happyz
/
llama.cpp
mirror of https://github.com/ggerganov/llama.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

convert : register Qwen 3.5 ForCausalLM for text only (#20119)

This commit is contained in:
Sigbjørn Skjæret 2026-03-05 10:30:02 +01:00 committed by GitHub
parent 5e335ba113
commit cf232515c9
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
convert_hf_to_gguf.py
View File

@ -4842,12 +4842,12 @@ class _LinearAttentionVReorderBase(Qwen3NextModel):
yield from super().modify_tensors(data_torch, name, bid)
@ModelBase.register("Qwen3_5ForConditionalGeneration")
@ModelBase.register("Qwen3_5ForConditionalGeneration", "Qwen3_5ForCausalLM")
class Qwen3_5TextModel(_LinearAttentionVReorderBase):
model_arch = gguf.MODEL_ARCH.QWEN35
@ModelBase.register("Qwen3_5MoeForConditionalGeneration")
@ModelBase.register("Qwen3_5MoeForConditionalGeneration", "Qwen3_5MoeForCausalLM")
class Qwen3_5MoeTextModel(_LinearAttentionVReorderBase):
model_arch = gguf.MODEL_ARCH.QWEN35MOE