Closed lchu-ibm closed 4 months ago
to match with https://github.com/foundation-model-stack/foundation-model-stack/blob/b06c5dfb6093f3a422f8a5d9bcff57ac81eedf5b/fms/models/llama.py#L342-L353
@daviswer based on the hf config, they are. they also share the same kvheads. the num paramter came out was also precisely 34b.
Llama2 34 and 70b are using gqa, which is different from llama1
to match with https://github.com/foundation-model-stack/foundation-model-stack/blob/b06c5dfb6093f3a422f8a5d9bcff57ac81eedf5b/fms/models/llama.py#L342-L353