Public/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-09-20 01:31:31 +02:00
Code Issues Packages Projects Releases Wiki Activity

convert: add @ModelBase.example

Browse Source
This commit is contained in:
Xuan Son Nguyen
2026-08-17 02:31:10 +02:00
parent 4df29be4f4
commit 71c7866a16
84 changed files with 231 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
conversion/bailingmoe.py
+3
View File
@@ -11,6 +11,7 @@ from .base import ModelBase, TextModel, gguf
@ModelBase.register("BailingMoeForCausalLM")
@ModelBase.example("inclusionAI/Ling-lite")
class BailingMoeModel(TextModel):
model_arch = gguf.MODEL_ARCH.BAILINGMOE
@@ -108,6 +109,7 @@ class BailingMoeModel(TextModel):
@ModelBase.register("BailingMoeV2ForCausalLM")
@ModelBase.example("inclusionAI/Ling-mini-2.0")
class BailingMoeV2Model(TextModel):
model_arch = gguf.MODEL_ARCH.BAILINGMOE2
@@ -189,6 +191,7 @@ class BailingMoeV2Model(TextModel):
@ModelBase.register("SarvamMoEForCausalLM", "modeling_sarvam_moe.SarvamMoEForCausalLM")
@ModelBase.example("sarvamai/sarvam-30b")
class SarvamMoEModel(BailingMoeV2Model):
model_arch = gguf.MODEL_ARCH.BAILINGMOE2
# Sarvam-MoE shares the BailingMoeV2 architecture; only differences: