vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

python linter

Browse source
This commit is contained in:
Pierrick HYMBERT 2024-12-28 15:49:47 +01:00 • committed by Georgi Gerganov
parent 4be934c453
commit 7385f7d7e2
No known key found for this signature in database
GPG key ID: 449E073F9DC10735
1 changed files with 1 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

1
convert_hf_to_gguf.py
View file

@ -2561,6 +2561,7 @@ class Phi3MiniModel(Model):
yield (self.format_tensor_name(gguf.MODEL_TENSOR.ROPE_FACTORS_LONG), torch.tensor(long_factors, dtype=torch.float32)) yield (self.format_tensor_name(gguf.MODEL_TENSOR.ROPE_FACTORS_LONG), torch.tensor(long_factors, dtype=torch.float32))
yield (self.format_tensor_name(gguf.MODEL_TENSOR.ROPE_FACTORS_SHORT), torch.tensor(short_factors, dtype=torch.float32)) yield (self.format_tensor_name(gguf.MODEL_TENSOR.ROPE_FACTORS_SHORT), torch.tensor(short_factors, dtype=torch.float32))
@Model.register("PhiMoEForCausalLM") @Model.register("PhiMoEForCausalLM")
class PhiMoeModel(Phi3MiniModel): class PhiMoeModel(Phi3MiniModel):
model_arch = gguf.MODEL_ARCH.PHIMOE model_arch = gguf.MODEL_ARCH.PHIMOE