]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
Stop the generation when <|eom_id|> token is encountered - needed for Llama 3.1 tool...
authorfairydreaming <redacted>
Mon, 5 Aug 2024 07:38:01 +0000 (09:38 +0200)
committerGitHub <redacted>
Mon, 5 Aug 2024 07:38:01 +0000 (09:38 +0200)
commitd3f0c7166adfa952237e0f437a5344362d8256d4
treea0e1bbdc48179c861a52de1fc1f80bc6dda79bf2
parente31a4f679779220312c165b0f5994c680a610e38
Stop the generation when <|eom_id|> token is encountered - needed for Llama 3.1 tool call support (#8858)

* gguf-py, llama : add constants and methods related to Llama-3.1 <|eom_id|> token

* llama : find Llama-3.1 <|eom_id|> token id during vocab loading

* llama-vocab : add Llama-3.1 <|eom_id|> token to the set of tokens stopping the generation

---------

Co-authored-by: Stanisław Szymczyk <redacted>
gguf-py/gguf/constants.py
gguf-py/gguf/gguf_writer.py
src/llama-vocab.cpp
src/llama-vocab.h
src/llama.cpp