diff options
| author | saood06 <saood05@gmail.com> | 2025-05-09 02:09:59 -0500 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2025-05-09 10:09:59 +0300 |
| commit | bc6ae515ceb14eeaf198e00251a9689539cea176 (patch) | |
| tree | 82ca4aa8afa0dce38e0f3cb6fa9c7a78ec0065d2 /include/llama.h | |
| parent | 4084ca7331611da4426d781a15a6ffa68312759e (diff) | |
Support for Llama-3-Nemotron models (#377)
* conflict resolution
* Changes to make work and add longrope support
* Changes to n_attention_wv rule
* Untested support of 253B
* DeciLMCausalModel now reads rope_theta from config.json properly
* Remove errant Granite mentions
* Better n_attention_vw rule
* Update vocab.py
---------
Co-authored-by: Yee Man Chan <ymchan@gmail.com>
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Diffstat (limited to 'include/llama.h')
| -rw-r--r-- | include/llama.h | 3 |
1 files changed, 2 insertions, 1 deletions
diff --git a/include/llama.h b/include/llama.h index d7376d7d..e2901861 100644 --- a/include/llama.h +++ b/include/llama.h @@ -230,7 +230,8 @@ extern "C" { LLAMA_ROPE_SCALING_TYPE_NONE = 0, LLAMA_ROPE_SCALING_TYPE_LINEAR = 1, LLAMA_ROPE_SCALING_TYPE_YARN = 2, - LLAMA_ROPE_SCALING_TYPE_MAX_VALUE = LLAMA_ROPE_SCALING_TYPE_YARN, + LLAMA_ROPE_SCALING_TYPE_LONGROPE = 3, + LLAMA_ROPE_SCALING_TYPE_MAX_VALUE = LLAMA_ROPE_SCALING_TYPE_LONGROPE, }; enum llama_pooling_type { |