LLM-Inference/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-08-12 22:31:11 +04:00
Code Issues Packages Projects Releases Wiki Activity

convert : accept "ExaoneMoeForCausalLM" arch spelling (#26660)

Browse Source
This commit is contained in:
Csaba Kecskemeti
2026-08-06 18:56:04 +08:00
committed by GitHub
parent a1f96d4fc2
commit e700bfb37f
2 changed files with 4 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
conversion/__init__.py
+1
View File
@@ -70,6 +70,7 @@ TEXT_MODEL_MAP: dict[str, str] = {
"Exaone4ForCausalLM": "exaone",
"ExaoneForCausalLM": "exaone",
"ExaoneMoEForCausalLM": "exaone",
"ExaoneMoeForCausalLM": "exaone",
"FalconForCausalLM": "falcon",
"FalconH1ForCausalLM": "falcon_h1",
"FalconMambaForCausalLM": "mamba",
conversion/exaone.py
+3 -1
View File
@@ -123,7 +123,9 @@ class Exaone4Model(TextModel):
yield (self.format_tensor_name(gguf.MODEL_TENSOR.ROPE_FREQS), torch.tensor(rope_factors, dtype=torch.float32))
@ModelBase.register("ExaoneMoEForCausalLM")
# note: transformers >= 5.1 renamed the class to "ExaoneMoeForCausalLM" (lowercase 'e'),
# so accept both spellings - LG AI have updated the configs of already-released models
@ModelBase.register("ExaoneMoEForCausalLM", "ExaoneMoeForCausalLM")
class ExaoneMoEModel(Exaone4Model):
model_arch = gguf.MODEL_ARCH.EXAONE_MOE