pip install git+https://github.com/huggingface/transformers@4970b23cedaf745f963779b4eae68da281e8c6ca

from modelscope import AutoModelForCausalLM, AutoTokenizer
import os
import re
model_name_or_path = "Tencent-Hunyuan/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
}

# pip install git+https://github.com/modelscope/ms-swift.git
git clone https://github.com/modelscope/ms-swift.git
cd ms-swift
pip install -e .
pip install git+https://github.com/huggingface/transformers@4970b23cedaf745f963779b4eae68da281e8c6ca

{"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>"}
]}

{"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>"}
]}

# 显存占用：4 * 68GiB
# 你可以设置`--dataset swift/Chinese-Qwen3-235B-2507-Distill-data-110k-SFT`跑通代码
PYTORCH_CUDA_ALLOC_CONF='expandable_segments:True' \
NPROC_PER_NODE=4 \
CUDA_VISIBLE_DEVICES=0,1,2,3 \
swift sft \
    --model Tencent-Hunyuan/Hunyuan-7B-Instruct \
    --train_type full \
    --dataset '<your-dataset>' \
    --attn_impl flash_attention_2 \
    --num_train_epochs 3 \
    --split_dataset_ratio 0.01 \
    --torch_dtype bfloat16 \
    --per_device_train_batch_size 1 \
    --per_device_eval_batch_size 1 \
    --learning_rate 1e-5 \
    --gradient_accumulation_steps 1 \
    --packing true \
    --eval_steps 200 \
    --save_steps 200 \
    --logging_steps 5 \
    --max_length 16384 \
    --warmup_ratio 0.05 \
    --dataloader_num_workers 8 \
    --dataset_num_proc 8 \
    --save_total_limit 2 \
    --save_only_model true \
    --output_dir output/Hunyuan-7B-Instruct \
    --deepspeed zero3 \
    --use_liger_kernel true

CUDA_VISIBLE_DEVICES=0 \
swift infer \
    --model output/vx-xxx/checkpoint-xxx \
    --stream true \
    --max_new_tokens 2048

swift export \
    --model output/vx-xxx/checkpoint-xxx \
    --push_to_hub true \
    --hub_model_id '<your-model-id>' \
    --hub_token '<your-sdk-token>'