CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-04 09:32:00 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'master' into compilade/refactor-kv-cache

Browse Source
This commit is contained in:
Francis Couture-Harpin
2024-08-31 21:06:32 -04:00
parent 9b38f8bf65 a47667cff4
commit bc320ef66d
395 changed files with 57725 additions and 169970 deletions
Download Patch File Download Diff File Expand all files Collapse all files

13
examples/retrieval/retrieval.cpp
View File

@@ -148,11 +148,12 @@ int main(int argc, char ** argv) {
llama_backend_init();
llama_numa_init(params.numa);
llama_model * model;
llama_context * ctx;
// load the model
std::tie(model, ctx) = llama_init_from_gpt_params(params);
llama_init_result llama_init = llama_init_from_gpt_params(params);
llama_model * model = llama_init.model;
llama_context * ctx = llama_init.context;
if (model == NULL) {
fprintf(stderr, "%s: error: unable to load model\n", __func__);
return 1;
@@ -252,6 +253,8 @@ int main(int argc, char ** argv) {
chunks[i].tokens.clear();
}
struct llama_batch query_batch = llama_batch_init(n_batch, 0, 1);
// start loop, receive query and return top k similar chunks based on cosine similarity
std::string query;
while (true) {
@@ -259,7 +262,6 @@ int main(int argc, char ** argv) {
std::getline(std::cin, query);
std::vector<int32_t> query_tokens = llama_tokenize(ctx, query, true);
struct llama_batch query_batch = llama_batch_init(n_batch, 0, 1);
batch_add_seq(query_batch, query_tokens, 0);
std::vector<float> query_emb(n_embd, 0);
@@ -292,6 +294,7 @@ int main(int argc, char ** argv) {
}
// clean up
llama_batch_free(query_batch);
llama_print_timings(ctx);
llama_free(ctx);
llama_free_model(model);