diff options
Diffstat (limited to 'examples/imatrix/imatrix.cpp')
| -rw-r--r-- | examples/imatrix/imatrix.cpp | 3 |
1 files changed, 2 insertions, 1 deletions
diff --git a/examples/imatrix/imatrix.cpp b/examples/imatrix/imatrix.cpp index d8cb0a64..1bf55f90 100644 --- a/examples/imatrix/imatrix.cpp +++ b/examples/imatrix/imatrix.cpp @@ -349,12 +349,13 @@ static void process_logits( static bool compute_imatrix(llama_context * ctx, const gpt_params & params, bool compute_ppl, int from_chunk) { const bool add_bos = llama_should_add_bos_token(llama_get_model(ctx)); + GGML_ASSERT(llama_add_eos_token(llama_get_model(ctx)) != 1); const int n_ctx = llama_n_ctx(ctx); auto tim1 = std::chrono::high_resolution_clock::now(); fprintf(stderr, "%s: tokenizing the input ..\n", __func__); - std::vector<llama_token> tokens = ::llama_tokenize(ctx, params.prompt, add_bos); + std::vector<llama_token> tokens = ::llama_tokenize(ctx, params.prompt, true); auto tim2 = std::chrono::high_resolution_clock::now(); fprintf(stderr, "%s: tokenization took %g ms\n",__func__,1e-3*std::chrono::duration_cast<std::chrono::microseconds>(tim2-tim1).count()); |