Paused
Agents
SLM-125M — SFT Scaling Study (2k vs 10k)
⚖
Ask two fine-tunes of a 125M model — did 5x more data help?
Harman Singh Sandhu
Ace-2504
·
AI & ML interests
None yet
Recent Activity
updated a model 6 days ago
Ace-2504/gemma-2-2b-sft-rlaif published a model 6 days ago
Ace-2504/gemma-2-2b-sft-rlaif updated a model 6 days ago
Ace-2504/gemma-2-2b-sft-dpoOrganizations
models 17
Ace-2504/gemma-2-2b-sft-rlaif
Text Generation • Updated • 20
Ace-2504/gemma-2-2b-sft-dpo
Text Generation • Updated • 15
Ace-2504/gemma-2-2b-raft
Text Generation • Updated • 12
Ace-2504/gemma-2-2b-sft
Text Generation • Updated • 14
Ace-2504/slm-500m-sft-rlaif
Text Generation • 0.5B • Updated • 19
Ace-2504/slm-500m-sft-dpo
Text Generation • 0.5B • Updated • 27
Ace-2504/slm-500m-raft
Text Generation • 0.5B • Updated • 23
Ace-2504/slm-500m-sft
Text Generation • 0.5B • Updated • 30
Ace-2504/slm-125m-sft-rlaif
Text Generation • 0.1B • Updated • 27
Ace-2504/slm-125m-sft-dpo
Text Generation • 0.1B • Updated • 27
datasets 0
None public yet