白嫖资源训练 DeepSeek R1 推理模型 精华

!pip install unsloth
!pip install --force-reinstall --no-cache-dir --no-deps git+https://github.com/unslothai/unsloth.git
1.
2.

from huggingface_hub import login
from kaggle_secrets import UserSecretsClient
user_secrets = UserSecretsClient()


hf_token = user_secrets.get_secret("HUGGINGFACE_TOKEN")
login(hf_token)
1.
2.
3.
4.
5.
6.
7.

import wandb


wb_token = user_secrets.get_secret("wandb")


wandb.login(key=wb_token)
run = wandb.init(
    project='Fine-tune-DeepSeek-R1-Distill-Llama-8B on Medical COT Dataset', 
    job_type="training", 
    annotallow="allow"
)
1.
2.
3.
4.
5.
6.
7.
8.
9.
10.
11.
12.

from unsloth import FastLanguageModel


max_seq_length = 2048 
dtype = None 
load_in_4bit = True




model, tokenizer = FastLanguageModel.from_pretrained(
    model_name = "unsloth/DeepSeek-R1-Distill-Llama-8B",
    max_seq_length = max_seq_length,
    dtype = dtype,
    load_in_4bit = load_in_4bit,
    token = hf_token, 
)
1.
2.
3.
4.
5.
6.
7.
8.
9.
10.
11.
12.
13.
14.
15.
16.
17.

prompt_style = """Below is an instruction that describes a task, paired with an input that provides further context. 
Write a response that appropriately completes the request. 
Before answering, think carefully about the question and create a step-by-step chain of thoughts to ensure a logical and accurate response.


### Instruction:
You are a medical expert with advanced knowledge in clinical reasoning, diagnostics, and treatment planning. 
Please answer the following medical question. 


### Question:
{}


### Response:
<think>{}"""




## =========================以下为中文翻译======================================


prompt_style = """以下是一条描述任务的指令，以及为其提供更多背景信息的输入内容。请给出一个能恰当完成该请求的回复。在回答之前，仔细思考问题，并创建一个逐步的思路链，以确保回复符合逻辑且准确。


### 指令：
你是一位在临床推理、诊断和治疗计划方面拥有高级知识的医学专家。请回答以下医学问题。


### 问题：
{}


### 回复：
<think>{}"""
1.
2.
3.
4.
5.
6.
7.
8.
9.
10.
11.
12.
13.
14.
15.
16.
17.
18.
19.
20.
21.
22.
23.
24.
25.
26.
27.
28.
29.
30.
31.
32.
33.
34.
35.
36.

question = "A 61-year-old woman with a long history of involuntary urine loss during activities like coughing or sneezing but no leakage at night undergoes a gynecological exam and Q-tip test. Based on these findings, what would cystometry most likely reveal about her residual volume and detrusor contractions?"




FastLanguageModel.for_inference(model) 
inputs = tokenizer([prompt_style.format(question, "")], return_tensors="pt").to("cuda")


outputs = model.generate(
    input_ids=inputs.input_ids,
    attention_mask=inputs.attention_mask,
    max_new_tokens=1200,
    use_cache=True,
)
response = tokenizer.batch_decode(outputs)
print(response[0].split("### Response:")[1])




## =========================以下为中文翻译======================================
一位 61 岁的女性，有长期在咳嗽或打喷嚏等活动时不自主漏尿但夜间无漏尿的病史，进行了妇科检查和棉签试验。基于这些发现，膀胱测压最有可能揭示她的残余尿量和逼尿肌收缩情况如何？
1.
2.
3.
4.
5.
6.
7.
8.
9.
10.
11.
12.
13.
14.
15.
16.
17.
18.
19.
20.
21.
22.
23.

<think>
Okay, so I have this medical question to answer. Let me try to break it down. The patient is a 61-year-old woman with a history of involuntary urine loss during activities like coughing or sneezing, but she doesn't leak at night. She's had a gynecological exam and a Q-tip test. I need to figure out what cystometry would show regarding her residual volume and detrusor contractions.


First, I should recall what I know about urinary incontinence. Involuntary urine loss during activities like coughing or sneezing makes me think of stress urinary incontinence. Stress incontinence typically happens when the urethral sphincter isn't strong enough to resist increased abdominal pressure from activities like coughing, laughing, or sneezing. This usually affects women, especially after childbirth when the pelvic muscles and ligaments are weakened.


The Q-tip test is a common diagnostic tool for stress urinary incontinence. The test involves inserting a Q-tip catheter, which is a small balloon catheter, into the urethra. The catheter is connected to a pressure gauge. The patient is asked to cough, and the pressure reading is taken. If the pressure is above normal (like above 100 mmHg), it suggests that the urethral sphincter isn't closing properly, which is a sign of stress incontinence.


So, based on the history and the Q-tip test, the diagnosis is likely stress urinary incontinence. Now, moving on to what cystometry would show. Cystometry, also known as a filling cystometry, is a diagnostic procedure where a catheter is inserted into the bladder, and the bladder is filled with a liquid to measure how much it can hold (residual volume) and how it responds to being filled (like during a cough or sneeze). This helps in assessing the capacity and compliance of the bladder.


In a patient with stress incontinence, the bladder's capacity might be normal, but the sphincter's function is impaired. So, during the cystometry, the residual volume might be within normal limits because the bladder isn't overfilled. However, when the patient is asked to cough or perform a Valsalva maneuver, the detrusor muscle (the smooth muscle layer of the bladder) might not contract effectively, leading to an increase in intra-abdominal pressure, which might cause leakage.


Wait, but detrusor contractions are usually associated with voiding. In stress incontinence, the issue isn't with the detrusor contractions but with the sphincter's inability to prevent leakage. So, during cystometry, the detrusor contractions would be normal because they are part of the normal voiding process. However, the problem is that the sphincter doesn't close properly, leading to leakage.


So, putting it all together, the residual volume might be normal, but the detrusor contractions would be normal as well. The key finding would be the impaired sphincter function leading to incontinence, which is typically demonstrated during the Q-tip test and clinical history. Therefore, the cystometry would likely show normal residual volume and normal detrusor contractions, but the underlying issue is the sphincter's inability to prevent leakage.
</think>


Based on the provided information, the cystometry findings in this 61-year-old woman with stress urinary incontinence would likely demonstrate the following:


1. **Residual Volume**: The residual volume would be within normal limits. This is because the bladder's capacity is typically normal in cases of stress incontinence, where the primary issue lies with the sphincter function rather than the bladder's capacity.


2. **Detrusor Contractions**: The detrusor contractions would also be normal. These contractions are part of the normal voiding process and are not impaired in stress urinary incontinence. The issue is not with the detrusor muscle but with the sphincter's inability to prevent leakage.


In summary, the key findings of the cystometry would be normal residual volume and normal detrusor contractions, highlighting the sphincteric defect as the underlying cause of the incontinence.<｜end▁of▁sentence｜>
1.
2.
3.
4.
5.
6.
7.
8.
9.
10.
11.
12.
13.
14.
15.
16.
17.
18.
19.
20.
21.
22.
23.
24.
25.
26.
27.
28.
29.
30.
31.
32.
33.

train_prompt_style = """Below is an instruction that describes a task, paired with an input that provides further context. 
Write a response that appropriately completes the request. 
Before answering, think carefully about the question and create a step-by-step chain of thoughts to ensure a logical and accurate response.


### Instruction:
You are a medical expert with advanced knowledge in clinical reasoning, diagnostics, and treatment planning. 
Please answer the following medical question. 


### Question:
{}


### Response:
<think>
{}
</think>
{}"""




## =========================以下为中文翻译======================================
train_prompt_style = """以下是一个描述任务的指令，与提供进一步上下文的输入相配对。写出一个适当完成请求的回应。在回答之前，仔细思考问题并创建一个逐步的思维链，以确保逻辑准确的回应。


### 指令：
您是医学专家，在临床推理、诊断和治疗计划方面拥有先进的知识。
请回答以下医学问题。


### 问题：


{}
### 响应：
<think>
{}
</think>
{}"""
1.
2.
3.
4.
5.
6.
7.
8.
9.
10.
11.
12.
13.
14.
15.
16.
17.
18.
19.
20.
21.
22.
23.
24.
25.
26.
27.
28.
29.
30.
31.
32.
33.
34.
35.
36.
37.
38.
39.
40.
41.

from datasets import load_dataset
dataset = load_dataset("FreedomIntelligence/medical-o1-reasoning-SFT","en", split = "train[0:500]",trust_remote_code=True)
dataset = dataset.map(formatting_prompts_func, batched = True,)
dataset["text"][0]
1.
2.
3.
4.

"Below is an instruction that describes a task, paired with an input that provides further context. \n
Write a response that appropriately completes the request. \n
Before answering, think carefully about the question and create a step-by-step chain of thoughts to ensure a logical and accurate response.\n\n
### Instruction:\n
You are a medical expert with advanced knowledge in clinical reasoning, diagnostics, and treatment planning. \n
Please answer the following medical question. \n\n
### Question:\n
A 61-year-old woman with a long history of involuntary urine loss during activities like coughing or sneezing but no leakage at night undergoes a gynecological exam and Q-tip test. Based on these findings, what would cystometry most likely reveal about her residual volume and detrusor contractions?\n\n
### Response:\n
<think>\n
Okay, let's think about this step by step. There's a 61-year-old woman here who's been dealing with involuntary urine leakages whenever she's doing something that ups her abdominal pressure like coughing or sneezing. This sounds a lot like stress urinary incontinence to me. Now, it's interesting that she doesn't have any issues at night; she isn't experiencing leakage while sleeping. This likely means her bladder's ability to hold urine is fine when she isn't under physical stress. Hmm, that's a clue that we're dealing with something related to pressure rather than a bladder muscle problem. \n\nThe fact that she underwent a Q-tip test is intriguing too. This test is usually done to assess urethral mobility. In stress incontinence, a Q-tip might move significantly, showing urethral hypermobility. This kind of movement often means there's a weakness in the support structures that should help keep the urethra closed during increases in abdominal pressure. So, that's aligning well with stress incontinence.\n\nNow, let's think about what would happen during cystometry. Since stress incontinence isn't usually about sudden bladder contractions, I wouldn't expect to see involuntary detrusor contractions during this test. Her bladder isn't spasming or anything; it's more about the support structure failing under stress. Plus, she likely empties her bladder completely because stress incontinence doesn't typically involve incomplete emptying. So, her residual volume should be pretty normal. \n\n
All in all, it seems like if they do a cystometry on her, it will likely show a normal residual volume and no involuntary contractions. Yup, I think that makes sense given her symptoms and the typical presentations of stress urinary incontinence.\n
</think>\n
Cystometry in this case of stress urinary incontinence would most likely reveal a normal post-void residual volume, as stress incontinence typically does not involve issues with bladder emptying. Additionally, since stress urinary incontinence is primarily related to physical exertion and not an overactive bladder, you would not expect to see any involuntary detrusor contractions during the test.
<｜end▁of▁sentence｜>"
1.
2.
3.
4.
5.
6.
7.
8.
9.
10.
11.
12.
13.
14.
15.

model = FastLanguageModel.get_peft_model(
    model,
    r=16,  
    target_modules=[
        "q_proj",
        "k_proj",
        "v_proj",
        "o_proj",
        "gate_proj",
        "up_proj",
        "down_proj",
    ],
    lora_alpha=16,
    lora_dropout=0,  
    bias="none",  
    use_gradient_checkpointing="unsloth",  # True or "unsloth" for very long context
    random_state=3407,
    use_rslora=False,  
    loftq_config=None,
)
1.
2.
3.
4.
5.
6.
7.
8.
9.
10.
11.
12.
13.
14.
15.
16.
17.
18.
19.
20.

from trl import SFTTrainer
from transformers import TrainingArguments
from unsloth import is_bfloat16_supported


trainer = SFTTrainer(
    model=model,
    tokenizer=tokenizer,
    train_dataset=dataset,
    dataset_text_field="text",
    max_seq_length=max_seq_length,
    dataset_num_proc=2,
    args=TrainingArguments(
        per_device_train_batch_size=2,
        gradient_accumulation_steps=4,
        # Use num_train_epochs = 1, warmup_ratio for full training runs!
        warmup_steps=5,
        max_steps=60,
        learning_rate=2e-4,
        fp16=not is_bfloat16_supported(),
        bf16=is_bfloat16_supported(),
        logging_steps=10,
        optim="adamw_8bit",
        weight_decay=0.01,
        lr_scheduler_type="linear",
        seed=3407,
        output_dir="outputs",
    ),
)
1.
2.
3.
4.
5.
6.
7.
8.
9.
10.
11.
12.
13.
14.
15.
16.
17.
18.
19.
20.
21.
22.
23.
24.
25.
26.
27.
28.
29.

# 更新库到最新版本
pip install --upgrade unsloth transformers


# 或者回退到特定版本
pip install unsloth==x.y.z transformers==a.b.c
1.
2.
3.
4.
5.
6.

trainer_stats = trainer.train()
1.

question = "A 61-year-old woman with a long history of involuntary urine loss during activities like coughing or sneezing but no leakage at night undergoes a gynecological exam and Q-tip test. Based on these findings, what would cystometry most likely reveal about her residual volume and detrusor contractions?"




FastLanguageModel.for_inference(model)  # Unsloth has 2x faster inference!
inputs = tokenizer([prompt_style.format(question, "")], return_tensors="pt").to("cuda")


outputs = model.generate(
    input_ids=inputs.input_ids,
    attention_mask=inputs.attention_mask,
    max_new_tokens=1200,
    use_cache=True,
)
response = tokenizer.batch_decode(outputs)
print(response[0].split("### Response:")[1])
1.
2.
3.
4.
5.
6.
7.
8.
9.
10.
11.
12.
13.
14.
15.
16.
17.

<think>
Okay, so let's think about this. We have a 61-year-old woman who's been dealing with involuntary urine loss during things like coughing or sneezing, but she's not leaking at night. That suggests she might have some kind of problem with her pelvic floor muscles or maybe her bladder.


Now, she's got a gynecological exam and a Q-tip test. Let's break that down. The Q-tip test is usually used to check for urethral obstruction. If it's positive, that means there's something blocking the urethra, like a urethral stricture or something else.


Given that she's had a positive Q-tip test, it's likely there's a urethral obstruction. That would mean her urethra is narrow, maybe due to a stricture or some kind of narrowing. So, her bladder can't empty properly during activities like coughing because the urethral obstruction is making it hard.


Now, let's think about what happens when her bladder can't empty. If there's a urethral obstruction, the bladder is forced to hold more urine, increasing the residual volume. That's because her bladder doesn't empty completely. So, her residual volume is probably increased.


Also, if her bladder can't empty properly, she might have increased detrusor contractions. These contractions are usually stronger to push the urine out. So, we expect her detrusor contractions to be increased.


Putting it all together, if she has a urethral obstruction and a positive Q-tip test, we'd expect her cystometry results to show increased residual volume and increased detrusor contractions. That makes sense because of the obstruction and how her bladder is trying to compensate by contracting more.
</think>
Based on the findings of the gynecological exam and the positive Q-tip test, it is most likely that the cystometry would reveal increased residual volume and increased detrusor contractions. The positive Q-tip test indicates urethral obstruction, which would force the bladder to retain more urine, thereby increasing the residual volume. Additionally, the obstruction can lead to increased detrusor contractions as the bladder tries to compensate by contracting more to expel the urine.<｜end▁of▁sentence｜>
1.
2.
3.
4.
5.
6.
7.
8.
9.
10.
11.
12.
13.
14.
15.
16.
17.
18.
19.

new_model_local = "DeepSeek-R1-Medical-COT"
model.save_pretrained(new_model_local) 
tokenizer.save_pretrained(new_model_local)


model.save_pretrained_merged(new_model_local, tokenizer, save_method = "merged_16bit",)
1.
2.
3.
4.
5.
6.

new_model_online = "skyxiaowang/DeepSeek-R1-Medical-COT"
model.push_to_hub(new_model_online)
tokenizer.push_to_hub(new_model_online)


model.push_to_hub_merged(new_model_online, tokenizer, save_method = "merged_16bit"))
1.
2.
3.
4.
5.
6.