[PixtralLarge] Update Pixtral conversion script to support large format! (#34801)

* update conversion script

* update for bias again

* remove pdv

* use my dir

* Update how we initialize the tokenizer

* Convert in bfloat16

* Undo that one again

* fix config dump

* .to() was broken for BatchMixFeature

* quick debug breakpoint

* put the breakpoint in the right place

* Add a config flag for the multimodal projector bias

* Add a config flag for the multimodal projector bias

* Conversion script can load chat templates

* Indent config for comparison

* Stop clobbering the config

* Re-enable the config clobber

* Get rid of the config manual save - it has no effect!

* Handle adapter bias correctly

* Default vision transformer activation to silu

* Remove legacy processing path

* One commit with all the debug breakpoints before I delete them all, in case I need to revert

* Update conversion

* Remove vLLM debugging instrumentation

* Drop xformers

* Remove debug enumerates

* make fixup

* make fixup

* Break copied from in pixtral

* Propagate multimodal_projector_bias change

* Propagate multimodal_projector_bias change

* Remove debug device .to()

* Restore attention weights output

* Fix Pixtral test

* Drop image_seq_length

* Drop image_seq_length

* Put the legacy processing code back

* Add the bias option to the llava_next_video config

* Add the bias option to the llava_next_video config

* Make certain args required in converter

* Make certain args required in converter

* typo

* make fixup

* Reverting some dtype changes since it seems to work without them

---------

Co-authored-by: arthur@huggingface.co <arthur@ip-26-0-166-244.ec2.internal>
Co-authored-by: Matt <rocketknight1@gmail.com>
Co-authored-by: Matt <Rocketknight1@users.noreply.github.com>

tests/models/pixtral/test_processor_pixtral.py

@@ -253,7 +253,7 @@ class PixtralProcessorTest(ProcessorTesterMixin, unittest.TestCase):
             "USER: [IMG]\nWhat's the content of the image? ASSISTANT:",
         ] * 5
         processor.tokenizer.pad_token = "</s>"
-        image_inputs = [self.image_0] * 5
+        image_inputs = [[self.image_0]] * 5
 
         # Make small for checking image token expansion
         processor.image_processor.size = {"longest_edge": 30}