vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

convert : update for baichuan (#2081)

Browse source 
1. guess n_layers;
2. relax warnings on context size;
3. add a note that its derivations are also supported.

Co-authored-by: Judd <foldl@boxvest.com>
This commit is contained in:
Judd 2023-07-07 00:23:49 +08:00 • committed by GitHub
parent a17a2683d8
commit 36680f6e40
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
6 changed files with 11 additions and 5 deletions
Download patch file Download diff file Expand all files Collapse all files

2
examples/perplexity/perplexity.cpp
View file

@ -130,7 +130,7 @@ int main(int argc, char ** argv) {
params.n_batch = std::min(params.n_batch, params.n_ctx);
if (params.n_ctx > 2048) {
fprintf(stderr, "%s: warning: model does not support context sizes greater than 2048 tokens (%d specified);"
fprintf(stderr, "%s: warning: model might not support context sizes greater than 2048 tokens (%d specified);"
"expect poor results\n", __func__, params.n_ctx);
}