Text Generation
PEFT
Safetensors
English
lora
grpo
trl
rlvr
reasoning
token-efficiency
negative-results
Instructions to use AlexWortega/llm-cipher-reasoning-loras with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use AlexWortega/llm-cipher-reasoning-loras with PEFT:
Task type is invalid.
- Notebooks
- Google Colab
- Kaggle
Ctrl+K
- ckpt_g0_4_az
- ckpt_g0_5_drgrpo
- ckpt_g0_6_hapo
- ckpt_g1_1_cod
- ckpt_g1_scale_eff3
- ckpt_g2_1_cod70
- ckpt_g2_2_codcos
- ckpt_g3_1_diffaware
- ckpt_g4_1_klanchor
- ckpt_g5_1_aimemix
- ckpt_g5_2_mathmix
- ckpt_phase0
- ckpt_phase0_r32
- ckpt_phase1
- ckpt_phase1_scaled
- ckpt_phase_eff
- ckpt_phase_eff3
- ckpt_phase_eff_mtword
- ckpt_phase_eff_target20
- ckpt_roundE_supertoken
- 2.88 kB
- 7.64 kB