š§"raw" pretrained smol_llama checkpoints - WIP š§
-
BEE-spoke-data/smol_llama-101M-GQA
Text Generation ⢠Updated ⢠2.88k ⢠28 -
BEE-spoke-data/smol_llama-81M-tied
Text Generation ⢠Updated ⢠867 ⢠6 -
BEE-spoke-data/smol_llama-220M-GQA
Text Generation ⢠Updated ⢠2.83k ⢠12 -
BEE-spoke-data/verysmol_llama-v11-KIx2
Text Generation ⢠Updated ⢠858 ⢠4