jayzou3773/less-is-moe-s1-calibration-128-seq8192 download history
jayzou3773/less-is-moe-s1-calibration-128-seq8192 is a text generation dataset on the Hugging Face Hub. In the last 30 days it was downloaded 35 times (9 in the last 7 days), and 193 times in total. It ranks #348,137 among datasets by monthly downloads.
Less-is-MoE S1K calibration data — 128 samples, seq_length 8192 This is the fixed calibration artifact used to prune GPT-OSS-120B, Qwen3.5-122B-A10B, and the Gemma-4-26B-A4B causal language tower. It uses the same 128 source rows as the full-length variant: yentinglin/s1K-1.1-trl-form
Models trained on less-is-moe-s1-calibration-128-seq8192
9 models list it as training data.
- jayzou3773/less-is-moe-gemma-4-26b-a4b-s1-128-seq8192-intdim-e-50 78 downloads in 30 days
- jayzou3773/less-is-moe-gpt-oss-120b-s1-128-seq8192-intdim-e-50 69 downloads in 30 days
- jayzou3773/less-is-moe-gemma-4-26b-a4b-s1-128-seq8192-intdim-g-50 54 downloads in 30 days
- jayzou3773/less-is-moe-gemma-4-26b-a4b-s1-128-seq8192-intdim-l-50 46 downloads in 30 days
- jayzou3773/less-is-moe-gpt-oss-120b-s1-128-seq8192-intdim-l-50 42 downloads in 30 days
- jayzou3773/less-is-moe-gpt-oss-120b-s1-128-seq8192-intdim-g-50 40 downloads in 30 days
- jayzou3773/less-is-moe-qwen3.5-122b-a10b-s1-128-seq8192-intdim-g-50 30 downloads in 30 days
- jayzou3773/less-is-moe-qwen3.5-122b-a10b-s1-128-seq8192-intdim-e-50 23 downloads in 30 days
- jayzou3773/less-is-moe-qwen3.5-122b-a10b-s1-128-seq8192-intdim-l-50 21 downloads in 30 days
Open jayzou3773/less-is-moe-s1-calibration-128-seq8192 on Hugging Face
Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.