Skip to content

Fix KeyError in GPT-OSS weight conversion script #42007

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
merged 3 commits into from
Nov 6, 2025
Merged

Fix KeyError in GPT-OSS weight conversion script #42007

Changes from 2 commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
2c2e1c1
Fix KeyError in GPT-OSS weight conversion script
Aznix07 Nov 4, 2025
3b6cb42
Fix code quality: remove trailing whitespace
Aznix07 Nov 4, 2025
c94c1bb
Address review: use pop with defaults, remove commented code
Aznix07 Nov 6, 2025
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
30 changes: 22 additions & 8 deletions src/transformers/models/gpt_oss/convert_gpt_oss_weights_to_hf.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -157,14 +157,28 @@ def write_model(
original_config = json.loads((Path(input_base_path) / "config.json").read_text())

num_local_experts = original_config.pop("num_experts")
rope_parameters = {
"beta_fast": float(original_config.pop("rope_ntk_beta")),
"beta_slow": float(original_config.pop("rope_ntk_alpha")),
"factor": float(original_config.pop("rope_parameters_factor")),
"rope_type": "yarn",
"truncate": False,
"original_max_position_embeddings": 4096,
}

# Handle both old and new config formats for rope_parameters
if "rope_parameters" in original_config:
# New format: rope_parameters already exists as a dict
rope_parameters = original_config.pop("rope_parameters")
# Ensure rope_type is set
if "rope_type" not in rope_parameters:
rope_parameters["rope_type"] = "yarn"
else:
# Old format: construct rope_parameters from individual keys
# Fallback to default values if rop_parameters is missing
rope_parameters = {
# "beta_fast": float(original_config.pop("rope_ntk_beta")),
# "beta_slow": float(original_config.pop("rope_ntk_alpha")),
# "factor": float(original_config.pop("rope_parameters_factor")),
Copy link
Member

@zucchini-nlp zucchini-nlp Nov 5, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

can we hardcode the values safely? I think it was better to obtain from the config

"rope_type": "yarn",
"truncate": False,
"original_max_position_embeddings": 4096,
"beta_fast": 32.0,
"beta_slow": 1.0,
"factor": 32.0,
}

config = GptOssConfig(
num_local_experts=num_local_experts,
Expand Down