SmolLM-135M-Instruct-layer-pruned-90M-raw

A Layer-Pruned version of SmolLM-Instruct-135M

Layers are removed from the top of the model (except for the last layer) in order to reduce the parameter count to approximately 99M.

Safetensors

Model size

99.1M params

Tensor type

BF16

Inference Providers NEW

This model is not currently available via any of the supported Inference Providers.

Model tree for Trelis/SmolLM-135M-Instruct-layer-pruned-90M-raw

Base model

Quantized

Finetuned

(75)

this model

Finetunes

Quantizations