diff options
author | Georgi Gerganov <ggerganov@gmail.com> | 2023-07-23 15:09:47 +0300 |
---|---|---|
committer | GitHub <noreply@github.com> | 2023-07-23 15:09:47 +0300 |
commit | e76d630df17e235e6b9ef416c45996765d2e36fb (patch) | |
tree | 15e0e9648f9b0e398b43e888216a73f84098ff3a /examples/main/main.cpp | |
parent | 1d0824b2476e7fda09751a0235c9e571b76d6f2c (diff) |
llama : grouped-query attention + LLaMAv2 70B support (#2276)
* CUDA: GQA implementation
* llama : support for GQA and LLaMAv2 70B
ggml-ci
* py : fix hparams parsing (if-else blocks)
ggml-ci
* py : oh boy ..
ggml-ci
* help : fix gqa value for 70B
ggml-ci
---------
Co-authored-by: JohannesGaessler <johannesg@5d6.de>
Diffstat (limited to 'examples/main/main.cpp')
-rw-r--r-- | examples/main/main.cpp | 4 |
1 files changed, 2 insertions, 2 deletions
diff --git a/examples/main/main.cpp b/examples/main/main.cpp index 4b4cd1d..3bd8ba2 100644 --- a/examples/main/main.cpp +++ b/examples/main/main.cpp @@ -93,8 +93,8 @@ int main(int argc, char ** argv) { } if (params.n_ctx > 2048) { - fprintf(stderr, "%s: warning: base model only supports context sizes no greater than 2048 tokens (%d specified);" - " you are on your own\n", __func__, params.n_ctx); + // TODO: determine the actual max context of the model (e.g. 4096 for LLaMA v2) and use that instead of 2048 + fprintf(stderr, "%s: warning: base model only supports context sizes no greater than 2048 tokens (%d specified)\n", __func__, params.n_ctx); } else if (params.n_ctx < 8) { fprintf(stderr, "%s: warning: minimum context size is 8, using minimum size.\n", __func__); params.n_ctx = 8; |