Goekdeniz-Guelmez 9fd6a5b6d0 adding PPO like clipping adapted from trl

2025-03-11 09:08:38 +01:00

..

__init__.py

LoRA: Extract small function (#614)

2024-06-02 06:38:42 -07:00

datasets.py

adding custom system message integration in dataset, more opimizations (generates now faster, while same RAM usage), fix for the identical generatrions, seperated the reward functions into a seperate file.

2025-02-24 20:49:22 +01:00

dora.py

Feature: QDoRA (#891)

2024-09-30 08:01:11 -07:00

grpo_reward_functions.py

updates

2025-03-05 12:59:41 +01:00

grpo_trainer.py

adding PPO like clipping adapted from trl

2025-03-11 09:08:38 +01:00

lora.py

Allow the entire model to be targed for LoRA and DoRA fine tuning: LoRA and DoRA embeddings with small DoRALinear bug fix (#914)

2024-08-16 07:38:36 -07:00

trainer.py

fix lora timings after validation (#1278)

2025-02-11 16:48:55 -08:00

utils.py

Merge branch 'ml-explore:main' into adding-GRPO-training

2025-03-08 22:41:10 +01:00