llama.cpp
Use model->gguf_kv for loading the template instead of using the C API.
#10868
Merged
Merged
Use model->gguf_kv for loading the template instead of using the C API. #10868
slaren
merged
2 commits into
ggml-org:master
from
dranger003:master
Bump model_template to 16384 bytes to support larger chat templates.
919fe432
Use `model->gguf_kv` for efficiency.
52bfa235
dranger003
changed the title
slaren
approved these changes
on 2024-12-17
Login to write a write a comment.
Login via GitHub