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
#Downloading the dataset
import json
import os
import urllib


def download_and_load_file(file_path, url):

    if not os.path.exists(file_path):
        with urllib.request.urlopen(url) as response:
            text_data = response.read().decode("utf-8")
        with open(file_path, "w", encoding="utf-8") as file:
            file.write(text_data)

    # The book originally contained this unnecessary "else" clause:
    #else:
    #    with open(file_path, "r", encoding="utf-8") as file:
    #        text_data = file.read()

    with open(file_path, "r", encoding="utf-8") as file:
        data = json.load(file)

    return data


file_path = "instruction-data.json"
url = (
    "https://raw.githubusercontent.com/rasbt/LLMs-from-scratch"
    "/main/ch07/01_main-chapter-code/instruction-data.json"
)

data = download_and_load_file(file_path, url)
print("Number of entries:", len(data)) #Number of entries: 1100

1
2
print("Example entry:\n", data[50])
print("Another example entry:\n", data[999])

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
#Implementing the prompt formatting function
def format_input(entry):
    instruction_text = (
        f"Below is an instruction that describes a task. "
        f"Write a response that appropriately completes the request."
        f"\n\n### Instruction:\n{entry['instruction']}"
    )

    input_text = f"\n\n### Input:\n{entry['input']}" if entry["input"] else ""

    return instruction_text + input_text

model_input = format_input(data[50])
desired_response = f"\n\n### Response:\n{data[50]['output']}"

print(model_input + desired_response)

1
2
3
4
model_input = format_input(data[999])
desired_response = f"\n\n### Response:\n{data[999]['output']}"

print(model_input + desired_response)

1
2
3
4
5
6
7
8
9
10
11
12
#Partitioning the dataset
train_portion = int(len(data) * 0.85)  # 85% for training
test_portion = int(len(data) * 0.1)    # 10% for testing
val_portion = len(data) - train_portion - test_portion  # Remaining 5% for validation

train_data = data[:train_portion]
test_data = data[train_portion:train_portion + test_portion]
val_data = data[train_portion + test_portion:]

print("Training set length:", len(train_data)) #Training set length: 935
print("Validation set length:", len(val_data)) #Validation set length: 55
print("Test set length:", len(test_data)) #Test set length: 110

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
#Implementing an instruction dataset class
import torch
from torch.utils.data import Dataset


class InstructionDataset(Dataset):
    def __init__(self, data, tokenizer):
        self.data = data

        # Pre-tokenize texts
        self.encoded_texts = []
        for entry in data:
            instruction_plus_input = format_input(entry)
            response_text = f"\n\n### Response:\n{entry['output']}"
            full_text = instruction_plus_input + response_text
            self.encoded_texts.append(
                tokenizer.encode(full_text)
            )

    def __getitem__(self, index):
        return self.encoded_texts[index]

    def __len__(self):
        return len(self.data)

1
2
3
4
import tiktoken
tokenizer = tiktoken.get_encoding("gpt2")

print(tokenizer.encode("<|endoftext|>", allowed_special={"<|endoftext|>"})) #[50256]

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
42
43
def custom_collate_draft_1(
    batch,
    pad_token_id=50256,
    device="cpu"
):
    # Find the longest sequence in the batch
    # and increase the max length by +1, which will add one extra
    # padding token below
    batch_max_length = max(len(item)+1 for item in batch)

    # Pad and prepare inputs
    inputs_lst = []

    for item in batch:
        new_item = item.copy()
        # Add an <|endoftext|> token
        new_item += [pad_token_id]
        # Pad sequences to batch_max_length
        padded = (
            new_item + [pad_token_id] *
            (batch_max_length - len(new_item))
        )
        # Via padded[:-1], we remove the extra padded token
        # that has been added via the +1 setting in batch_max_length
        # (the extra padding token will be relevant in later codes)
        inputs = torch.tensor(padded[:-1])
        inputs_lst.append(inputs)

    # Convert list of inputs to tensor and transfer to target device
    inputs_tensor = torch.stack(inputs_lst).to(device)
    return inputs_tensor

inputs_1 = [0, 1, 2, 3, 4]
inputs_2 = [5, 6]
inputs_3 = [7, 8, 9]

batch = (
    inputs_1,
    inputs_2,
    inputs_3
)

print(custom_collate_draft_1(batch))

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
def custom_collate_draft_2(
    batch,
    pad_token_id=50256,
    device="cpu"
):
    # Find the longest sequence in the batch
    batch_max_length = max(len(item)+1 for item in batch)

    # Pad and prepare inputs
    inputs_lst, targets_lst = [], []

    for item in batch:
        new_item = item.copy()
        # Add an <|endoftext|> token
        new_item += [pad_token_id]
        # Pad sequences to max_length
        padded = (
            new_item + [pad_token_id] *
            (batch_max_length - len(new_item))
        )
        inputs = torch.tensor(padded[:-1])  # Truncate the last token for inputs
        targets = torch.tensor(padded[1:])  # Shift +1 to the right for targets
        inputs_lst.append(inputs)
        targets_lst.append(targets)

    # Convert list of inputs to tensor and transfer to target device
    inputs_tensor = torch.stack(inputs_lst).to(device)
    targets_tensor = torch.stack(targets_lst).to(device)
    return inputs_tensor, targets_tensor

inputs, targets = custom_collate_draft_2(batch)
print(inputs)
print(targets)

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
42
43
44
45
46
47
48
49
#Implementing a custom batch collate function
def custom_collate_fn(
    batch,
    pad_token_id=50256,
    ignore_index=-100,
    allowed_max_length=None,
    device="cpu" #device可以是cpu，cuda（针对NVIDIA GPU），mps（针对Apple Silicon芯片的Mac）
):
    # Find the longest sequence in the batch
    batch_max_length = max(len(item)+1 for item in batch)

    # Pad and prepare inputs and targets
    inputs_lst, targets_lst = [], []

    for item in batch:
        new_item = item.copy()
        # Add an <|endoftext|> token
        new_item += [pad_token_id]
        # Pad sequences to max_length
        padded = (
            new_item + [pad_token_id] *
            (batch_max_length - len(new_item))
        )
        inputs = torch.tensor(padded[:-1])  # Truncate the last token for inputs
        targets = torch.tensor(padded[1:])  # Shift +1 to the right for targets

        # New: Replace all but the first padding tokens in targets by ignore_index
        mask = targets == pad_token_id
        indices = torch.nonzero(mask).squeeze()
        if indices.numel() > 1:
            targets[indices[1:]] = ignore_index

        # New: Optionally truncate to maximum sequence length
        if allowed_max_length is not None:
            inputs = inputs[:allowed_max_length]
            targets = targets[:allowed_max_length]

        inputs_lst.append(inputs)
        targets_lst.append(targets)

    # Convert list of inputs and targets to tensors and transfer to target device
    inputs_tensor = torch.stack(inputs_lst).to(device)
    targets_tensor = torch.stack(targets_lst).to(device)

    return inputs_tensor, targets_tensor

inputs, targets = custom_collate_fn(batch)
print(inputs)
print(targets)

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
logits_1 = torch.tensor(
    [[-1.0, 1.0],  # 1st training example
     [-0.5, 1.5]]  # 2nd training example
)
targets_1 = torch.tensor([0, 1])


loss_1 = torch.nn.functional.cross_entropy(logits_1, targets_1)
print(loss_1) #tensor(1.1269)

logits_2 = torch.tensor(
    [[-1.0, 1.0],
     [-0.5, 1.5],
     [-0.5, 1.5]]  # New 3rd training example
)
targets_2 = torch.tensor([0, 1, 1])

loss_2 = torch.nn.functional.cross_entropy(logits_2, targets_2)
print(loss_2) #tensor(0.7936)

targets_3 = torch.tensor([0, 1, -100]) #把targets_2中的第三个值换成-100

loss_3 = torch.nn.functional.cross_entropy(logits_2, targets_3)
print(loss_3) #tensor(1.1269)
print("loss_1 == loss_3:", loss_1 == loss_3) #loss_1 == loss_3: tensor(True)

1
2
3
4
5
6
7
8
9
from functools import partial

device = torch.device("cuda" if torch.cuda.is_available() else "cpu")

customized_collate_fn = partial(
    custom_collate_fn,
    device=device,
    allowed_max_length=1024
)

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
42
#Initializing the data loaders
from torch.utils.data import DataLoader


num_workers = 0
batch_size = 8

torch.manual_seed(123)

train_dataset = InstructionDataset(train_data, tokenizer)
train_loader = DataLoader(
    train_dataset,
    batch_size=batch_size,
    collate_fn=customized_collate_fn,
    shuffle=True,
    drop_last=True,
    num_workers=num_workers
)

val_dataset = InstructionDataset(val_data, tokenizer)
val_loader = DataLoader(
    val_dataset,
    batch_size=batch_size,
    collate_fn=customized_collate_fn,
    shuffle=False,
    drop_last=False,
    num_workers=num_workers
)

test_dataset = InstructionDataset(test_data, tokenizer)
test_loader = DataLoader(
    test_dataset,
    batch_size=batch_size,
    collate_fn=customized_collate_fn,
    shuffle=False,
    drop_last=False,
    num_workers=num_workers
)

print("Train loader:")
for inputs, targets in train_loader:
    print(inputs.shape, targets.shape)

1
2
print(inputs[0])
print(targets[0])

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
#Loading the pretrained model
from gpt_download import download_and_load_gpt2
from previous_chapters import GPTModel, load_weights_into_gpt


BASE_CONFIG = {
    "vocab_size": 50257,     # Vocabulary size
    "context_length": 1024,  # Context length
    "drop_rate": 0.0,        # Dropout rate
    "qkv_bias": True         # Query-key-value bias
}

model_configs = {
    "gpt2-small (124M)": {"emb_dim": 768, "n_layers": 12, "n_heads": 12},
    "gpt2-medium (355M)": {"emb_dim": 1024, "n_layers": 24, "n_heads": 16},
    "gpt2-large (774M)": {"emb_dim": 1280, "n_layers": 36, "n_heads": 20},
    "gpt2-xl (1558M)": {"emb_dim": 1600, "n_layers": 48, "n_heads": 25},
}

CHOOSE_MODEL = "gpt2-medium (355M)"

BASE_CONFIG.update(model_configs[CHOOSE_MODEL])

model_size = CHOOSE_MODEL.split(" ")[-1].lstrip("(").rstrip(")")
settings, params = download_and_load_gpt2(
    model_size=model_size,
    models_dir="gpt2"
)

model = GPTModel(BASE_CONFIG)
load_weights_into_gpt(model, params)
model.eval();

1
2
3
4
torch.manual_seed(123)

input_text = format_input(val_data[0])
print(input_text)

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
from previous_chapters import (
    generate,
    text_to_token_ids,
    token_ids_to_text
)

token_ids = generate(
    model=model,
    idx=text_to_token_ids(input_text, tokenizer),
    max_new_tokens=35,
    context_size=BASE_CONFIG["context_length"],
    eos_id=50256,
)
generated_text = token_ids_to_text(token_ids, tokenizer)
print(generated_text)

1
2
response_text = generated_text[len(input_text):].strip()
print(response_text)

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
from previous_chapters import (
    calc_loss_loader,
    train_model_simple
)

model.to(device)

torch.manual_seed(123)

with torch.no_grad():
    train_loss = calc_loss_loader(train_loader, model, device, num_batches=5)
    val_loss = calc_loss_loader(val_loader, model, device, num_batches=5)

print("Training loss:", train_loss) #Training loss: 3.825910234451294
print("Validation loss:", val_loss) #Validation loss: 3.7619343757629395

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
#Instruction fine-tuning the pretrained LLM
import time

start_time = time.time()

torch.manual_seed(123)

optimizer = torch.optim.AdamW(model.parameters(), lr=0.00005, weight_decay=0.1)

num_epochs = 2

train_losses, val_losses, tokens_seen = train_model_simple(
    model, train_loader, val_loader, optimizer, device,
    num_epochs=num_epochs, eval_freq=5, eval_iter=5,
    start_context=format_input(val_data[0]), tokenizer=tokenizer
)

end_time = time.time()
execution_time_minutes = (end_time - start_time) / 60
print(f"Training completed in {execution_time_minutes:.2f} minutes.")

1
2
3
4
from previous_chapters import plot_losses

epochs_tensor = torch.linspace(0, num_epochs, len(train_losses))
plot_losses(epochs_tensor, tokens_seen, train_losses, val_losses)

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
torch.manual_seed(123)


for entry in test_data[:3]:

    input_text = format_input(entry)

    token_ids = generate(
        model=model,
        idx=text_to_token_ids(input_text, tokenizer).to(device),
        max_new_tokens=256,
        context_size=BASE_CONFIG["context_length"],
        eos_id=50256
    )
    generated_text = token_ids_to_text(token_ids, tokenizer)
    response_text = (
        generated_text[len(input_text):]
        .replace("### Response:", "")
        .strip()
)

    print(input_text)
    print(f"\nCorrect response:\n>> {entry['output']}")
    print(f"\nModel response:\n>> {response_text.strip()}")
    print("-------------------------------------")

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
#在整个测试集上运行模型，对测试集中的每个样本都生成答案
from tqdm import tqdm

for i, entry in tqdm(enumerate(test_data), total=len(test_data)):

    input_text = format_input(entry)

    token_ids = generate(
        model=model,
        idx=text_to_token_ids(input_text, tokenizer).to(device),
        max_new_tokens=256,
        context_size=BASE_CONFIG["context_length"],
        eos_id=50256
    )
    generated_text = token_ids_to_text(token_ids, tokenizer)
    response_text = generated_text[len(input_text):].replace("### Response:", "").strip()

    test_data[i]["model_response"] = response_text

#保存到json文件
with open("instruction-data-with-response.json", "w") as file:
    json.dump(test_data, file, indent=4)  # "indent" for pretty-printing

1
print(test_data[0])

1
2
3
4
5
6
7
8
9
import re


file_name = f"{re.sub(r'[ ()]', '', CHOOSE_MODEL) }-sft.pth"
torch.save(model.state_dict(), file_name)
print(f"Model saved as {file_name}") #Model saved as gpt2-medium355M-sft.pth

# Load model via
# model.load_state_dict(torch.load("gpt2-medium355M-sft.pth"))

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
import psutil

def check_if_running(process_name):
    running = False
    for proc in psutil.process_iter(["name"]):
        if process_name in proc.info["name"]:
            running = True
            break
    return running

ollama_running = check_if_running("ollama")

if not ollama_running:
    raise RuntimeError("Ollama not running. Launch ollama before proceeding.")
print("Ollama running:", check_if_running("ollama")) #Ollama running: True

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
42
43
44
45
46
47
48
49
import urllib.request

def query_model(
    prompt,
    model="llama3",
    url="http://localhost:11434/api/chat"
):
    # Create the data payload as a dictionary
    data = {
        "model": model,
        "messages": [
            {"role": "user", "content": prompt}
        ],
        "options": {     # Settings below are required for deterministic responses
            "seed": 123,
            "temperature": 0,
            "num_ctx": 2048
        }
    }


    # Convert the dictionary to a JSON formatted string and encode it to bytes
    payload = json.dumps(data).encode("utf-8")

    # Create a request object, setting the method to POST and adding necessary headers
    request = urllib.request.Request(
        url,
        data=payload,
        method="POST"
    )
    request.add_header("Content-Type", "application/json")

    # Send the request and capture the response
    response_data = ""
    with urllib.request.urlopen(request) as response:
        # Read and decode the response
        while True:
            line = response.readline().decode("utf-8")
            if not line:
                break
            response_json = json.loads(line)
            response_data += response_json["message"]["content"]

    return response_data


model = "llama3"
result = query_model("What do Llamas eat?", model)
print(result)

1
2
3
4
5
6
7
8
9
10
11
12
13
14
for entry in test_data[:3]:
    prompt = (
        f"Given the input `{format_input(entry)}` "
        f"and correct output `{entry['output']}`, "
        f"score the model response `{entry['model_response']}`"
        f" on a scale from 0 to 100, where 100 is the best score. "
    )
    print("\nDataset response:")
    print(">>", entry['output'])
    print("\nModel response:")
    print(">>", entry["model_response"])
    print("\nScore:")
    print(">>", query_model(prompt)) #给预测输出和GT，直接让Llama 3打分
    print("\n-------------------------")

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
#Evaluating the instruction fine-tuning LLM
def generate_model_scores(json_data, json_key, model="llama3"):
    scores = []
    for entry in tqdm(json_data, desc="Scoring entries"):
        prompt = (
            f"Given the input `{format_input(entry)}` "
            f"and correct output `{entry['output']}`, "
            f"score the model response `{entry[json_key]}`"
            f" on a scale from 0 to 100, where 100 is the best score. "
            f"Respond with the integer number only."
        )
        score = query_model(prompt, model)
        try:
            scores.append(int(score))
        except ValueError:
            print(f"Could not convert score: {score}")
            continue

    return scores


scores = generate_model_scores(test_data, "model_response")
print(f"Number of scores: {len(scores)} of {len(test_data)}")
print(f"Average score: {sum(scores)/len(scores):.2f}\n")