π§"raw" pretrained smol_llama checkpoints - WIP π§
-
BEE-spoke-data/smol_llama-101M-GQA
Text Generation β’ Updated β’ 2.73k β’ 28 -
BEE-spoke-data/smol_llama-81M-tied
Text Generation β’ Updated β’ 1.21k β’ 6 -
BEE-spoke-data/smol_llama-220M-GQA
Text Generation β’ Updated β’ 2.59k β’ 12 -
BEE-spoke-data/verysmol_llama-v11-KIx2
Text Generation β’ Updated β’ 1.21k β’ 4