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

delete comments

Browse source
This commit is contained in:
Valentin Mamedov 2024-12-14 20:20:45 +07:00
parent ca168fc7a4
commit f3d0a23fe5
1 changed files with 1 additions and 6 deletions
Download patch file Download diff file Expand all files Collapse all files

7
convert_hf_to_gguf.py
View file

@ -3503,13 +3503,8 @@ class DeepseekModel(Model):
rope_dim = hparams["head_dim"]
else:
rope_dim = hparams["hidden_size"] // hparams["num_attention_heads"]
self.gguf_writer.add_rope_dimension_count(rope_dim)
# if self.hparams.get("rope_scaling") is not None and "factor" in self.hparams["rope_scaling"]:
# if self.hparams["rope_scaling"].get("type") == "linear":
# self.gguf_writer.add_rope_scaling_type(gguf.RopeScalingType.LINEAR)
# self.gguf_writer.add_rope_scaling_factor(self.hparams["rope_scaling"]["factor"])
self.gguf_writer.add_rope_scaling_type(gguf.RopeScalingType.NONE)
self.gguf_writer.add_leading_dense_block_count(hparams["first_k_dense_replace"])
self.gguf_writer.add_vocab_size(hparams["vocab_size"])