model: add Mellum architecture (#23966)
* model: support for Mellum architecture * model: improve mellum.py formatting * model: improve mellum.py formatting once again * deps: downgrade transformers to 4.57.6 (to fix CI) * deps: remove huggingface_hub dependency * deps: remove huggingface_hub from test requirements --------- Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
This commit is contained in:
co-authored by
Sigbjørn Skjæret
parent
bfb4308b05
commit
4fb16eccce
@@ -135,6 +135,7 @@ TEXT_MODEL_MAP: dict[str, str] = {
|
||||
"Mamba2ForCausalLM": "mamba",
|
||||
"MambaForCausalLM": "mamba",
|
||||
"MambaLMHeadModel": "mamba",
|
||||
"MellumForCausalLM": "mellum",
|
||||
"MiMoV2FlashForCausalLM": "mimo",
|
||||
"MiMoV2ForCausalLM": "mimo",
|
||||
"MiniCPM3ForCausalLM": "minicpm",
|
||||
|
||||
Reference in New Issue
Block a user