[model] support GLM4.6v (#9586)

This commit is contained in:
Hertz
2025-12-09 11:06:42 +08:00
committed by GitHub
parent 5744f1ea94
commit c1f5f8fff6
3 changed files with 19 additions and 5 deletions

View File

@@ -78,8 +78,11 @@ def run_sft(
# Compatible with Transformers v4 and Transformers v5
if is_transformers_version_greater_than("5.0.0RC0"):
extra_special_tokens = getattr(tokenizer, "_extra_special_tokens", [])
extra_ids = tokenizer.convert_tokens_to_ids(extra_special_tokens)
extra_ids = getattr(tokenizer, "additional_special_tokens_ids", None)
if not isinstance(extra_ids, list):
extra_special_tokens = getattr(tokenizer, "_extra_special_tokens", [])
string_tokens = [str(t) for t in extra_special_tokens]
extra_ids = tokenizer.convert_tokens_to_ids(string_tokens)
all_eos_ids = [tokenizer.eos_token_id] + [i for i in extra_ids if i != -1]
unique_eos_ids = list(dict.fromkeys(all_eos_ids))
gen_kwargs["eos_token_id"] = unique_eos_ids