shimmyshimmer commited on
Commit
4c29a2a
·
verified ·
1 Parent(s): 5e4ccdf

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -0
README.md CHANGED
@@ -39,6 +39,8 @@ tags:
39
  - View the rest of our notebooks in our [docs here](https://docs.unsloth.ai/get-started/unsloth-notebooks).
40
  - Thank you to the [llama.cpp](https://github.com/ggml-org/llama.cpp) team for their work on supporting this model. We wouldn't be able to release quants without them!
41
 
 
 
42
  # gpt-oss-20b Details
43
 
44
  <p align="center">
 
39
  - View the rest of our notebooks in our [docs here](https://docs.unsloth.ai/get-started/unsloth-notebooks).
40
  - Thank you to the [llama.cpp](https://github.com/ggml-org/llama.cpp) team for their work on supporting this model. We wouldn't be able to release quants without them!
41
 
42
+ The F32 quant is MXFP4 upcasted to BF16 for every single layer and is unquantized.
43
+
44
  # gpt-oss-20b Details
45
 
46
  <p align="center">