from modelscope import AutoModelForCausalLM, AutoTokenizer
model_name = "Qwen/Qwen3-30B-A3B"
# 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 = "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,
    enable_thinking=True # Switch between thinking and non-thinking modes. Default is 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)
print("content:", content)

text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=False  # True is the default value for enable_thinking.
)

SGLANG_USE_MODELSCOPE=1 python -m sglang.launch_server --model-path Qwen/Qwen3-32B --reasoning-parser qwen3

VLLM_USE_MODELSCOPE=1 vllm serve Qwen/Qwen3-32B --enable-reasoning --reasoning-parser deepseek_r1

ollama run modelscope.cn/unsloth/Qwen3-8B-GGUF

from openai import OpenAI
client = OpenAI(
    base_url='https://api-inference.modelscope.cn/v1/',
    api_key='MODELSCOPE_SDK_TOKEN', # ModelScope Token
)
# set extra_body for thinking control
extra_body = {
    # enable thinking, set to False to disable
    "enable_thinking": True,
    # use thinking_budget to contorl num of tokens used for thinking
    # "thinking_budget": 4096
}
response = client.chat.completions.create(
    model='Qwen/Qwen3-32B',  # ModelScope Model-Id
    messages=[
        {
          'role': 'user',
          'content': '9.9和9.11谁大'
        }
    ],
    stream=True,
    extra_body=extra_body
)
done_thinking = False
for chunk in response:
    thinking_chunk = chunk.choices[0].delta.reasoning_content
    answer_chunk = chunk.choices[0].delta.content
    if thinking_chunk != '':
        print(thinking_chunk, end='', flush=True)
    elif answer_chunk != '':
        if not done_thinking:
            print('\n\n === Final Answer ===\n')
            done_thinking = True
        print(answer_chunk, end='', flush=True)

嗯，我现在要比较9.9和9.11哪个更大。首先，我应该先理解这两个数字的结构。9.9是一个小数，而9.11看起来也是一个小数，不过可能有些人可能会误解为日期或者其他形式？不过题目里明确说是比较数值大小，所以应该按照数学上的小数来处理。
首先，我需要确认这两个数的小数点位置。9.9是九又十分之九，也就是9 + 0.9 = 9.9。而9.11则是九又百分之一十一，也就是9 + 0.11 = 9.11。这时候，我需要比较这两个小数的大小。通常比较小数的方法是从左到右逐位比较，直到找到不同的数字为止。
首先比较整数部分，两个数都是9，所以这部分相等。接下来比较小数部分。第一个数是0.9，第二个数是0.11。这时候需要注意小数位数的问题。0.9可以看作0.90，因为小数末尾的零不改变数值的大小。这样两个小数就变成了0.90和0.11。现在比较0.90和0.11的话，第一位小数是9和1，显然9比1大，所以0.90大于0.11，因此整个数9.9（即9.90）比9.11大。
====================Final Answer====================
9.9和9.11的比较可以通过以下步骤进行：
1. **整数部分**：两者均为9，相等。
2. **小数部分**：
   - 9.9可写为 **9.90**（补零不改变数值）。
   - 比较十分位：9.90的十分位是 **9**，9.11的十分位是 **1**。
   - 由于 $9 > 1$，因此 **9.90 > 9.11**。
**结论**：  
$$
\boxed{9.9 > 9.11}
$$

git clone https://github.com/modelscope/ms-swift.git
cd ms-swift
pip install -e .
pip install liger-kernel transformers -U

# 训练显存：22GB
# 你可以指定`--dataset AI-ModelScope/alpaca-gpt4-data-zh`来跑通实验
CUDA_VISIBLE_DEVICES=0 \
swift sft \
    --model Qwen/Qwen3-8B \
    --train_type lora \
    --dataset '<dataset-path>' \
    --torch_dtype bfloat16 \
    --num_train_epochs 1 \
    --per_device_train_batch_size 1 \
    --per_device_eval_batch_size 1 \
    --learning_rate 1e-4 \
    --lora_rank 8 \
    --lora_alpha 32 \
    --target_modules all-linear \
    --gradient_accumulation_steps 4 \
    --eval_steps 50 \
    --save_steps 50 \
    --save_total_limit 2 \
    --logging_steps 5 \
    --max_length 2048 \
    --output_dir output \
    --warmup_ratio 0.05 \
    --dataloader_num_workers 4 \
    --packing true \
    --user_liger_kernel true

{"messages": [{"role": "user", "content": "浙江的省会在哪？"}, {"role": "assistant", "content": "<think>\nxxx\n</think>\n\n浙江的省会在杭州。"}]}

pip install math_verify==0.5.2

# llm
{"messages": [{"role": "system", "content": "You are a useful and harmless assistant"}, {"role": "user", "content": "Tell me tomorrow's weather"}]}
{"messages": [{"role": "system", "content": "You are a useful and harmless math calculator"}, {"role": "user", "content": "What is 1 + 1?"}, {"role": "assistant", "content": "It equals 2"}, {"role": "user", "content": "What about adding 1?"}]}
{"messages": [{"role": "user", "content": "What is your name?"}]}
# mllm
{"messages": [{"role": "user", "content": "<image>What is the difference between the two images?"}], "images": ["/xxx/x.jpg"]}
{"messages": [{"role": "user", "content": "<image><image>What is the difference between the two images?"}], "images": ["/xxx/y.jpg", "/xxx/z.png"]}

--external_plugins examples/train/grpo/plugin/plugin.py \
--reward_funcs external_math_acc external_math_format \
--reward_model AI-ModelScope/Skywork-Reward-Llama-3.1-8B-v0.2

# 70G*8
CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 \
NPROC_PER_NODE=8 \
swift rlhf \
    --rlhf_type grpo \
    --model Qwen/Qwen3-8B \
    --train_type full \
    --dataset AI-MO/NuminaMath-TIR \
    --torch_dtype bfloat16 \
    --num_train_epochs 1 \
    --per_device_train_batch_size 2 \
    --per_device_eval_batch_size 2 \
    --learning_rate 1e-6 \
    --save_total_limit 2 \
    --logging_steps 5 \
    --output_dir output \
    --gradient_accumulation_steps 1 \
    --warmup_ratio 0.05 \
    --dataloader_num_workers 4 \
    --max_completion_length 4096 \
    --vllm_max_model_len 8192 \
    --reward_funcs accuracy \
    --num_generations 16 \
    --use_vllm true \
    --vllm_gpu_memory_utilization 0.4 \
    --sleep_level 1 \
    --offload_model true \
    --offload_optimizer true \
    --gc_collect_after_offload true \
    --deepspeed zero3 \
    --num_infer_workers 8 \
    --tensor_parallel_size 1 \
    --temperature 1.0 \
    --top_p 0.85 \
    --report_to wandb \
    --log_completions true \
    --overlong_filter true

# https://help.aliyun.com/zh/pai/user-guide/general-environment-variables
# 请确保两个节点的保存权重路径相同
NNODES=$WORLD_SIZE \
NODE_RANK=$RANK \
megatron sft \
    --load Qwen3-30B-A3B-Base-mcore \
    --dataset 'liucong/Chinese-DeepSeek-R1-Distill-data-110k-SFT' \
    --tensor_model_parallel_size 2 \
    --expert_model_parallel_size 8 \
    --moe_grouped_gemm true \
    --moe_shared_expert_overlap true \
    --moe_aux_loss_coeff 0.01 \
    --micro_batch_size 1 \
    --global_batch_size 16 \
    --packing true \
    --recompute_granularity full \
    --recompute_method uniform \
    --recompute_num_layers 1 \
    --train_iters 2000 \
    --eval_iters 50 \
    --finetune true \
    --cross_entropy_loss_fusion true \
    --lr 1e-5 \
    --lr_warmup_iters 100 \
    --min_lr 1e-6 \
    --save megatron_output/Qwen3-30B-A3B-Base \
    --eval_interval 200 \
    --save_interval 200 \
    --max_length 8192 \
    --num_workers 8 \
    --dataset_num_proc 8 \
    --no_save_optim true \
    --no_save_rng true \
    --sequence_parallel true \
    --use_flash_attn true