vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-11 09:34:37 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'upstream' into concedo_experimental

Browse source 
# Conflicts:
#	.github/workflows/build.yml
#	CMakeLists.txt
#	README.md
#	ci/run.sh
#	llama.cpp
#	models/ggml-vocab-llama-bpe.gguf.inp
#	models/ggml-vocab-llama-bpe.gguf.out
#	requirements.txt
#	scripts/compare-llama-bench.py
#	scripts/sync-ggml.last
#	tests/CMakeLists.txt
#	tests/test-backend-ops.cpp
#	tests/test-grammar-integration.cpp
#	tests/test-tokenizer-1-bpe.cpp
This commit is contained in:
Concedo 2024-05-14 19:28:47 +08:00
commit 2ee808a747
66 changed files with 3034 additions and 1821 deletions
Download patch file Download diff file Expand all files Collapse all files

12
examples/embedding/embedding.cpp
View file

@ -50,6 +50,12 @@ static void batch_decode(llama_context * ctx, llama_batch & batch, float * outpu
}
float * out = output + batch.seq_id[i][0] * n_embd;
//TODO: I would also add a parameter here to enable normalization or not.
/*fprintf(stdout, "unnormalized_embedding:");
for (int hh = 0; hh < n_embd; hh++) {
fprintf(stdout, "%9.6f ", embd[hh]);
}
fprintf(stdout, "\n");*/
llama_embd_normalize(embd, out, n_embd);
}
}
@ -124,10 +130,12 @@ int main(int argc, char ** argv) {
inputs.push_back(inp);
}
// add SEP if not present
// check if the last token is SEP
// it should be automatically added by the tokenizer when 'tokenizer.ggml.add_eos_token' is set to 'true'
for (auto & inp : inputs) {
if (inp.empty() || inp.back() != llama_token_sep(model)) {
inp.push_back(llama_token_sep(model));
fprintf(stderr, "%s: warning: last token in the prompt is not SEP\n", __func__);
fprintf(stderr, "%s: 'tokenizer.ggml.add_eos_token' should be set to 'true' in the GGUF header\n", __func__);
}
}