Skip to content

Fix config utils #1357

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
hiworldwzj merged 2 commits into from
Jun 16, 2026
Merged

Fix config utils #1357

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
5ef948b
fix: fix a eos id bug
Jun 16, 2026
c2fcf85
fix
hiworldwzj Jun 16, 2026
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
24 changes: 22 additions & 2 deletions lightllm/utils/config_utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -238,16 +238,36 @@ def get_eos_token_ids(model_path: str) -> Optional[List[int]]:

# Qwen3.5 checkpoints can have an eos_token_id in config that differs from
# tokenizer.eos_token_id. In practice tokenizer.eos_token_id is the reliable
# stop id (<|im_end|>) for detokenization/stop behavior.
# stop id (<|im_end|>, <|endoftext|>) for detokenization/stop behavior.
try:
config_json = get_config_json(model_path)
model_type = config_json.get("model_type") or config_json.get("text_config", {}).get("model_type")
if model_type in {"qwen3_5", "qwen3_5_text", "qwen3_5_moe", "qwen3_5_moe_text"}:
from transformers import AutoTokenizer

eos_token_ids = []

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=False)
if tokenizer.eos_token_id is not None:
return [int(tokenizer.eos_token_id)]
eos_token_ids.append(int(tokenizer.eos_token_id))
Comment on lines 251 to +252

@gemini-code-assist gemini-code-assist Bot Jun 16, 2026

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

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

high

If tokenizer.eos_token_id is a list (which is common for tokenizers with multiple end-of-sequence tokens), calling int(tokenizer.eos_token_id) will raise a TypeError. Since this block is wrapped in a try...except Exception block, the error will be silently caught, and the function will fall back to the default behavior, bypassing the Qwen3.5-specific logic entirely. We should handle both int and list/iterable types for tokenizer.eos_token_id.

Suggested change
if tokenizer.eos_token_id is not None:
return [int(tokenizer.eos_token_id)]
eos_token_ids.append(int(tokenizer.eos_token_id))
if tokenizer.eos_token_id is not None:
if isinstance(tokenizer.eos_token_id, list):
eos_token_ids.extend(int(eid) for eid in tokenizer.eos_token_id)
else:
eos_token_ids.append(int(tokenizer.eos_token_id))


generation_config_path = os.path.join(model_path, "generation_config.json")
if os.path.exists(generation_config_path):
with open(generation_config_path, "r") as file:
generation_eos_token_id = json.load(file).get("eos_token_id")
if isinstance(generation_eos_token_id, int):
eos_token_ids.append(generation_eos_token_id)
elif isinstance(generation_eos_token_id, list):
eos_token_ids.extend(generation_eos_token_id)

config_eos_token_id = _get_config_llm_keyvalue(model_path=model_path, key_name=["eos_token_id"])
if isinstance(config_eos_token_id, int):
eos_token_ids.append(config_eos_token_id)
elif isinstance(config_eos_token_id, list):
eos_token_ids.extend(config_eos_token_id)

if eos_token_ids:
return list(set(eos_token_ids))
except Exception:
pass

Expand Down
Loading