Something is wrong with the 4bit uploads, 57.9B params???
#2
by
fsaudm
- opened
then, when trying to load with both unsloth and transformers, Im getting:
Some weights of the model checkpoint at unsloth/Llama-4-Scout-17B-16E-Instruct-unsloth-dynamic-bnb-4bit were not used when initializing Llama4ForConditionalGeneration: ['language_model.model.layers.0.feed_forward.experts.down_proj.weight',
...
, 'language_model.model.layers.9.feed_forward.experts.gate_up_proj']
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
wait for our official announcement! Should be tomorrow - PR is in progress
@shimmyshimmer any updates?