]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: ecebbd2)
llama-run : fix context size (#11094)
authorEric Curtin <redacted>
Mon, 6 Jan 2025 22:45:28 +0000 (22:45 +0000)
committerGitHub <redacted>
Mon, 6 Jan 2025 22:45:28 +0000 (23:45 +0100)
commitdc7cef9f373f2a24b851f0df7a618c5209e593fa
tree315cfdf765ba1843de01947d5e9cd0f8cb1d6b8btree
parentecebbd292d741ac084cf248146b2cfb17002aa1dcommit | diff
llama-run : fix context size (#11094)

Set `n_ctx` equal to `n_batch` in `Opt` class. Now context size is
a more reasonable 2048.

Signed-off-by: Eric Curtin <redacted>
examples/run/run.cpp diff | blob | history
Packaging of ggml-org/llama.cpp