]>
git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
chat : Granite Docling stopping (#16438)
* fix: Fix duplicate fake image before token on first slice
Branch: GraniteDoclingStopping
Signed-off-by: Gabe Goodhart <redacted>
* fix: Use double-newline before overview image
Branch: GraniteDoclingStopping
Signed-off-by: Gabe Goodhart <redacted>
* fix: Remove incorrect newline at the end of granite chat template gen prompt
There should not be one, even for the language models.
Branch: GraniteDoclingStopping
Signed-off-by: Gabe Goodhart <redacted>
* tests: Remove bad newline from granite chat template test (legacy)
Branch: GraniteDoclingStopping
Signed-off-by: Gabe Goodhart <redacted>
---------
Signed-off-by: Gabe Goodhart <redacted>
overview / pkg / ggml / sources / llama.cpp / commit