Preserves the source tokenizer's eos_token in tokenizer_config.json after merged saves so runtimes such as vLLM read the correct stop token. Centralized inside the patched tokenizer save_pretrained so all save paths (merged_16bit, GGUF, torchao, push_to_hub) benefit, with filename_prefix support. Fixes #5386 |
||
|---|---|---|
| .. | ||
| gpt-oss-merge | ||
| language_models | ||
| non_peft | ||
| text_to_speech_models | ||
| vision_models | ||
| test_fix_sentencepiece_gguf_robustness.py | ||
| test_patch_saving_none_tokenizer.py | ||
| test_preserve_tokenizer_eos_token.py | ||
| test_save_shell_injection.py | ||
| test_unsloth_save.py | ||