CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-28 08:31:25 +00:00
Code Issues Packages Projects Releases Wiki Activity

model-conversion : add embedding prompt file support (#15871)

Browse Source 
This commit adds support for passing a prompt file to the model
conversion targets/scripts. It also updates the logits.cpp to print out
embedding information in the same format as when running the original
embedding model.

The motivation for this is that it allows us to pass files of different
sizes when running the converted models and validating the logits.

This can be particularly important when testing the sliding window
functionality of models where the sequence length needs to exceed a
certain number of tokens to trigger the sliding window logic.
This commit is contained in:
Daniel Bevenius
2025-09-25 12:02:36 +02:00
committed by GitHub
parent d0991da39d
commit aa3ee0eb0b
7 changed files with 187 additions and 34 deletions
Download Patch File Download Diff File Expand all files Collapse all files

52
examples/model-conversion/logits.cpp
View File

@@ -151,6 +151,35 @@ int main(int argc, char ** argv) {
logits = llama_get_embeddings(ctx);
n_logits = llama_model_n_embd(model) * batch.n_tokens;
type = "-embeddings";
const int n_embd = llama_model_n_embd(model);
const int n_embd_count = batch.n_tokens;
printf("Embedding dimension: %d\n", n_embd);
printf("\n");
// Print embeddings in the specified format
for (int j = 0; j < n_embd_count; j++) {
printf("embedding %d: ", j);
// Print first 3 values
for (int i = 0; i < 3 && i < n_embd; i++) {
printf("%9.6f ", logits[j * n_embd + i]);
}
printf(" ... ");
// Print last 3 values
for (int i = n_embd - 3; i < n_embd; i++) {
if (i >= 0) {
printf("%9.6f ", logits[j * n_embd + i]);
}
}
printf("\n");
}
printf("\n");
printf("Embeddings size: %d\n", n_logits);
} else {
logits = llama_get_logits_ith(ctx, batch.n_tokens - 1);
@@ -183,22 +212,23 @@ int main(int argc, char ** argv) {
return 1;
}
for (int i = 0; i < n_logits; i++) {
fprintf(f, "%d: %.6f\n", i, logits[i]); // Added index and changed format
fprintf(f, "%d: %.6f\n", i, logits[i]);
}
fclose(f);
// Print first and last 10 logits for quick verification
printf("First 10 logits: ");
for (int i = 0; i < 10 && i < n_logits; i++) {
printf("%.6f ", logits[i]);
}
printf("\n");
if (!embedding_mode) {
printf("First 10 logits: ");
for (int i = 0; i < 10 && i < n_logits; i++) {
printf("%.6f ", logits[i]);
}
printf("\n");
printf("Last 10 logits: ");
for (int i = n_logits - 10; i < n_logits; i++) {
if (i >= 0) printf("%.6f ", logits[i]);
printf("Last 10 logits: ");
for (int i = n_logits - 10; i < n_logits; i++) {
if (i >= 0) printf("%.6f ", logits[i]);
}
printf("\n\n");
}
printf("\n\n");
printf("Logits saved to %s\n", bin_filename);
printf("Logits saved to %s\n", txt_filename);