upstream-archive/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-07-23 11:10:55 -05:00
Code Issues Packages Projects Releases Wiki Activity

convert : support Step3.7-Flash (#23845)

Browse Source 
* feat: support step3.7

* fix: register Step-3.7 BPE pre-tokenizer hash

* delete fromjson

* register step3.7 arch to Step35Model

* drop vit projector in base filter

* Apply suggestion from @CISC

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* restore blank line

---------

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
This commit is contained in:
forforever73
2026-06-02 15:54:49 +08:00
committed by GitHub
parent 4f3a4beb8d
commit f7a0777a5c
3 changed files with 25 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
conversion/base.py
View File

@@ -2593,7 +2593,7 @@ def get_model_architecture(hparams: dict[str, Any], model_type: ModelType) -> st
# Step3-VL keeps text config under text_config but uses a custom top-level architecture.
# For text conversion we route to a dedicated text-only class.
# TODO: refactor this later to avoid adding exception here
if model_type == ModelType.TEXT and arch in ("StepVLForConditionalGeneration", "Sarashina2VisionForCausalLM", "Exaone4_5_ForConditionalGeneration"):
if model_type == ModelType.TEXT and arch in ("StepVLForConditionalGeneration", "Sarashina2VisionForCausalLM", "Exaone4_5_ForConditionalGeneration", "Step3p7ForConditionalGeneration"):
return arch
# if "architectures" is found in the sub-config, use that instead