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

ci : integrate with ggml-org/ci (#2250)

Browse source 
* ci : run ctest

ggml-ci

* ci : add open llama 3B-v2 tests

ggml-ci

* ci : disable wget progress output

ggml-ci

* ci : add open llama 3B-v2 tg tests for q4 and q5 quantizations

ggml-ci

* tests : try to fix tail free sampling test

ggml-ci

* ci : add K-quants

ggml-ci

* ci : add short perplexity tests

ggml-ci

* ci : add README.md

* ppl : add --chunks argument to limit max number of chunks

ggml-ci

* ci : update README
This commit is contained in:
Georgi Gerganov 2023-07-18 14:24:43 +03:00 • committed by GitHub
parent 6cbf9dfb32
commit d01bccde9f
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
8 changed files with 312 additions and 6 deletions
Download patch file Download diff file Expand all files Collapse all files

6
examples/perplexity/perplexity.cpp
View file

@ -32,13 +32,15 @@ void perplexity(llama_context * ctx, const gpt_params & params) {
// BOS tokens will be added for each chunk before eval
auto tokens = ::llama_tokenize(ctx, params.prompt, true);
int count = 0;
const int n_chunk_max = tokens.size() / params.n_ctx;
const int n_chunk = tokens.size() / params.n_ctx;
const int n_chunk = params.n_chunks < 0 ? n_chunk_max : std::min(params.n_chunks, n_chunk_max);
const int n_vocab = llama_n_vocab(ctx);
const int n_batch = params.n_batch;
int count = 0;
double nll = 0.0;
fprintf(stderr, "%s: calculating perplexity over %d chunks, batch_size=%d\n", __func__, n_chunk, n_batch);
for (int i = 0; i < n_chunk; ++i) {