jdelony/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-06-27 23:50:20 -05:00
Code Issues Packages Projects Releases Wiki Activity

add unified assistant

Browse Source
This commit is contained in:
Aman Gupta 2026-06-05 14:59:44 +08:00
parent dd97604fc4
commit 4eaa3cee66
2 changed files with 2 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
conversion/__init__.py
View File

@ -79,6 +79,7 @@ TEXT_MODEL_MAP: dict[str, str] = {
"Gemma4ForConditionalGeneration": "gemma",
"Gemma4ForCausalLM": "gemma",
"Gemma4UnifiedForConditionalGeneration": "gemma",
"Gemma4UnifiedAssistantForCausalLM": "gemma",
"GemmaForCausalLM": "gemma",
"Glm4ForCausalLM": "glm",
"Glm4MoeForCausalLM": "glm",

2
conversion/gemma.py
View File

@ -785,7 +785,7 @@ class Gemma4UnifiedModel(Gemma4Model):
self.gguf_writer.add_suppress_tokens(suppress_tokens)
@ModelBase.register("Gemma4AssistantForCausalLM")
@ModelBase.register("Gemma4AssistantForCausalLM", "Gemma4UnifiedAssistantForCausalLM")
class Gemma4AssistantModel(Gemma4Model):
model_arch = gguf.MODEL_ARCH.GEMMA4_ASSISTANT