What is the capital of France?",
    "How do I make pancakes?",
    "Explain quantum computing"
]

# Prepare batch
batch_raw_text = []
for q in questions:
    raw_text, _ = make_context(
        tokenizer, q,
        system="You are a helpful assistant.",
        max_window_size=model.generation_config.max_window_size,
        chat_format=model.generation_config.chat_format,
    )
    batch_raw_text.append(raw_text)

# Batch generation
batch_input_ids = tokenizer(batch_raw_text, padding='longest')
batch_input_ids = torch.LongTensor(batch_input_ids['input_ids']).to(model.device)

batch_out_ids = model.generate(
    batch_input_ids,
    generation_config=model.generation_config
)

# Decode responses
for i, response in enumerate(batch_out_ids):
    decoded = tokenizer.decode(response, skip_special_tokens=True)
    print(f"Q{i+1}: {decoded}")

# Using chat_stream for token-by-token generation
for response in model.chat_stream(
    tokenizer,
    "Tell me a story",
    history=None
):
    print(response, end="", flush=True)