nm-testing
/

TinyLlama-1.1B-Chat-v1.0-gsm8k-pruned.2of4-chnl_wts_per_tok_dyn_act_int8-BitM

8-bit precision

compressed-tensors

Model card Files Files and versions

No model card

Downloads last month: 7

Safetensors

Model size

737M params

Tensor type

I64

·

BF16

·

I8

·

U8

·

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support