2/27/25, 11:59 PM PLC_codeGen_codelama.

ipynb - Colab

pip install transformers accelerate torch datasets peft bitsandbytes

https://colab.research.google.com/drive/1p58RwOA0-k0Gq5edNOY6mFis61SBuyae#scrollTo=h40RpyaynDYP&printMode=true 1/6
2/27/25, 11:59 PM PLC_codeGen_codelama.ipynb - Colab
Success u y u sta ed d a cuda cupt cu .5.8
Attempting uninstall: nvidia-cublas-cu12
Found existing installation: nvidia-cublas-cu12 12.5.3.2
Uninstalling nvidia-cublas-cu12-12.5.3.2:
Successfully uninstalled nvidia-cublas-cu12-12.5.3.2
Attempting uninstall: nvidia-cusparse-cu12
Found existing installation: nvidia-cusparse-cu12 12.5.1.3
Uninstalling nvidia-cusparse-cu12-12.5.1.3:
Successfully uninstalled nvidia-cusparse-cu12-12.5.1.3
Attempting uninstall: nvidia-cudnn-cu12
Found existing installation: nvidia-cudnn-cu12 9.3.0.75
Uninstalling nvidia-cudnn-cu12-9.3.0.75:
Successfully uninstalled nvidia-cudnn-cu12-9.3.0.75
Attempting uninstall: nvidia-cusolver-cu12
Found existing installation: nvidia-cusolver-cu12 11.6.3.83
Uninstalling nvidia-cusolver-cu12-11.6.3.83:
Successfully uninstalled nvidia-cusolver-cu12-11.6.3.83
Successfully installed bitsandbytes-0.45.3 datasets-3.3.2 dill-0.3.8 multiprocess-0.70.16 nvidia-cublas-cu12-12.4.5.8 nvidia-cuda-cupt

from datasets import Dataset

from transformers import AutoTokenizer

# Load CSV dataset

import pandas as pd

df = pd.read_csv("dataset.csv")

# Load tokenizer
model_name = "codellama/CodeLlama-7b-hf"
tokenizer = AutoTokenizer.from_pretrained(model_name)

# 🚨 FIX: Assign padding token explicitly

tokenizer.pad_token = tokenizer.eos_token # Use EOS token for padding

# Tokenize dataset
def tokenize_function(examples):
inputs = tokenizer(
examples["name"], truncation=True, padding="max_length", max_length=512
)
targets = tokenizer(

https://colab.research.google.com/drive/1p58RwOA0-k0Gq5edNOY6mFis61SBuyae#scrollTo=h40RpyaynDYP&printMode=true 2/6
2/27/25, 11:59 PM PLC_codeGen_codelama.ipynb - Colab
examples["code"], truncation=True, padding="max_length", max_length=512
)

return {
"input_ids": inputs["input_ids"],
"attention_mask": inputs["attention_mask"],
"labels": targets["input_ids"], # Expected output
}

# Convert Pandas DataFrame to Hugging Face Dataset

dataset = Dataset.from_pandas(df)

# Apply tokenization
dataset = dataset.map(tokenize_function, batched=True, remove_columns=["name", "code"])

# Split dataset into training and validation sets

dataset = dataset.train_test_split(test_size=0.1)

print("✅ Dataset successfully tokenized and prepared!")

Map: 100% 50/50 [00:00<00:00, 449.15 examples/s]

✅ Dataset successfully tokenized and prepared!

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig

# Define 4-bit quantization settings

bnb_config = BitsAndBytesConfig(
load_in_4bit=True,
bnb_4bit_quant_type="nf4",
bnb_4bit_use_double_quant=True,
bnb_4bit_compute_dtype=torch.float16
)

model_name = "codellama/CodeLlama-7b-hf"

# Load tokenizer
tokenizer = AutoTokenizer.from_pretrained(model_name)
https://colab.research.google.com/drive/1p58RwOA0-k0Gq5edNOY6mFis61SBuyae#scrollTo=h40RpyaynDYP&printMode=true 3/6
2/27/25, 11:59 PM PLC_codeGen_codelama.ipynb - Colab

# Free GPU memory before loading

torch.cuda.empty_cache()

from accelerate import infer_auto_device_map

device_map = infer_auto_device_map(model, max_memory={0: "12GiB", "cpu": "20GiB"})

model = AutoModelForCausalLM.from_pretrained(
model_name,
quantization_config=bnb_config,
device_map=device_map,
torch_dtype=torch.float16,
)

print("✅ Model loaded successfully on Google Colab's T4 GPU!")

---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
<ipython-input-18-dfc82b45ae0f> in <cell line: 0>()
21 device_map = infer_auto_device_map(model, max_memory={0: "12GiB", "cpu": "20GiB"})
22
---> 23 model = AutoModelForCausalLM.from_pretrained(
24 model_name,
25 quantization_config=bnb_config,

2 frames
/usr/local/lib/python3.11/dist-packages/transformers/quantizers/quantizer_bnb_4bit.py in validate_environment(self, *args, **kwargs)
101 pass
102 elif "cpu" in device_map_without_lm_head.values() or "disk" in device_map_without_lm_head.values():
--> 103 raise ValueError(
104 "Some modules are dispatched on the CPU or the disk. Make sure you have enough GPU RAM to fit the "
105 "quantized model. If you want to dispatch the model on the CPU or the disk while keeping these modules "

ValueError: Some modules are dispatched on the CPU or the disk. Make sure you have enough GPU RAM to fit the quantized model. If you
want to dispatch the model on the CPU or the disk while keeping these modules in 32-bit, you need to set
`llm_int8_enable_fp32_cpu_offload=True` and pass a custom `device_map` to `from_pretrained`. Check
https://huggingface.co/docs/transformers/main/en/main_classes/quantization#offload-between-cpu-and-gpu for more details.

https://colab.research.google.com/drive/1p58RwOA0-k0Gq5edNOY6mFis61SBuyae#scrollTo=h40RpyaynDYP&printMode=true 4/6
2/27/25, 11:59 PM PLC_codeGen_codelama.ipynb - Colab

Next steps: Explain error

# Load fine-tuned model

tokenizer = AutoTokenizer.from_pretrained("./finetuned_codellama")
model = AutoModelForCausalLM.from_pretrained("./finetuned_codellama", torch_dtype=torch.float16, device_map="auto")

# New Prompt
prompt = "generate ladder of bottle filling system on conveyer belt"

# Tokenize input
inputs = tokenizer(prompt, return_tensors="pt").to("cuda")

# Generate code
with torch.no_grad():
outputs = model.generate(**inputs, max_new_tokens=100)

# Decode output
generated_code = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(generated_code)

https://colab.research.google.com/drive/1p58RwOA0-k0Gq5edNOY6mFis61SBuyae#scrollTo=h40RpyaynDYP&printMode=true 5/6
2/27/25, 11:59 PM PLC_codeGen_codelama.ipynb - Colab

https://colab.research.google.com/drive/1p58RwOA0-k0Gq5edNOY6mFis61SBuyae#scrollTo=h40RpyaynDYP&printMode=true 6/6