Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+gpt-oss-20B-base-MXFP4.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,15 @@
+---
+language:
+- en
+license: mit
+datasets:
+- HuggingFaceFW/fineweb
+base_model: jxm/gpt-oss-20b-base
+library_name: transformers
+tags:
+- llama-cpp
+---
+
+Quantized to MXFP4 using llama.cpp b6150
+
+I also gguf-my-repo'd a q6_K on my personal account but it's actually not any better and it's too big. looks like llama.cpp quantization is bad quality for these models except for mxfp4

gpt-oss-20B-base-MXFP4.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56c638e1fb07d07e4e498993b700e4cbf23aae1de3af6df33ac55596d7ce14a8
+size 12109567040