[Model] GLM adaptation (#34124)
This commit is contained in:
@@ -181,7 +181,7 @@ class SpeculativeConfig:
|
||||
@staticmethod
|
||||
def hf_config_override(hf_config: PretrainedConfig) -> PretrainedConfig:
|
||||
initial_architecture = hf_config.architectures[0]
|
||||
if hf_config.model_type in ("deepseek_v3", "deepseek_v32"):
|
||||
if hf_config.model_type in ("deepseek_v3", "deepseek_v32", "glm_moe_dsa"):
|
||||
hf_config.model_type = "deepseek_mtp"
|
||||
if hf_config.model_type == "deepseek_mtp":
|
||||
n_predict = getattr(hf_config, "num_nextn_predict_layers", None)
|
||||
|
||||
Reference in New Issue
Block a user