codegen¶
Model type |
|
Class |
|
Task |
|
Source |
|
Description¶
CodeGen causal language model.
Identical architecture to GPT-J (single-norm parallel residual) but
uses a fused qkv_proj weight that is split during
preprocess_weights.
CodeGen is MHA only (no GQA), so num_key_value_heads is forced to
match num_attention_heads.
Replicates HuggingFace’s CodeGenForCausalLM.
Usage¶
mobius build --model <MODEL_ID> output_dir/
from mobius import build
model = build("<MODEL_ID>")