> For the complete documentation index, see [llms.txt](https://boinc-ai.gitbook.io/peft/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://boinc-ai.gitbook.io/peft/task-guides/prompt-tuning-for-causal-language-modeling.md).

# Prompt tuning for causal language modeling

Prompting helps guide language model behavior by adding some input text specific to a task. Prompt tuning is an additive method for only training and updating the newly added prompt tokens to a pretrained model. This way, you can use one pretrained model whose weights are frozen, and train and update a smaller set of prompt parameters for each downstream task instead of fully finetuning a separate model. As models grow larger and larger, prompt tuning can be more efficient, and results are even better as model parameters scale.

💡 Read [The Power of Scale for Parameter-Efficient Prompt Tuning](https://arxiv.org/abs/2104.08691) to learn more about prompt tuning.

This guide will show you how to apply prompt tuning to train a [`bloomz-560m`](https://huggingface.co/bigscience/bloomz-560m) model on the `twitter_complaints` subset of the [RAFT](https://huggingface.co/datasets/ought/raft) dataset.

Before you begin, make sure you have all the necessary libraries installed:

Copied

```
!pip install -q peft transformers datasets
```

### Setup

Start by defining the model and tokenizer, the dataset and the dataset columns to train on, some training hyperparameters, and the [PromptTuningConfig](https://huggingface.co/docs/peft/main/en/package_reference/tuners#peft.PromptTuningConfig). The [PromptTuningConfig](https://huggingface.co/docs/peft/main/en/package_reference/tuners#peft.PromptTuningConfig) contains information about the task type, the text to initialize the prompt embedding, the number of virtual tokens, and the tokenizer to use:

Copied

```
from transformers import AutoModelForCausalLM, AutoTokenizer, default_data_collator, get_linear_schedule_with_warmup
from peft import get_peft_config, get_peft_model, PromptTuningInit, PromptTuningConfig, TaskType, PeftType
import torch
from datasets import load_dataset
import os
from torch.utils.data import DataLoader
from tqdm import tqdm

device = "cuda"
model_name_or_path = "bigscience/bloomz-560m"
tokenizer_name_or_path = "bigscience/bloomz-560m"
peft_config = PromptTuningConfig(
    task_type=TaskType.CAUSAL_LM,
    prompt_tuning_init=PromptTuningInit.TEXT,
    num_virtual_tokens=8,
    prompt_tuning_init_text="Classify if the tweet is a complaint or not:",
    tokenizer_name_or_path=model_name_or_path,
)

dataset_name = "twitter_complaints"
checkpoint_name = f"{dataset_name}_{model_name_or_path}_{peft_config.peft_type}_{peft_config.task_type}_v1.pt".replace(
    "/", "_"
)
text_column = "Tweet text"
label_column = "text_label"
max_length = 64
lr = 3e-2
num_epochs = 50
batch_size = 8
```

### Load dataset

For this guide, you’ll load the `twitter_complaints` subset of the [RAFT](https://huggingface.co/datasets/ought/raft) dataset. This subset contains tweets that are labeled either `complaint` or `no complaint`:

Copied

```
dataset = load_dataset("ought/raft", dataset_name)
dataset["train"][0]
{"Tweet text": "@HMRCcustomers No this is my first job", "ID": 0, "Label": 2}
```

To make the `Label` column more readable, replace the `Label` value with the corresponding label text and store them in a `text_label` column. You can use the [map](https://huggingface.co/docs/datasets/main/en/package_reference/main_classes#datasets.Dataset.map) function to apply this change over the entire dataset in one step:

Copied

```
classes = [k.replace("_", " ") for k in dataset["train"].features["Label"].names]
dataset = dataset.map(
    lambda x: {"text_label": [classes[label] for label in x["Label"]]},
    batched=True,
    num_proc=1,
)
dataset["train"][0]
{"Tweet text": "@HMRCcustomers No this is my first job", "ID": 0, "Label": 2, "text_label": "no complaint"}
```

### Preprocess dataset

Next, you’ll setup a tokenizer; configure the appropriate padding token to use for padding sequences, and determine the maximum length of the tokenized labels:

Copied

```
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path)
if tokenizer.pad_token_id is None:
    tokenizer.pad_token_id = tokenizer.eos_token_id
target_max_length = max([len(tokenizer(class_label)["input_ids"]) for class_label in classes])
print(target_max_length)
3
```

Create a `preprocess_function` to:

1. Tokenize the input text and labels.
2. For each example in a batch, pad the labels with the tokenizers `pad_token_id`.
3. Concatenate the input text and labels into the `model_inputs`.
4. Create a separate attention mask for `labels` and `model_inputs`.
5. Loop through each example in the batch again to pad the input ids, labels, and attention mask to the `max_length` and convert them to PyTorch tensors.

Copied

```
def preprocess_function(examples):
    batch_size = len(examples[text_column])
    inputs = [f"{text_column} : {x} Label : " for x in examples[text_column]]
    targets = [str(x) for x in examples[label_column]]
    model_inputs = tokenizer(inputs)
    labels = tokenizer(targets)
    for i in range(batch_size):
        sample_input_ids = model_inputs["input_ids"][i]
        label_input_ids = labels["input_ids"][i] + [tokenizer.pad_token_id]
        # print(i, sample_input_ids, label_input_ids)
        model_inputs["input_ids"][i] = sample_input_ids + label_input_ids
        labels["input_ids"][i] = [-100] * len(sample_input_ids) + label_input_ids
        model_inputs["attention_mask"][i] = [1] * len(model_inputs["input_ids"][i])
    # print(model_inputs)
    for i in range(batch_size):
        sample_input_ids = model_inputs["input_ids"][i]
        label_input_ids = labels["input_ids"][i]
        model_inputs["input_ids"][i] = [tokenizer.pad_token_id] * (
            max_length - len(sample_input_ids)
        ) + sample_input_ids
        model_inputs["attention_mask"][i] = [0] * (max_length - len(sample_input_ids)) + model_inputs[
            "attention_mask"
        ][i]
        labels["input_ids"][i] = [-100] * (max_length - len(sample_input_ids)) + label_input_ids
        model_inputs["input_ids"][i] = torch.tensor(model_inputs["input_ids"][i][:max_length])
        model_inputs["attention_mask"][i] = torch.tensor(model_inputs["attention_mask"][i][:max_length])
        labels["input_ids"][i] = torch.tensor(labels["input_ids"][i][:max_length])
    model_inputs["labels"] = labels["input_ids"]
    return model_inputs
```

Use the [map](https://huggingface.co/docs/datasets/main/en/package_reference/main_classes#datasets.Dataset.map) function to apply the `preprocess_function` to the entire dataset. You can remove the unprocessed columns since the model won’t need them:

Copied

```
processed_datasets = dataset.map(
    preprocess_function,
    batched=True,
    num_proc=1,
    remove_columns=dataset["train"].column_names,
    load_from_cache_file=False,
    desc="Running tokenizer on dataset",
)
```

Create a [`DataLoader`](https://pytorch.org/docs/stable/data.html#torch.utils.data.DataLoader) from the `train` and `eval` datasets. Set `pin_memory=True` to speed up the data transfer to the GPU during training if the samples in your dataset are on a CPU.

Copied

```
train_dataset = processed_datasets["train"]
eval_dataset = processed_datasets["test"]


train_dataloader = DataLoader(
    train_dataset, shuffle=True, collate_fn=default_data_collator, batch_size=batch_size, pin_memory=True
)
eval_dataloader = DataLoader(eval_dataset, collate_fn=default_data_collator, batch_size=batch_size, pin_memory=True)
```

### Train

You’re almost ready to setup your model and start training!

Initialize a base model from [AutoModelForCausalLM](https://huggingface.co/docs/transformers/main/en/model_doc/auto#transformers.AutoModelForCausalLM), and pass it and `peft_config` to the `get_peft_model()` function to create a [PeftModel](https://huggingface.co/docs/peft/main/en/package_reference/peft_model#peft.PeftModel). You can print the new [PeftModel](https://huggingface.co/docs/peft/main/en/package_reference/peft_model#peft.PeftModel)’s trainable parameters to see how much more efficient it is than training the full parameters of the original model!

Copied

```
model = AutoModelForCausalLM.from_pretrained(model_name_or_path)
model = get_peft_model(model, peft_config)
print(model.print_trainable_parameters())
"trainable params: 8192 || all params: 559222784 || trainable%: 0.0014648902430985358"
```

Setup an optimizer and learning rate scheduler:

Copied

```
optimizer = torch.optim.AdamW(model.parameters(), lr=lr)
lr_scheduler = get_linear_schedule_with_warmup(
    optimizer=optimizer,
    num_warmup_steps=0,
    num_training_steps=(len(train_dataloader) * num_epochs),
)
```

Move the model to the GPU, then write a training loop to start training!

Copied

```
model = model.to(device)

for epoch in range(num_epochs):
    model.train()
    total_loss = 0
    for step, batch in enumerate(tqdm(train_dataloader)):
        batch = {k: v.to(device) for k, v in batch.items()}
        outputs = model(**batch)
        loss = outputs.loss
        total_loss += loss.detach().float()
        loss.backward()
        optimizer.step()
        lr_scheduler.step()
        optimizer.zero_grad()

    model.eval()
    eval_loss = 0
    eval_preds = []
    for step, batch in enumerate(tqdm(eval_dataloader)):
        batch = {k: v.to(device) for k, v in batch.items()}
        with torch.no_grad():
            outputs = model(**batch)
        loss = outputs.loss
        eval_loss += loss.detach().float()
        eval_preds.extend(
            tokenizer.batch_decode(torch.argmax(outputs.logits, -1).detach().cpu().numpy(), skip_special_tokens=True)
        )

    eval_epoch_loss = eval_loss / len(eval_dataloader)
    eval_ppl = torch.exp(eval_epoch_loss)
    train_epoch_loss = total_loss / len(train_dataloader)
    train_ppl = torch.exp(train_epoch_loss)
    print(f"{epoch=}: {train_ppl=} {train_epoch_loss=} {eval_ppl=} {eval_epoch_loss=}")
```

### Share model

You can store and share your model on the Hub if you’d like. Log in to your BOINC AI account and enter your token when prompted:

Copied

```
from boincai_hub import notebook_login

notebook_login()
```

Use the [push\_to\_hub](https://huggingface.co/docs/transformers/main/en/main_classes/model#transformers.PreTrainedModel.push_to_hub) function to upload your model to a model repository on the Hub:

Copied

```
peft_model_id = "your-name/bloomz-560m_PROMPT_TUNING_CAUSAL_LM"
model.push_to_hub("your-name/bloomz-560m_PROMPT_TUNING_CAUSAL_LM", use_auth_token=True)
```

Once the model is uploaded, you’ll see the model file size is only 33.5kB! 🤏

### Inference

Let’s try the model on a sample input for inference. If you look at the repository you uploaded the model to, you’ll see a `adapter_config.json` file. Load this file into [PeftConfig](https://huggingface.co/docs/peft/main/en/package_reference/config#peft.PeftConfig) to specify the `peft_type` and `task_type`. Then you can load the prompt tuned model weights, and the configuration into [from\_pretrained()](https://huggingface.co/docs/peft/main/en/package_reference/peft_model#peft.PeftModel.from_pretrained) to create the [PeftModel](https://huggingface.co/docs/peft/main/en/package_reference/peft_model#peft.PeftModel):

Copied

```
from peft import PeftModel, PeftConfig

peft_model_id = "stevhliu/bloomz-560m_PROMPT_TUNING_CAUSAL_LM"

config = PeftConfig.from_pretrained(peft_model_id)
model = AutoModelForCausalLM.from_pretrained(config.base_model_name_or_path)
model = PeftModel.from_pretrained(model, peft_model_id)
```

Grab a tweet and tokenize it:

Copied

```
inputs = tokenizer(
    f'{text_column} : {"@nationalgridus I have no water and the bill is current and paid. Can you do something about this?"} Label : ',
    return_tensors="pt",
)
```

Put the model on a GPU and *generate* the predicted label:

Copied

```
model.to(device)

with torch.no_grad():
    inputs = {k: v.to(device) for k, v in inputs.items()}
    outputs = model.generate(
        input_ids=inputs["input_ids"], attention_mask=inputs["attention_mask"], max_new_tokens=10, eos_token_id=3
    )
    print(tokenizer.batch_decode(outputs.detach().cpu().numpy(), skip_special_tokens=True))
[
    "Tweet text : @nationalgridus I have no water and the bill is current and paid. Can you do something about this? Label : complaint"
]
```