Trelis
/

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

Text Generation

text-generation-inference

Model card Files Files and versions

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.

Downloads last month: 4

Safetensors

Model size

99.1M params

Tensor type

BF16

·

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

Base model

HuggingFaceTB/SmolLM-135M

Quantized

HuggingFaceTB/SmolLM-135M-Instruct

Finetuned

(178)

this model

Finetunes

Quantizations