开放思维

import argparse

import torch
from openmind import is_torch_npu_available
from openmind import AutoTokenizer, AutoModelForCausalLM


def parse_args():
    parser = argparse.ArgumentParser()
    parser.add_argument(
        "--model_name_or_path",
        type=str,
        help="Path to model",
        default="deepseek-coder-33b-base",
    )

    args = parser.parse_args()
    return args
def main():
    args = parse_args()
    if args.model_name_or_path:
        model_path = args.model_name_or_path
    else:
        model_path = "../"

    tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

    model = AutoModelForCausalLM.from_pretrained(
        model_path,
        trust_remote_code=True,
        torch_dtype=torch.float16, 
        device_map="auto"
    )

    input_text = """<｜fim▁begin｜>def quick_sort(arr):
        if len(arr) <= 1:
            return arr
        pivot = arr[0]
        left = []
        right = []
    <｜fim▁hole｜>
            if arr[i] < pivot:
                left.append(arr[i])
            else:
                right.append(arr[i])
        return quick_sort(left) + [pivot] + quick_sort(right)<｜fim▁end｜>"""
    inputs = tokenizer(input_text, return_tensors="pt").to(model.device)
    outputs = model.generate(**inputs, max_length=128)
    print(tokenizer.decode(outputs[0], skip_special_tokens=True)[len(input_text):])

from modelscope import AutoTokenizer, AutoModelForCausalLM
import torch
tokenizer = AutoTokenizer.from_pretrained("deepseek-ai/deepseek-coder-33b-base", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("deepseek-ai/deepseek-coder-33b-base", trust_remote_code=True).cuda()
input_text = "#write a quick sort algorithm"
inputs = tokenizer(input_text, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_length=128)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

from modelscope import AutoTokenizer, AutoModelForCausalLM
import torch
tokenizer = AutoTokenizer.from_pretrained("deepseek-ai/deepseek-coder-33b-base", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("deepseek-ai/deepseek-coder-33b-base", trust_remote_code=True).cuda()
input_text = """<｜fim▁begin｜>def quick_sort(arr):
    if len(arr) <= 1:
        return arr
    pivot = arr[0]
    left = []
    right = []
<｜fim▁hole｜>
        if arr[i] < pivot:
            left.append(arr[i])
        else:
            right.append(arr[i])
    return quick_sort(left) + [pivot] + quick_sort(right)<｜fim▁end｜>"""
inputs = tokenizer(input_text, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_length=128)
print(tokenizer.decode(outputs[0], skip_special_tokens=True)[len(input_text):])

from modelscope import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("deepseek-ai/deepseek-coder-33b-base", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("deepseek-ai/deepseek-coder-33b-base", trust_remote_code=True).cuda()

input_text = """#utils.py
import torch
from sklearn import datasets
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.metrics import accuracy_score

def load_data():
    iris = datasets.load_iris()
    X = iris.data
    y = iris.target

    # Standardize the data
    scaler = StandardScaler()
    X = scaler.fit_transform(X)

    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42)

    # Convert numpy data to PyTorch tensors
    X_train = torch.tensor(X_train, dtype=torch.float32)
    X_test = torch.tensor(X_test, dtype=torch.float32)
    y_train = torch.tensor(y_train, dtype=torch.int64)
    y_test = torch.tensor(y_test, dtype=torch.int64)
    
    return X_train, X_test, y_train, y_test

def evaluate_predictions(y_test, y_pred):
    return accuracy_score(y_test, y_pred)
#model.py
import torch
import torch.nn as nn
import torch.optim as optim
from torch.utils.data import DataLoader, TensorDataset

class IrisClassifier(nn.Module):
    def __init__(self):
        super(IrisClassifier, self).__init__()
        self.fc = nn.Sequential(
            nn.Linear(4, 16),
            nn.ReLU(),
            nn.Linear(16, 3)
        )

    def forward(self, x):
        return self.fc(x)

    def train_model(self, X_train, y_train, epochs, lr, batch_size):
        criterion = nn.CrossEntropyLoss()
        optimizer = optim.Adam(self.parameters(), lr=lr)
        
        # Create DataLoader for batches
        dataset = TensorDataset(X_train, y_train)
        dataloader = DataLoader(dataset, batch_size=batch_size, shuffle=True)

        for epoch in range(epochs):
            for batch_X, batch_y in dataloader:
                optimizer.zero_grad()
                outputs = self(batch_X)
                loss = criterion(outputs, batch_y)
                loss.backward()
                optimizer.step()

    def predict(self, X_test):
        with torch.no_grad():
            outputs = self(X_test)
            _, predicted = outputs.max(1)
        return predicted.numpy()
#main.py
from utils import load_data, evaluate_predictions
from model import IrisClassifier as Classifier

def main():
    # Model training and evaluation
"""
inputs = tokenizer(input_text, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=140)
print(tokenizer.decode(outputs[0]))