tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-27 03:55:20 +00:00
Code Issues Packages Projects Releases Wiki Activity

convert : qwen2/3moe : set yarn metadata if present (#13331)

Browse Source 
* set yarn metadata if present

* add comment about enabling YaRN

Co-authored-by: Xuan-Son Nguyen <son@huggingface.co>

---------

Co-authored-by: Xuan-Son Nguyen <son@huggingface.co>
This commit is contained in:
Sigbjørn Skjæret
2025-05-06 11:12:06 +02:00
committed by GitHub
parent 15a28ec8c7
commit 764b85627b
1 changed files with 7 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
convert_hf_to_gguf.py
View File

@ -2761,6 +2761,13 @@ class Qwen2MoeModel(TextModel):
if (shared_expert_intermediate_size := self.hparams.get('shared_expert_intermediate_size')) is not None:
self.gguf_writer.add_expert_shared_feed_forward_length(shared_expert_intermediate_size)
logger.info(f"gguf: expert shared feed forward length = {shared_expert_intermediate_size}")
# YaRN is not enabled by default
# To enable it, please refer to this guide: https://huggingface.co/Qwen/Qwen3-30B-A3B#processing-long-texts
if self.hparams.get("rope_scaling") is not None and "factor" in self.hparams["rope_scaling"]:
if self.hparams["rope_scaling"].get("type") == "yarn":
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"])
_experts: list[dict[str, Tensor]] | None = None