SF-Foundation PRO

SF-Foundation

·

AI & ML interests

None yet

Recent Activity

published a model about 23 hours ago

SF-Foundation/Gemma4-26B-sft-FP8-dynamic

upvoted a paper about 23 hours ago

Adaptive Layerwise Perturbation: Unifying Off-Policy Corrections for LLM RL

upvoted a paper about 23 hours ago

Co-Evolving Harnesses and Models: On-Policy Correction Helps Weaker Models Catch Up Where Imitation Fails

View all activity

Organizations

spaces 1

Trackio

models 21

SF-Foundation/Gemma4-26B-sft-FP8-dynamic

26B • Updated 1 day ago • 1

SF-Foundation/Gemma4-26B-FinetunedLoRA

Text Generation • Updated 24 days ago • 15

SF-Foundation/Gemma3-270M-reranker

0.3B • Updated 29 days ago • 19

SF-Foundation/Gemma4-31B-FinetunedLoRA-V3

SF-Foundation/sft_gemma31B_fullft_bf16_weighted_loss

1.0B • Updated Jul 27 • 4

SF-Foundation/Gemma4-31B-Finetuned-V2

33B • Updated Jul 8 • 7

SF-Foundation/Gemma-4-31B-Finetuned

33B • Updated Jul 7 • 83

SF-Foundation/HyperClassifier-gpt-oss-20b-qat-0226-experimental

21B • Updated Feb 25 • 7

SF-Foundation/TextBase-OSS-20B-0203

21B • Updated Feb 4 • 4

SF-Foundation/Mistral3_14B_Instruct_BF16_20260130

Image-Text-to-Text • 14B • Updated Jan 31 • 2

datasets 0

None public yet