gaoziyuan 4ead15822c 【Sync develop】support vl model name_mapping and ori_vocab_size (#2915) ...

* support vl ori_vacab_size

* support trainer_degree in name_mapping

* fix

2025-07-20 23:14:15 -07:00

..

ernie4_5_vl

【Sync develop】support vl model name_mapping and ori_vocab_size (#2915)

2025-07-20 23:14:15 -07:00

__init__.py

【Fearture】support qwen2 some func (#2740)

2025-07-08 12:03:04 +08:00

deepseek_v3.py

refactor rl get_name_mappings_to_training (#2847)

2025-07-15 07:31:42 -07:00

ernie4_5_moe.py

fix rollout_model and add rl ut (#2882)

2025-07-17 13:37:54 +08:00

ernie4_5_mtp.py

refactor rl get_name_mappings_to_training (#2847)

2025-07-15 07:31:42 -07:00

model_base.py

Simplify the Config code (#2770)

2025-07-14 19:50:05 +08:00

qwen2.py

refactor rl get_name_mappings_to_training (#2847)

2025-07-15 07:31:42 -07:00

qwen3.py

refactor rl get_name_mappings_to_training (#2847)

2025-07-15 07:31:42 -07:00

qwen3moe.py

refactor rl get_name_mappings_to_training (#2847)

2025-07-15 07:31:42 -07:00

tp_utils.py

Simplify the Config code (#2770)

2025-07-14 19:50:05 +08:00

utils.py

refactor rl get_name_mappings_to_training (#2847)

2025-07-15 07:31:42 -07:00