readCtrl_lambda / code /fine_tune_sft_dpo /unsloth_compiled_cache

1.52 MB

Ctrl+K

3 contributors

History: 1 commit

mshahidul

Initial commit of readCtrl code without large models

030876e 7 months ago

UnslothBCOTrainer.py

102 kB
Initial commit of readCtrl code without large models 7 months ago
UnslothCPOTrainer.py

91.7 kB
Initial commit of readCtrl code without large models 7 months ago
UnslothDPOTrainer.py

147 kB
Initial commit of readCtrl code without large models 7 months ago
UnslothGKDTrainer.py

58.8 kB
Initial commit of readCtrl code without large models 7 months ago
UnslothGRPOTrainer.py

210 kB
Initial commit of readCtrl code without large models 7 months ago
UnslothKTOTrainer.py

112 kB
Initial commit of readCtrl code without large models 7 months ago
UnslothNashMDTrainer.py

59.7 kB
Initial commit of readCtrl code without large models 7 months ago
UnslothORPOTrainer.py

88 kB
Initial commit of readCtrl code without large models 7 months ago
UnslothOnlineDPOTrainer.py

122 kB
Initial commit of readCtrl code without large models 7 months ago
UnslothPPOTrainer.py

79.6 kB
Initial commit of readCtrl code without large models 7 months ago
UnslothPRMTrainer.py

50.3 kB
Initial commit of readCtrl code without large models 7 months ago
UnslothRLOOTrainer.py

144 kB
Initial commit of readCtrl code without large models 7 months ago
UnslothRewardTrainer.py

63.3 kB
Initial commit of readCtrl code without large models 7 months ago
UnslothSFTTrainer.py

79.5 kB
Initial commit of readCtrl code without large models 7 months ago
UnslothXPOTrainer.py

62.3 kB
Initial commit of readCtrl code without large models 7 months ago
moe_utils.py

48.5 kB
Initial commit of readCtrl code without large models 7 months ago