Why use an old model like Qwen3-8B?
#3
by weightsnweights - opened
Why use an old model like Qwen3-8B? Why not any of the multitude of newer models with vastly superior performance?
"Qwen3-8B encoder", not "Qwen3-8B"
Why use an old model like Qwen3-8B? Why not any of the multitude of newer models with vastly superior performance?
"Qwen3-8B encoder", not "Qwen3-8B"