HuggingFaceTB
/

SmolVLM-Instruct

Image-Text-to-Text

Inference Endpoints

Model card Files Files and versions Community

Xenova HF staff commited on about 1 month ago

Commit

792b809

•

1 Parent(s): 3f26bde

Upload q4f16 decoder ONNX weights w/ float32 inputs_embeds

Files changed (1) hide show

onnx/decoder_model_merged_q4f16.onnx +2 -2

onnx/decoder_model_merged_q4f16.onnx CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73e9722bd19fe5b4174d8b6eabe28d590d3a0cbd45cb0b4165e15b084aa0187c
-size 965031413

 version https://git-lfs.github.com/spec/v1
+oid sha256:2d74ec46083829ddb18f58fcceb358d2ba58d2a1320bdab431c32e4d2896981d
+size 965031477