panopstor/llama32vis
Image-Text-to-Text
•
Updated
Victor Hall
panopstor
AI & ML interests
data engineering, production infrastructure, product development
Recent Activity
updated
a model
about 19 hours ago
panopstor/llama32vis
published
a model
about 19 hours ago
panopstor/llama32vis
replied to
appliedml42's
post
3 months ago
I am trying to find resources that explain how I can protect against instruction following capability degradation due to LoRA fine-tuning.
For example, I fine-tuned Llama 3.2 3B Instruct on https://huggingface.co/datasets/cornell-movie-review-data/rotten_tomatoes dataset and saw significant degradation in ifeval benchmark scores.
I would appreciate any pointers 🙏🏽
Organizations
models
10
panopstor/EveryDream
Text-to-Image
•
Updated
•
318
•
10
panopstor/condition_embedding_perturbation
Updated
•
2
panopstor/huber-exp
Updated
panopstor/SD15-768
Text-to-Image
•
Updated
•
18
•
1
panopstor/temp
Updated
panopstor/testmodel123
Updated
panopstor/attn_mask_tests
Updated
panopstor/ff7r-stable-diffusion
Updated
•
27
panopstor/finetunedump
Updated