bamba¶
Model type |
|
Class |
|
Task |
|
Source |
|
Description¶
Bamba hybrid Mamba2+Attention causal language model.
Uses HybridCausalLMTask with mixed "mamba2" and
"full_attention" layer types for the cache.
HuggingFace reference: BambaForCausalLM.
Usage¶
mobius build --model <MODEL_ID> output_dir/
from mobius import build
model = build("<MODEL_ID>")