A "work-in-progress" collection of experimental SFT runs. Primary focus: minimizing catastrophic forgetting, testing LoRA vs. Full-Parameter tuning.
Francesco Albanese
Francesco-A
·
AI & ML interests
None yet
Recent Activity
updated a bucket about 7 hours ago
Francesco-A/trackio-bucket published a bucket about 7 hours ago
Francesco-A/trackio-bucket upvoted an article about 2 months ago
Training and Finetuning Sparse Embedding Models with Sentence TransformersOrganizations
