* moondream implementation
* add moondream example
* change config default activation
* Add assets and integrate phi mixformer with example
* Make use of kv cache and fix seq_len bug; Clean up example code
* Add README link to example
* Remove pos_embed scaling; Remove assets; Add to README; Expand VisionConfig
* Delete image
* Use apply instead of forward
* Add the Gemma models.
* Add the gemma example.
* Adapt the RmsNorm.
* Get the 2b model to work.
* 7b support.
* Use the config head dim.
* Yet another fix.
* Make the matrixes contiguous.
* Also get the 7b model to work.
* And add to the readme.
* Start adding the RWKV model.
* More of the forward step.
* Handle rescaling.
* FeedForward.
* More work on RWKV.
* Better state tracking.
* Finish a first pass on forward.
* Fix the shape mismatches.
* Do not rescale in f32.
* Rename to rwkv-v5.
* Add the new models to the readme.
* Sketch the mamba model for inference.
* Complete the forward pass.
* Add the mamba example.
* Optimize the selective-scan part.
* Fix a couple shape mismatches and get inference to work.
* Tweak the readmes.
* More readme tweaks.
* Add support for SD Turbo
* Set Leading as default in euler_ancestral discrete
* Use the appropriate default values for n_steps and guidance_scale.
---------
Co-authored-by: Laurent <laurent.mazare@gmail.com>
* Add support to UL2 model family
* Update docs with UL2
* Create ActivationWithOptionalGating to avoid polluting activations
* Also refactor quantized t5
* Remove useless conversion
* Revert Activation::NewGelu name change
* Remove useless return
* Apply rustfmt and clippy recommendations
* Reuse t5::ActivationWithOptionalGating in quantized version
* (cosmetic change) use a match rather than ifs + avoid early returns.
---------
Co-authored-by: Laurent <laurent.mazare@gmail.com>
I think it makes more sense to have it there, since it's a seq2seq model with cross attention, and not a LM. There are also Decoder only T5 models that work as LMs, but that's not the standard.
Vishal Patil