diff options
| author | Laurent Mazare <laurent.mazare@gmail.com> | 2024-09-30 19:31:14 +0200 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2024-09-30 19:31:14 +0200 |
| commit | 683ab698def755c24cec9987069d25efcf831fc4 (patch) | |
| tree | 84d0bd8ad2f5d7a00f67050c83520326d947b2fe /candle-transformers/src/models/llava/mod.rs | |
| parent | 2f49e1b5349f4e56677ec0d3dc3fe98f9cbb87c7 (diff) | |
| download | candle-683ab698def755c24cec9987069d25efcf831fc4.tar.gz candle-683ab698def755c24cec9987069d25efcf831fc4.tar.bz2 candle-683ab698def755c24cec9987069d25efcf831fc4.zip | |
Add Pixtral. (#2521)
* Add Pixtral.
* More pixtral vision encoder.
* Sketch a pixtral example.
* Sketch a pixtral example.
* Better image loading.
* Support loading images embedded in safetensor files.
* Clippy fixes.
* Add the llava multimodal adapter.
* Add more of the llava bits.
* Add the pixtral config.
* More pixtral inference.
* Add the text generation bits.
* Get the example to work.
* Bugfix.
* Run some bits of the model in f32.
* Blessed version :)
* Better rope frequency computations.
* README update.
Diffstat (limited to 'candle-transformers/src/models/llava/mod.rs')
| -rw-r--r-- | candle-transformers/src/models/llava/mod.rs | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/candle-transformers/src/models/llava/mod.rs b/candle-transformers/src/models/llava/mod.rs index caa8737a..1ed3b50c 100644 --- a/candle-transformers/src/models/llava/mod.rs +++ b/candle-transformers/src/models/llava/mod.rs @@ -279,7 +279,7 @@ impl LLaVA { (), ))? } else { - todo!("not implemented in original python LLaVA yet") + bail!("not implemented in original python LLaVA yet") }; let new_image_feature = if mm_patch_merge_type.contains("unpad") { let new_image_feature = new_image_feature |