model : support MTP in GLM-4.7-Flash (#24868)
This commit is contained in:
@@ -3221,6 +3221,13 @@ MODEL_TENSORS: dict[MODEL_ARCH, list[MODEL_TENSOR]] = {
|
||||
MODEL_TENSOR.FFN_DOWN_SHEXP,
|
||||
MODEL_TENSOR.FFN_UP_SHEXP,
|
||||
MODEL_TENSOR.FFN_EXP_PROBS_B,
|
||||
# NextN/MTP tensors
|
||||
MODEL_TENSOR.NEXTN_EH_PROJ,
|
||||
MODEL_TENSOR.NEXTN_EMBED_TOKENS,
|
||||
MODEL_TENSOR.NEXTN_ENORM,
|
||||
MODEL_TENSOR.NEXTN_HNORM,
|
||||
MODEL_TENSOR.NEXTN_SHARED_HEAD_HEAD,
|
||||
MODEL_TENSOR.NEXTN_SHARED_HEAD_NORM,
|
||||
],
|
||||
MODEL_ARCH.DEEPSEEK2OCR: [
|
||||
MODEL_TENSOR.TOKEN_EMBD,
|
||||
|
||||
Reference in New Issue
Block a user