Skip to content

Change use of setup_chat_template to clone_chat_template #1167

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
qheaden wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Change use of setup_chat_template to clone_chat_template #1167

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
13 changes: 10 additions & 3 deletions chapters/en/chapter11/3.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -99,7 +99,7 @@ Now that we understand the key components, let's implement the training with pro

```python
from datasets import load_dataset
from trl import SFTConfig, SFTTrainer
from trl import SFTConfig, SFTTrainer, clone_chat_template
import torch

# Set device
Expand All @@ -110,12 +110,19 @@ dataset = load_dataset("HuggingFaceTB/smoltalk", "all")

# Configure model and tokenizer
model_name = "HuggingFaceTB/SmolLM2-135M"
instruct_model_name = "HuggingFaceTB/SmolLM2-135M-Instruct"

model = AutoModelForCausalLM.from_pretrained(pretrained_model_name_or_path=model_name).to(
device
)
tokenizer = AutoTokenizer.from_pretrained(pretrained_model_name_or_path=model_name)
# Setup chat template
model, tokenizer = setup_chat_format(model=model, tokenizer=tokenizer)

# Setup chat template by cloning it from the tokenizer used by the instruct version of the model
model, tokenizer, added_tokens = clone_chat_template(
model=model,
tokenizer=tokenizer,
source_tokenizer_path=instruct_model_name
)

# Configure trainer
training_args = SFTConfig(
Expand Down
Loading