hanluzhi0429@gmail.com 165d823891 [2025.06.22] add reward model PPO GRPO train code

2025-06-22 23:31:24 +08:00

..

configuration_dolly.py

[2025.06.19] update train code, pretoken corpus

2025-06-19 17:00:27 +08:00

modeling_dolly.py

[2025.06.17] update train code

2025-06-17 17:17:49 +08:00

step0_train_tokenizer_jsonl.py

[2025.06.19] update train code, pretoken corpus

2025-06-19 17:00:27 +08:00

step0_train_tokenizer_parquet.py

[2025.06.19] update train code, pretoken corpus

2025-06-19 17:00:27 +08:00

step1_init_model_weights.py

[2025.06.17] update train code

2025-06-17 17:17:49 +08:00

step1.1_count_tokens_length.py

[2025.06.19] update train code, pretoken corpus

2025-06-19 17:00:27 +08:00

step2_get_tokens_from_parquet.py

[2025.06.19] update train code, pretoken corpus

2025-06-19 17:00:27 +08:00

step3_train_llm.py

[2025.06.19] update train code, pretoken corpus

2025-06-19 17:00:27 +08:00

step4_cold_start.py

[2025.06.22] add reward model、PPO、GRPO train code

2025-06-22 22:57:51 +08:00

step5.0_train_reward_model.py

[2025.06.22] add reward model PPO GRPO train code

2025-06-22 23:31:24 +08:00

step5.1_PPO.py

[2025.06.22] add reward model、PPO、GRPO train code

2025-06-22 22:57:51 +08:00

step5.2_GRPO.py

[2025.06.22] add reward model、PPO、GRPO train code

2025-06-22 22:57:51 +08:00