Qwen3-Next-80B-A3B-Thinking

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

KeyError: 'qwen3_next'

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "Qwen/Qwen3-Next-80B-A3B-Thinking"

# load the tokenizer and the model
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    dtype="auto",
    device_map="auto"
)

# prepare the model input
prompt = "Give me a short introduction to large language model."
messages = [
    {"role": "user", "content": prompt},
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# conduct text completion
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768,
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 

# parsing thinking content
try:
    # rindex finding 151668 (</think>)
    index = len(output_ids) - output_ids[::-1].index(151668)
except ValueError:
    index = 0

thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")

print("thinking content:", thinking_content) # no opening <think> tag
print("content:", content)

pip install 'sglang[all]>=0.5.2'

python -m sglang.launch_server --model-path Qwen/Qwen3-Next-80B-A3B-Thinking --port 30000 --tp-size 4 --context-length 262144 --reasoning-parser deepseek-r1 --mem-fraction-static 0.8

python -m sglang.launch_server --model-path Qwen/Qwen3-Next-80B-A3B-Thinking --port 30000 --tp-size 4 --context-length 262144 --reasoning-parser deepseek-r1 --mem-fraction-static 0.8 --speculative-algo NEXTN --speculative-num-steps 3 --speculative-eagle-topk 1 --speculative-num-draft-tokens 4

pip install 'vllm>=0.10.2'

vllm serve Qwen/Qwen3-Next-80B-A3B-Thinking --port 8000 --tensor-parallel-size 4 --max-model-len 262144 --reasoning-parser deepseek_r1

vllm serve Qwen/Qwen3-Next-80B-A3B-Thinking --port 8000 --tensor-parallel-size 4 --max-model-len 262144 --reasoning-parser deepseek_r1 --speculative-config '{"method":"qwen3_next_mtp","num_speculative_tokens":2}'

from qwen_agent.agents import Assistant

# Define LLM
# Using Alibaba Cloud Model Studio
llm_cfg = {
    'model': 'Qwen3-Next-80B-A3B-Thinking',
    'model_type': 'qwen_dashscope',
}

# Using OpenAI-compatible API endpoint. It is recommended to disable the reasoning and the tool call parsing
# functionality of the deployment frameworks and let Qwen-Agent automate the related operations. For example, 
# `vllm serve Qwen/Qwen3-Next-80B-A3B-Thinking --served-model-name Qwen3-Next-80B-A3B-Thinking --port 8000 --tensor-parallel-size 4 --max-model-len 262144`.
#
# llm_cfg = {
#     'model': 'Qwen3-Next-80B-A3B-Thinking',
# 
#     # Use a custom endpoint compatible with OpenAI API:
#     'model_server': 'http://localhost:8000/v1',  # api_base without reasoning and tool call parsing
#     'api_key': 'EMPTY',
#     'generate_cfg': {
#         'thought_in_content': True,
#     },
# }

# Define Tools
tools = [
    {'mcpServers': {  # You can specify the MCP configuration file
            'time': {
                'command': 'uvx',
                'args': ['mcp-server-time', '--local-timezone=Asia/Shanghai']
            },
            "fetch": {
                "command": "uvx",
                "args": ["mcp-server-fetch"]
            }
        }
    },
  'code_interpreter',  # Built-in tools
]

# Define Agent
bot = Assistant(llm=llm_cfg, function_list=tools)

# Streaming generation
messages = [{'role': 'user', 'content': 'https://qwenlm.github.io/blog/ Introduce the latest developments of Qwen'}]
for responses in bot.run(messages=messages):
    pass
print(responses)

@misc{qwen3technicalreport,
      title={Qwen3 Technical Report}, 
      author={Qwen Team},
      year={2025},
      eprint={2505.09388},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2505.09388}, 
}

@article{qwen2.5-1m,
      title={Qwen2.5-1M Technical Report}, 
      author={An Yang and Bowen Yu and Chengyuan Li and Dayiheng Liu and Fei Huang and Haoyan Huang and Jiandong Jiang and Jianhong Tu and Jianwei Zhang and Jingren Zhou and Junyang Lin and Kai Dang and Kexin Yang and Le Yu and Mei Li and Minmin Sun and Qin Zhu and Rui Men and Tao He and Weijia Xu and Wenbiao Yin and Wenyuan Yu and Xiafei Qiu and Xingzhang Ren and Xinlong Yang and Yong Li and Zhiying Xu and Zipeng Zhang},
      journal={arXiv preprint arXiv:2501.15383},
      year={2025}
}