Supplementary code for the Build a Large Language Model From Scratch book by Sebastian Raschka Code repository: https://github.com/rasbt/LLMs-from-scratch

Load And Use Finetuned Model

This notebook contains minimal code to load the finetuned model that was instruction finetuned and saved in chapter 7 via ch07.ipynb.

from importlib.metadata import version

pkgs = [
    "tiktoken",    # Tokenizer
    "torch",       # Deep learning library
]
for p in pkgs:
    print(f"{p} version: {version(p)}")

---------------------------------------------------------------------------
PackageNotFoundError                      Traceback (most recent call last)
Cell In[1], line 8
      3 pkgs = [
      4     "tiktoken",    # Tokenizer
      5     "torch",       # Deep learning library
      6 ]
      7 for p in pkgs:
----> 8     print(f"{p} version: {version(p)}")

File /Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/importlib/metadata/__init__.py:946, in version(distribution_name)
    939 def version(distribution_name):
    940     """Get the version string for the named package.
    941 
    942     :param distribution_name: The name of the distribution package to query.
    943     :return: The version string for the package as defined in the package's
    944         "Version" metadata key.
    945     """
--> 946     return distribution(distribution_name).version

File /Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/importlib/metadata/__init__.py:919, in distribution(distribution_name)
    913 def distribution(distribution_name):
    914     """Get the ``Distribution`` instance for the named package.
    915 
    916     :param distribution_name: The name of the distribution package as a string.
    917     :return: A ``Distribution`` instance (or subclass thereof).
    918     """
--> 919     return Distribution.from_name(distribution_name)

File /Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/importlib/metadata/__init__.py:518, in Distribution.from_name(cls, name)
    516         return dist
    517 else:
--> 518     raise PackageNotFoundError(name)

PackageNotFoundError: No package metadata was found for tiktoken

from pathlib import Path

finetuned_model_path = Path("gpt2-medium355M-sft.pth")
if not finetuned_model_path.exists():
    print(
        f"Could not find '{finetuned_model_path}'.\n"
        "Run the `ch07.ipynb` notebook to finetune and save the finetuned model."
    )

from previous_chapters import GPTModel


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(")")
model = GPTModel(BASE_CONFIG)

import torch

model.load_state_dict(torch.load(
    "gpt2-medium355M-sft.pth",
    map_location=torch.device("cpu"),
    weights_only=True
))
model.eval();

import tiktoken

tokenizer = tiktoken.get_encoding("gpt2")

prompt = """Below is an instruction that describes a task. Write a response 
that appropriately completes the request.

### Instruction:
Convert the active sentence to passive: 'The chef cooks the meal every day.'
"""

from previous_chapters import (
    generate,
    text_to_token_ids,
    token_ids_to_text
)

def extract_response(response_text, input_text):
    return response_text[len(input_text):].replace("### Response:", "").strip()

torch.manual_seed(123)

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

response = token_ids_to_text(token_ids, tokenizer)
response = extract_response(response, prompt)
print(response)

The meal is cooked every day by the chef.