chargoddard
/

SmolLlamix-8x101M-take2

Text Generation

Inference Endpoints

text-generation-inference

Model card Files Files and versions Community

Edit model card

This is another training run of SmolLlamix-8x101M with slightly different hyperparameters. Just testing to see how it holds up against the first run.

Downloads last month: 3,160

Safetensors

Model size

399M params

Tensor type

BF16

·

Dataset used to train chargoddard/SmolLlamix-8x101M-take2