0元！使用魔搭免费算力，基于Qwen基座模型，复现DeepSeek-R1

!pip install vllm -U
!pip install trl -U

import re
import torch
from modelscope.msdatasets import MsDataset
from modelscope import AutoTokenizer, AutoModelForCausalLM
from trl import GRPOConfig, GRPOTrainer

# Load and prep dataset

SYSTEM_PROMPT = """
Respond in the following format:
<reasoning>
...
</reasoning>
<answer>
...
</answer>
"""

XML_COT_FORMAT = """\
<reasoning>
{reasoning}
</reasoning>
<answer>
{answer}
</answer>
"""

def extract_xml_answer(text: str) -> str:
    answer = text.split("<answer>")[-1]
    answer = answer.split("</answer>")[0]
    return answer.strip()

def extract_hash_answer(text: str) -> str | None:
    if "####" not in text:
        return None
    return text.split("####")[1].strip()

# uncomment middle messages for 1-shot prompting
def get_gsm8k_questions(split = "train") -> MsDataset:
    data =  MsDataset.load('modelscope/gsm8k', subset_name='main', split=split)
    data = data.map(lambda x: { # type: ignore
        'prompt': [
            {'role': 'system', 'content': SYSTEM_PROMPT},
            {'role': 'user', 'content': x['question']}
        ],
        'answer': extract_hash_answer(x['answer'])
    }) # type: ignore
    return data # type: ignore

dataset = get_gsm8k_questions()

# Reward functions
def correctness_reward_func(prompts, completions, answer, **kwargs) -> list[float]:
    responses = [completion[0]['content'] for completion in completions]
    q = prompts[0][-1]['content']
    extracted_responses = [extract_xml_answer(r) for r in responses]
    print('-'*20, f"Question:\n{q}", f"\nAnswer:\n{answer[0]}", f"\nResponse:\n{responses[0]}", f"\nExtracted:\n{extracted_responses[0]}")
    return [2.0 if r == a else 0.0 for r, a in zip(extracted_responses, answer)]

def int_reward_func(completions, **kwargs) -> list[float]:
    responses = [completion[0]['content'] for completion in completions]
    extracted_responses = [extract_xml_answer(r) for r in responses]
    return [0.5 if r.isdigit() else 0.0 for r in extracted_responses]

def strict_format_reward_func(completions, **kwargs) -> list[float]:
    """Reward function that checks if the completion has a specific format."""
    pattern = r"^<reasoning>\n.*?\n</reasoning>\n<answer>\n.*?\n</answer>\n$"
    responses = [completion[0]["content"] for completion in completions]
    matches = [re.match(pattern, r) for r in responses]
    return [0.5 if match else 0.0 for match in matches]

def soft_format_reward_func(completions, **kwargs) -> list[float]:
    """Reward function that checks if the completion has a specific format."""
    pattern = r"<reasoning>.*?</reasoning>\s*<answer>.*?</answer>"
    responses = [completion[0]["content"] for completion in completions]
    matches = [re.match(pattern, r) for r in responses]
    return [0.5 if match else 0.0 for match in matches]

def count_xml(text) -> float:
    count = 0.0
    if text.count("<reasoning>\n") == 1:
        count += 0.125
    if text.count("\n</reasoning>\n") == 1:
        count += 0.125
    if text.count("\n<answer>\n") == 1:
        count += 0.125
        count -= len(text.split("\n</answer>\n")[-1])*0.001
    if text.count("\n</answer>") == 1:
        count += 0.125
        count -= (len(text.split("\n</answer>")[-1]) - 1)*0.001
    return count

def xmlcount_reward_func(completions, **kwargs) -> list[float]:
    contents = [completion[0]["content"] for completion in completions]
    return [count_xml(c) for c in contents]

model_name = "Qwen/Qwen2.5-0.5B-Instruct"

output_dir="outputs/Qwen-0.5B-GRPO"
run_name="Qwen-0.5B-GRPO-gsm8k"

training_args = GRPOConfig(
    output_dir=output_dir,
    run_name=run_name,
    learning_rate=5e-6,
    adam_beta1 = 0.9,
    adam_beta2 = 0.99,
    weight_decay = 0.1,
    warmup_ratio = 0.1,
    lr_scheduler_type='cosine',
    logging_steps=1,
    bf16=True,
    per_device_train_batch_size=1,
    gradient_accumulation_steps=4,
    num_generations=8,
    max_prompt_length=256,
    max_completion_length=200,
    num_train_epochs=1,
    save_steps=100,
    max_grad_norm=0.1,
    log_on_each_node=False,
    use_vllm=True,
    vllm_gpu_memory_utilization=.2,
    vllm_device="cuda:0",
    report_to="none" #I'm disabling Wandb.
)

model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype=torch.bfloat16,
    device_map=None
).to("cuda")

tokenizer = AutoTokenizer.from_pretrained(model_name)
tokenizer.pad_token = tokenizer.eos_token

trainer = GRPOTrainer(
    model=model,
    processing_class=tokenizer,
    reward_funcs=[
        xmlcount_reward_func,
        soft_format_reward_func,
        strict_format_reward_func,
        int_reward_func,
        correctness_reward_func],
    args=training_args,
    train_dataset=dataset,
    #peft_config=peft_config
)
trainer.train()

from modelscope import AutoModelForCausalLM, AutoTokenizer

model_name = "/mnt/workspace/outputs/Qwen-0.5B-GRPO/checkpoint-1868"

model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "Xiao Ming bought 4 apples, ate 1, and gave 1 to his sister. How many apples were left?"
messages = [
    {"role": "system", "content": SYSTEM_PROMPT},
    {"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)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=256
)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]

response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(response)