pip install "transformers>=4.56.0"

from transformers import AutoModelForCausalLM, AutoTokenizer
import os
import re

model_name_or_path = "tencent/Hunyuan-7B-Instruct"

tokenizer = AutoTokenizer.from_pretrained(model_name_or_path)
model = AutoModelForCausalLM.from_pretrained(model_name_or_path, device_map="auto")  # You may want to use bfloat16 and/or move to GPU here
messages = [
    {"role": "user", "content": "Write a short summary of the benefits of regular exercise"},
]
tokenized_chat = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True,return_tensors="pt",
                                                enable_thinking=True # Toggle thinking mode (default: True)
                                                )

outputs = model.generate(tokenized_chat.to(model.device), max_new_tokens=2048)

output_text = tokenizer.decode(outputs[0])
print("output_text=",output_text)
think_pattern = r'<think>(.*?)</think>'
think_matches = re.findall(think_pattern, output_text, re.DOTALL)

answer_pattern = r'<answer>(.*?)</answer>'
answer_matches = re.findall(answer_pattern, output_text, re.DOTALL)

think_content = [match.strip() for match in think_matches][0]
answer_content = [match.strip() for match in answer_matches][0]
print(f"thinking_content:{think_content}\n\n")
print(f"answer_content:{answer_content}\n\n")

{
  "do_sample": true,
  "top_k": 20,
  "top_p": 0.8,
  "repetition_penalty": 1.05,
  "temperature": 0.7
}

# think_pattern
think = ""
answer = ""
think_pattern = f"<think>\n{think}\n</think>\n<answer>\n{answer}\n</answer>"

# fast think pattern
messages = [
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "/no_think海水为什么是咸的" },
    {"role": "assistant", "content": "<think>\n\n</think>\n<answer>\n海水是咸的主要是因为其中含有许多溶解在水中的盐类和矿物质。这些盐类和矿物质来自于地球表面的岩石和土壤中的化学物质，随着时间的推移，它们被带到了海洋中。当海水蒸发时，水分蒸发掉了，但盐类和矿物质仍然留在水中，导致海水变得更加咸味。因此，海水的咸度是由其中的盐类和矿物质的含量决定的。\n</answer>"}
]

# slow think pattern
messages = [
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "1+1=" },
    {"role": "assistant", "content": "<think>\n嗯，用户问的是1加1等于多少。首先，我需要确认这是一个基本的算术问题。1加1在十进制的数学体系中，通常的结果是2。不过，可能需要考虑是否有其他情况，比如二进制或者其他数制，但用户没有特别说明，所以默认应该是十进制。另外，有时候可能会有脑筋急转弯的情况，比如在某些语境下1+1可能等于1（比如1滴水加1滴水还是1滴水），但通常数学问题中都是2。所以最准确的回答应该是2。</think>\n<answer>\n在十进制的基本算术运算中，1加1的结果是2。这是数学中最基础的加法运算之一，遵循自然数的加法规则。因此，1 + 1 = 2。\n</answer>"}
]

from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("your_tokenizer_path", trust_remote_code=True)
train_ids = tokenizer.apply_chat_template(messages)

[
  {
    "messages": [
      {
        "role": "system",
        "content": "System prompt (optional)"
      },
      {
        "role": "user",
        "content": "Human instruction"
      },
      {
        "role": "assistant",
        "content": "Model response"
      }
    ]
  }
]

"dataset_name": {
  "file_name": "dataset.json",
  "formatting": "sharegpt",
  "columns": {
    "messages": "messages"
  },
  "tags": {
    "role_tag": "role",
    "content_tag": "content",
    "user_tag": "user",
    "assistant_tag": "assistant",
    "system_tag": "system"
  }
}

### model
model_name_or_path: [!!!add the model path here!!!]

### dataset
dataset: [!!!add the dataset name here!!!]

docker pull hunyuaninfer/hunyuan-7B:hunyuan-moe-7B-trtllm

docker run --privileged --user root --name hunyuanLLM_infer --rm -it --ipc=host --ulimit memlock=-1 --ulimit stack=67108864 --gpus=all hunyuaninfer/hunyuan-7B:hunyuan-moe-7B-trtllm

cat >/path/to/extra-llm-api-config.yml <<EOF
use_cuda_graph: true
cuda_graph_padding_enabled: true
cuda_graph_batch_sizes:
- 1
- 2
- 4
- 8
- 16
- 32
print_iter_log: true
EOF

trtllm-serve \
  /path/to/HunYuan-moe-7B \
  --host localhost \
  --port 8000 \
  --backend pytorch \
  --max_batch_size 32 \
  --max_num_tokens 16384 \
  --tp_size 2 \
  --kv_cache_free_gpu_memory_fraction 0.6 \
  --trust_remote_code \
  --extra_llm_api_options /path/to/extra-llm-api-config.yml

export MODEL_PATH=tencent/Hunyuan-7B-Instruct

export MODEL_PATH=/root/.cache/modelscope/hub/models/Tencent-Hunyuan/Hunyuan-7B-Instruct/

python3 -m vllm.entrypoints.openai.api_server \
    --host 0.0.0.0 \
    --port 8000 \
    --trust-remote-code \
    --model ${MODEL_PATH} \
    --tensor-parallel-size 1 \
    --dtype bfloat16 \
    --quantization experts_int8 \
    --served-model-name hunyuan \
    2>&1 | tee log_server.txt

curl http://0.0.0.0:8000/v1/chat/completions -H 'Content-Type: application/json' -d '{
"model": "hunyuan",
"messages": [
    {
        "role": "system",
        "content": [{"type": "text", "text": "You are a helpful assistant."}]
    },
    {
        "role": "user",
        "content": [{"type": "text", "text": "请按面积大小对四大洋进行排序，并给出面积最小的洋是哪一个？直接输出结果。"}]
    }
],
"max_tokens": 2048,
"temperature":0.7,
"top_p": 0.6,
"top_k": 20,
"repetition_penalty": 1.05,
"stop_token_ids": [127960]
}'

python3 -m vllm.entrypoints.openai.api_server \
    --host 0.0.0.0 \
    --port 8000 \
    --trust-remote-code \
    --model ${MODEL_PATH} \
    --tensor-parallel-size 1 \
    --dtype bfloat16 \
    --served-model-name hunyuan \
    --quantization experts_int8 \
    2>&1 | tee log_server.txt

export MODEL_PATH=PATH_TO_INT4_MODEL

python3 -m vllm.entrypoints.openai.api_server \
    --host 0.0.0.0 \
    --port 8000 \
    --trust-remote-code \
    --model ${MODEL_PATH} \
    --tensor-parallel-size 1 \
    --dtype bfloat16 \
    --served-model-name hunyuan \
    --quantization gptq_marlin \
    2>&1 | tee log_server.txt

python3 -m vllm.entrypoints.openai.api_server \
    --host 0.0.0.0 \
    --port 8000 \
    --trust-remote-code \
    --model ${MODEL_PATH} \
    --tensor-parallel-size 1 \
    --dtype bfloat16 \
    --served-model-name hunyuan \
    --kv-cache-dtype fp8 \
    2>&1 | tee log_server.txt

docker pull lmsysorg/sglang:latest

docker run --entrypoint="python3" --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    --ulimit nproc=10000 \
    --privileged \
    --ipc=host \
     lmsysorg/sglang:latest \
    -m sglang.launch_server --model-path hunyuan/huanyuan_7B --tp 4 --trust-remote-code --host 0.0.0.0 --port 30000