거래 전략을 위한 Weights & Biases 기반 Code Llama 미세 조정 가이드

!pip install openai
from datetime import datetime
import os
import openai
import sys
import pandas as pd
import json
from IPython.display import Markdown, display
!pip install wandb
import wandb
wandb.init(project="together", name="togethercomputer/CodeLlama")

os.environ["OPENAI_API_KEY"] = 'your_api_key'


client = openai.OpenAI(
    api_key=os.environ.get("your_api_key"),
    base_url="https://api.together.xyz/v1",
    )


!pip install --upgrade together
import together
together.api_key = "your_api_key"

results = []
def get_code_completion(user_content, base_model, model_name):
    messages = [
        {
            "role": "system",
            "content": "You are an expert quant programmer that helps to write Python trading strategies code based on the user request. Don't be too verbose.",
        },
        {
            "role": "user",
            "content": user_content, 
        }
    ]
    response = client.chat.completions.create(
        model=base_model, 
        messages=messages,         
        temperature=0.1 
    )


    results.append({"user_prompt": user_content, str(model_name): response.choices[0].message.content})
    return response.choices[0].message.content


base_model = "codellama/CodeLlama-7b-Instruct-hf"


user_prompt = "Please write a Python script that performs a simple moving average (SMA) crossover trading strategy backtest."


chat_completion = get_code_completion(user_prompt, base_model, 'pretrained-7b')
print("Prompt:", user_prompt)
print("Completion:", chat_completion)

!pip install datasets
from datasets import load_dataset
dataset = load_dataset('lumalik/Quant-Trading-Instruct')

dataset_df = dataset['train'].to_pandas()
dataset_df_100 = dataset_df.iloc[:100]

output_file_path = 'output_data1.jsonl'
instruct_template = \
"""<s>[INST] <<SYS>>\n{context}\n<</SYS>>\n\n{question} [/INST] {answer} </s>"""
with open(output_file_path, 'w') as file:
    for index, row in dataset_df_100.iterrows():
        formatted_text = instruct_template.format(
            context=row['context'],
            question=row['question'],
            answer=row['answer']
        )
        json_object = {"text": formatted_text}
        file.write(json.dumps(json_object) + '\n')
print(f"Data successfully written to {output_file_path}"

resp = together.Files.check(file="/content/output_data1.jsonl")
print(resp)

together.Files.upload(file="/content/output_data1.jsonl")

resp = together.Finetune.create(
  training_file = 'tarining_file_id',
  model = 'togethercomputer/CodeLlama-7b-Instruct',
  n_epochs = 5,
  n_checkpoints = 1,
  batch_size = 32,
  learning_rate = 1e-5,
  suffix = 'codeLlama-7b-finetune-trading',
  wandb_api_key = ‘wandb API key’,
)
fine_tune_id = resp['id']

finetuned_model = 'model_id_here'
model_list = together.Models.list()
print(f"{len(model_list)} models available")
available_model_names = [model_dict['name'] for model_dict in model_list]
finetuned_model in available_model_names

together.Models.start(finetuned_model)
together.Models.ready(finetuned_model)

user_prompt = "Please write a Python script that performs a simple moving average (SMA) crossover trading strategy backtest."
chat_completion = get_code_completion(user_prompt, base_model, 'finetuned-7b')
print("Prompt:", user_prompt)
print("Completion:", chat_completion)

df_results = pd.DataFrame(results)
wandb.log({"results_table": wandb.Table(dataframe=df_results)})