一步步将DeepSeek R1微调成一个DeepDoctor（资深医生）

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

from huggingface_hub import loginfrom kaggle_secrets import UserSecretsClientuser_secrets = UserSecretsClient()
hf_token = user_secrets.get_secret("HUGGINGFACE_TOKEN")login(hf_token)

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", anonymous="allow")

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, )

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>{}"""

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])

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>{}"""

EOS_TOKEN = tokenizer.eos_token# Must add EOS_TOKEN

def formatting_prompts_func(examples):inputs = examples["Question"]cots = examples["Complex_CoT"]outputs = examples["Response"]texts = []for input, cot, output in zip(inputs, cots, outputs):text = train_prompt_style.format(input, cot, output) + EOS_TOKENtexts.append(text)return {"text": texts,}

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 contextrandom_state=3407,use_rslora=False,loftq_config=None,)

from trl import SFTTrainerfrom transformers import TrainingArgumentsfrom 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",),)

trainer_stats = trainer.train()

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])

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",)

new_model_online = "realyinchen/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")