CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-07 09:57:00 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add LLaDA-7b-MoE diffusion model (#16003)

Browse Source
This commit is contained in:
Aman Gupta
2025-09-16 10:38:28 +08:00
committed by GitHub
parent 3d4053f77f
commit 6d758839ff
9 changed files with 315 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
src/llama-vocab.cpp
View File

@@ -1962,7 +1962,8 @@ void llama_vocab::impl::load(llama_model_loader & ml, const LLM_KV & kv) {
pre_type = LLAMA_VOCAB_PRE_TYPE_TRILLION;
clean_spaces = false;
} else if (
tokenizer_pre == "bailingmoe") {
tokenizer_pre == "bailingmoe" ||
tokenizer_pre == "llada-moe") {
pre_type = LLAMA_VOCAB_PRE_TYPE_BAILINGMOE;
clean_spaces = false;
} else if (