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

server: fix incorrectly reported token probabilities (#7125)

Browse source 
* server: normalize token probabilities

* fix temperature == 0.0f
This commit is contained in:
Johannes Gäßler 2024-05-07 23:07:58 +02:00 • committed by GitHub
parent b6aa670203
commit af0a5b6163
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
4 changed files with 31 additions and 11 deletions
Download patch file Download diff file Expand all files Collapse all files

5
common/sampling.cpp
View file

@ -35,6 +35,8 @@ struct llama_sampling_context * llama_sampling_init(const struct llama_sampling_
result->prev.resize(params.n_prev);
result->n_considered = 0;
llama_sampling_set_rng_seed(result, params.seed);
return result;
@ -64,6 +66,7 @@ void llama_sampling_reset(llama_sampling_context * ctx) {
std::fill(ctx->prev.begin(), ctx->prev.end(), 0);
ctx->cur.clear();
ctx->n_considered = 0;
}
void llama_sampling_set_rng_seed(struct llama_sampling_context * ctx, uint32_t seed) {
@ -253,6 +256,8 @@ static llama_token llama_sampling_sample_impl(
}
}
ctx_sampling->n_considered = cur_p.size;
return id;
}