HuggingFaceTB
/

SmolLM-360M-Instruct-ONNX-fp16

Model card Files Files and versions Community

SmolLM-360M-Instruct-ONNX-fp16 / onnx

1 contributor

History: 1 commit

Xenova's picture

Xenova HF staff

Optimized fp16/q4f16 ONNX export (MHA) (#1)

89d56ab verified 3 months ago

model_fp16.onnx

819 MB
LFS

Optimized fp16/q4f16 ONNX export (MHA) (#1) 3 months ago
model_q4f16.onnx

299 MB
LFS

Optimized fp16/q4f16 ONNX export (MHA) (#1) 3 months ago