isuramanchi commited on
Commit
384f1fa
·
verified ·
1 Parent(s): 6cf421e

gemma-4-E2B-it-cuda-q8.base: Google's MTP head embedded (gemma4-mtp, head_version 1)

Browse files

The same bundle with the gemma-4 -assistant head embedded in its speculator section by basert add-speculator (BaseRT 0.4.3): every model tensor keeps its bytes, offsets and checksums; the head is f16. BaseRT 0.4.3 + superfluid 0.1.6 serve it with --speculate mtp-head / auto; 0.4.2 and 0.1.5 serve it as before, leaving the head alone.

Files changed (1) hide show
  1. gemma-4-E2B-it-cuda-q8.base +2 -2
gemma-4-E2B-it-cuda-q8.base CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:115c4ae330c2b4acd9dfc586a3ebe6a2080efb9de10f893f8d42eaf960a8e5d4
3
- size 5350326272
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62ed6171de32f6ab850c2e0d4d5b008e89acd85d546ba5d3dfead7e0e8ea3ac2
3
+ size 5505138688