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

llama : minor sampling refactor (2) (#9386)

Browse source
This commit is contained in:
slaren 2024-09-09 17:10:46 +02:00 • committed by GitHub
parent 38ca6f644b
commit 5fb5e24811
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
12 changed files with 115 additions and 113 deletions
Download patch file Download diff file Expand all files Collapse all files

1
examples/gritlm/gritlm.cpp
View file

@ -121,7 +121,6 @@ static std::string generate(llama_context * ctx, llama_sampler * smpl, const std
llama_decode(ctx, bat);
llama_token token = llama_sampler_sample(smpl, ctx, bat.n_tokens - 1);
llama_sampler_accept(smpl, token);
if (token == eos_token) {
break;