@wassname is the most recent version of the notebook broken? running it as is doesn't seem to ablate the refusals. The intervention generations still refuse, but the fully "merged" orthogonalized ones are more helpful.
wing lian PRO
winglian
AI & ML interests
None yet
Recent Activity
liked
a dataset
4 days ago
KodCode/KodCode-Light-RL-10K
liked
a dataset
4 days ago
open-r1/verifiable-coding-problems-python_decontaminated
liked
a dataset
4 days ago
AI-MO/NuminaMath-LEAN
Organizations
replied to
their
post
over 1 year ago
Sorry about that! Public now.
posted
an
update
over 1 year ago
Post
Full fine-tuning of Microsoft's Phi2 on a single 4090 is now supported in axolotl. Thanks to
@abacaj
and
@vikhyatk
for their help with gradient checkpointing and flash attention fixes.
alpaca finetune: openaccess-ai-collective/phi2-alpaca
wandb: https://wandb.ai/oaaic/phi2/runs/00pc4ugb?workspace=user-wing-lian
merged PR: https://github.com/OpenAccess-AI-Collective/axolotl/pull/1058
alpaca finetune: openaccess-ai-collective/phi2-alpaca
wandb: https://wandb.ai/oaaic/phi2/runs/00pc4ugb?workspace=user-wing-lian
merged PR: https://github.com/OpenAccess-AI-Collective/axolotl/pull/1058
-
- 8 replies