Qwen3-Coder-Next开源！推动小型混合模型在智能体编程上的边界

from modelscope import AutoModelForCausalLM, AutoTokenizer
model_name = "Qwen/Qwen3-Coder-Next"
# load the tokenizer and the model
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
  model_name,
  torch_dtype="auto",
  device_map="auto"
)
# prepare the model input
prompt = "Write a quick sort algorithm."
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=65536
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 
content = tokenizer.decode(output_ids, skip_special_tokens=True)
print("content:", content)

pip install 'sglang[all]>=v0.5.8'

SGLANG_USE_MODELSCOPE=true python -m sglang.launch_server --model Qwen/Qwen3-Coder-Next --port 30000 --tp-size 2 --tool-call-parser qwen3_coder

pip install 'vllm>=0.15.0'

VLLM_USE_MODELSCOPE=true vllm serve Qwen/Qwen3-Coder-Next --port 8000 --tensor-parallel-size 2 --enable-auto-tool-choice --tool-call-parser qwen3_coder

# Your tool implementation
def square_the_number(num: float) -> dict:
    return num ** 2
# Define Tools
tools=[
    {
        "type":"function",
        "function":{
            "name": "square_the_number",
            "description": "output the square of the number.",
            "parameters": {
                "type": "object",
                "required": ["input_num"],
                "properties": {
                    'input_num': {
                        'type': 'number', 
                        'description': 'input_num is a number that will be squared'
                        }
                },
            }
        }
    }
]
from openai import OpenAI
# Define LLM
client = OpenAI(
    # Use a custom endpoint compatible with OpenAI API
    base_url='http://localhost:8000/v1',  # api_base
    api_key="EMPTY"
)
messages = [{'role': 'user', 'content': 'square the number 1024'}]
completion = client.chat.completions.create(
    messages=messages,
    model="Qwen3-Coder-Next",
    max_tokens=65536,
    tools=tools,
)
print(completion.choices[0])

git clone https://github.com/modelscope/ms-swift.git
cd ms-swift
# 避免后续代码改动导致的不兼容问题
git checkout d2a67bf8cd6159faa74e5b109a80970eb81e1b6d
pip install -e .

# 8 * 55GiB
PYTORCH_CUDA_ALLOC_CONF='expandable_segments:True' \
NPROC_PER_NODE=8 \
CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 \
megatron sft \
    --model Qwen/Qwen3-Coder-Next \
    --load_safetensors true \
    --save_safetensors true \
    --merge_lora true \
    --dataset 'AI-ModelScope/alpaca-gpt4-data-zh#500' \
              'AI-ModelScope/alpaca-gpt4-data-en#500' \
              'swift/self-cognition#500' \
    --load_from_cache_file true \
    --tuner_type lora \
    --lora_rank 8 \
    --lora_alpha 32 \
    --target_modules all-linear \
    --expert_model_parallel_size 4 \
    --moe_permute_fusion true \
    --moe_grouped_gemm true \
    --moe_shared_expert_overlap true \
    --moe_aux_loss_coeff 1e-3 \
    --micro_batch_size 2 \
    --global_batch_size 16 \
    --recompute_granularity full \
    --recompute_method uniform \
    --recompute_num_layers 1 \
    --max_epochs 1 \
    --finetune true \
    --cross_entropy_loss_fusion true \
    --lr 1e-4 \
    --lr_warmup_fraction 0.05 \
    --min_lr 1e-5 \
    --save megatron_output/Qwen3-Coder-Next \
    --eval_interval 200 \
    --save_interval 200 \
    --max_length 2048 \
    --num_workers 8 \
    --dataset_num_proc 8 \
    --no_save_optim true \
    --no_save_rng true \
    --sequence_parallel true \
    --attention_backend flash \
    --model_author swift \
    --model_name swift-robot

{"messages": [{"role": "system", "content": "<system>"}, {"role": "user", "content": "<query1>"}, {"role": "assistant", "content": "<response1>"}, {"role": "user", "content": "<query2>"}, {"role": "assistant", "content": "<response2>"}]}

CUDA_VISIBLE_DEVICES=0,1,2,3 \
swift infer \
    --model megatron_output/Qwen3-Coder-Next/vx-xxx/checkpoint-xxx-merged \
    --stream true

swift export \
    --model megatron_output/Qwen3-Coder-Next/vx-xxx/checkpoint-xxx-merged \
    --push_to_hub true \
    --hub_model_id '<your-model-id>' \
    --hub_token '<your-sdk-token>'