bn999
/

mistral-4.2B

Text Generation

Inference Endpoints

text-generation-inference

Model card Files Files and versions Community

Edit model card

Selectively pruned and re-trained Mistral-7B for reduced size, targeting only MPT layers.

Downloads last month: 2,083

Safetensors

Model size

4.42B params

Tensor type

BF16

·

Finetuned from