abhishekgahlot commited on
Commit
2282a89
·
verified ·
1 Parent(s): d39b40d

cards: independent-project note (not affiliated with TypeSafe; Jev is their product)

Browse files
Files changed (1) hide show
  1. README.md +2 -0
README.md CHANGED
@@ -13,6 +13,8 @@ tags:
13
 
14
  The FP8 file of [OpenJev](https://huggingface.co/openjev/openjev): the same weights stored as FP8 (e4m3, 128×128 weight blocks, dynamic activations), about 29 GB instead of 54 GB. Everything about the model, the API and the results is in the main card; this page only says how this file was checked and how to run it.
15
 
 
 
16
  ## Measured, not assumed
17
 
18
  A one-pass readout lives on small score differences, so the file was re-run on the same frozen tests as the 16-bit model, with the same helper and the same fixed calibration:
 
13
 
14
  The FP8 file of [OpenJev](https://huggingface.co/openjev/openjev): the same weights stored as FP8 (e4m3, 128×128 weight blocks, dynamic activations), about 29 GB instead of 54 GB. Everything about the model, the API and the results is in the main card; this page only says how this file was checked and how to run it.
15
 
16
+ *OpenJev is an independent project, not affiliated with TypeSafe; Jev is their product.*
17
+
18
  ## Measured, not assumed
19
 
20
  A one-pass readout lives on small score differences, so the file was re-run on the same frozen tests as the 16-bit model, with the same helper and the same fixed calibration: