]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
llama: Add support for Gemma2ForCausalLM (#8156)
authorpculliton <redacted>
Fri, 28 Jun 2024 04:00:43 +0000 (00:00 -0400)
committerGitHub <redacted>
Fri, 28 Jun 2024 04:00:43 +0000 (21:00 -0700)
commite57dc62057d41211ac018056c19c02cd544694df
treec3f9260b9d0ed53e04c81bcb153a839616b9787f
parenta27aa50ab7e07fe46aae619076b6e31d5663e914
llama: Add support for Gemma2ForCausalLM (#8156)

* Inference support for Gemma 2 model family

* Update convert-hf-to-gguf.py, constants, and tensor mappings

* cleanup

* format fix

* Fix special token vocab bug

* Don't add space prefix

* fix deleted lines

* Update src/llama.cpp

Co-authored-by: slaren <redacted>
* Add model type names

* Add control vector

* Fix model type identification

---------

Co-authored-by: Andrei Betlen <redacted>
Co-authored-by: slaren <redacted>
convert-hf-to-gguf.py
gguf-py/gguf/constants.py
gguf-py/gguf/tensor_mapping.py
src/llama.cpp