diff options
| author | postmasters <namnguyen@google.com> | 2024-02-21 05:08:22 -0800 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2024-02-21 15:08:22 +0200 |
| commit | 580111d42b3b6ad0a390bfb267d6e3077506eb31 (patch) | |
| tree | 9eed0a46aacfa10e586ea478c191106f11e59feb /examples/server | |
| parent | 88c46cbdac05cebd936511b1d3c74112e721615f (diff) | |
llama : add `gemma` model (#5631)
There are couple things in this architecture:
1. Shared input and output embedding parameters.
2. Key length and value length are not derived from `n_embd`.
More information about the models can be found at
https://ai.google.dev/gemma. GGUFs can be downloaded from
https://huggingface.co/google.
Diffstat (limited to 'examples/server')
0 files changed, 0 insertions, 0 deletions