Skip to content

generate_hf_golden_logits: propagate trust_remote_code to tokenizer; add --hf-load-dtype=auto #3775

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
copybara-service merged 1 commit into from
Apr 29, 2026
+9 −4
Merged

generate_hf_golden_logits: propagate trust_remote_code to tokenizer; add --hf-load-dtype=auto #3775

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: 9 additions & 4 deletions tests/assets/logits_generation/generate_hf_golden_logits.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -85,15 +85,20 @@ def save_golden_logits(

model_class = AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained(model_id)
tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=trust_remote_code)
print(f"loading model from {hf_model_path}")

if hf_load_dtype == "float32":
torch_dtype = torch.float32
elif hf_load_dtype == "bfloat16":
torch_dtype = torch.bfloat16
elif hf_load_dtype == "auto":
# Preserve per-tensor dtypes from safetensors metadata, useful for mixed-
# precision checkpoints where forcing a single dtype would corrupt non-
# default tensors.
torch_dtype = None
else:
raise ValueError
raise ValueError(f"unsupported --hf-load-dtype: {hf_load_dtype}")

model = model_class.from_pretrained(
hf_model_path,
Expand Down Expand Up @@ -194,9 +199,9 @@ def main(raw_args=None) -> None:
"--hf-load-dtype",
type=str,
required=False,
choices=["float32", "bfloat16"],
choices=["float32", "bfloat16", "auto"],
default="float32",
help="model_class.from_pretrained: dtype",
help="model_class.from_pretrained: dtype. 'auto' preserves per-tensor dtypes from safetensors.",
)
parser.add_argument(
"--trust-remote-code",
Expand Down
Loading