New Uploads to add llama.cpp fixes

#6
by danielhanchen - opened

New uploads that add 2 new fixes. You will need to redownload.

  1. vocab: fix Gemma4 tokenizer (#21343) - https://github.com/ggml-org/llama.cpp/pull/21343
  2. fix: gemma 4 template (#21326) - https://github.com/ggml-org/llama.cpp/pull/21326

https://github.com/ggml-org/llama.cpp/pull/21418

Specialized parser also merged.

Sign up or log in to comment