Superminaren/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-09-27 21:46:57 +02:00
Code Issues Packages Projects Releases Wiki Activity

convert: add MiMo-V2.6 support (#29257)

Browse Source 
* convert: add MiMo-V2.6 support
Hoist the K3 mxfp4 conversion repack into base.py so it can be reused
Remove decoder from mmproj convert
* Update conversion/mimo.py
* fix: use autoparser
---------

Co-authored-by: Sigbjørn Skjæret <[email protected]>
Co-authored-by: Piotr Wilkin <[email protected]>
This commit is contained in:
AesSedai
2026-09-22 14:38:09 +02:00
committed by GitHub
co-authored by Sigbjørn Skjæret Piotr Wilkin
parent a60f9aead0
commit bfd73a876e
4 changed files with 121 additions and 36 deletions
Download Patch File Download Diff File Expand all files Collapse all files
common/chat.cpp
+3 -1
View File
@@ -1212,7 +1212,9 @@ std::optional<common_chat_params> common_chat_try_specialized_template(
// Qwen3-Coder XML tool calls, also used by Nemotron Nano 3, Qwen3.5 and StepFun-3.5-Flash
if (src.find("<tool_call>") != std::string::npos &&
src.find("<function=") != std::string::npos &&
src.find("<parameter=") != std::string::npos) {
src.find("<parameter=") != std::string::npos &&
// Exclude models that don't use \n between tags
src.find("'<tool_call><function=' ~ tool_call.name ~ '>'") == std::string::npos) {
LOG_DBG("Using specialized template: Qwen3-Coder\n");
return common_chat_params_init_qwen3_coder(tmpl, params);
}