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

convert-hf : fix flake8 Lint errors

Browse source
This commit is contained in:
Stanisław Szymczyk 2024-05-27 18:25:47 +02:00
parent d02130d549
commit bde971a9ca
1 changed files with 1 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

5
convert-hf-to-gguf.py
View file

@ -2646,14 +2646,11 @@ class DeepseekV2Model(Model):
self.gguf_writer.add_rope_scaling_type(gguf.RopeScalingType.YARN)
self.gguf_writer.add_rope_scaling_factor(self.hparams["rope_scaling"]["factor"])
self.gguf_writer.add_rope_scaling_orig_ctx_len(self.hparams["rope_scaling"]["original_max_position_embeddings"])
self.gguf_writer.add_rope_scaling_yarn_log_mul(0.1*hparams["rope_scaling"]["mscale_all_dim"])
self.gguf_writer.add_rope_scaling_yarn_log_mul(0.1 * hparams["rope_scaling"]["mscale_all_dim"])
_experts: list[dict[str, Tensor]] | None = None
def modify_tensors(self, data_torch: Tensor, name: str, bid: int | None) -> Iterable[tuple[str, Tensor]]:
n_head = self.hparams["num_attention_heads"]
n_kv_head = self.hparams.get("num_key_value_heads")
# process the experts separately
if name.find("mlp.experts") != -1:
n_experts = self.hparams["n_routed_experts"]