Skip to content

Clean examples #1791

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

Merged
kashif merged 2 commits into from
Jul 4, 2024
Merged

Clean examples #1791

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
7d05e45
clean examples
qgallouedec Jul 1, 2024
0696575
Merge branch 'huggingface:main' into clean-examples
qgallouedec Jul 1, 2024
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
1 change: 0 additions & 1 deletion examples/scripts/cpo.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -77,7 +77,6 @@ class ScriptArguments:
# Model & Tokenizer
################
model = AutoModelForCausalLM.from_pretrained(model_config.model_name_or_path)
peft_config = get_peft_config(model_config)
tokenizer = AutoTokenizer.from_pretrained(model_config.model_name_or_path)
if tokenizer.pad_token is None:
tokenizer.pad_token = tokenizer.eos_token
Expand Down
2 changes: 1 addition & 1 deletion examples/scripts/dpo.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -172,7 +172,7 @@ def process(row):
train_dataset=train_dataset,
eval_dataset=eval_dataset,
tokenizer=tokenizer,
peft_config=get_peft_config(model_config),
peft_config=peft_config,
callbacks=[RichProgressCallback] if TRL_USE_RICH else None,
)

Expand Down
10 changes: 3 additions & 7 deletions examples/scripts/dpo_visual.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -143,12 +143,8 @@ def process(row):
row["rejected"] = processor.apply_chat_template(row["rejected"], tokenize=False)

if "images" in row:
for idx, img in enumerate(row["images"]): # Resize each image so the largest side is 640 pixels
ratio = min(1.0, 640 / max(img.size))
new_size = (int(img.size[0] * ratio), int(img.size[1] * ratio))
row["images"][idx] = img.resize(new_size)
row["images"] = row["images"]

for img in row["images"]: # Resize each image so the largest side is 640 pixels
img.thumbnail((640, 640)) # Resize the image to at most 640x640 pixels
return row

with PartialState().local_main_process_first():
Expand All @@ -167,7 +163,7 @@ def process(row):
train_dataset=train_dataset,
eval_dataset=eval_dataset,
tokenizer=processor,
peft_config=get_peft_config(model_config),
peft_config=peft_config,
callbacks=[RichProgressCallback] if TRL_USE_RICH else None,
)

Expand Down
1 change: 0 additions & 1 deletion examples/scripts/orpo.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -77,7 +77,6 @@ class ScriptArguments:
# Model & Tokenizer
################
model = AutoModelForCausalLM.from_pretrained(model_config.model_name_or_path)
peft_config = get_peft_config(model_config)
tokenizer = AutoTokenizer.from_pretrained(model_config.model_name_or_path)
if tokenizer.pad_token is None:
tokenizer.pad_token = tokenizer.eos_token
Expand Down