all : be more strict about converting float to double (#458)

* Be more strict about converting float to double

* Test equivalence of round, SILU implementations

Test module is commented out in CMakeLists.txt because the tests may
take a long time, depending on how much the compiler optimizes.

* Fix softmax in perplexity.cpp

* all : prefer float over double where appropriate

* perplexity : add <cmath>

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
Stephan Walter 2023-03-28 16:48:20 +00:00 committed by GitHub
parent 20e1e84884
commit 436e561931
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
11 changed files with 185 additions and 117 deletions

View file

@ -215,13 +215,13 @@ void gpt_print_usage(int /*argc*/, char ** argv, const gpt_params & params) {
fprintf(stderr, " prompt file to start generation.\n");
fprintf(stderr, " -n N, --n_predict N number of tokens to predict (default: %d, -1 = infinity)\n", params.n_predict);
fprintf(stderr, " --top_k N top-k sampling (default: %d)\n", params.top_k);
fprintf(stderr, " --top_p N top-p sampling (default: %.1f)\n", params.top_p);
fprintf(stderr, " --top_p N top-p sampling (default: %.1f)\n", (double)params.top_p);
fprintf(stderr, " --repeat_last_n N last n tokens to consider for penalize (default: %d)\n", params.repeat_last_n);
fprintf(stderr, " --repeat_penalty N penalize repeat sequence of tokens (default: %.1f)\n", params.repeat_penalty);
fprintf(stderr, " --repeat_penalty N penalize repeat sequence of tokens (default: %.1f)\n", (double)params.repeat_penalty);
fprintf(stderr, " -c N, --ctx_size N size of the prompt context (default: %d)\n", params.n_ctx);
fprintf(stderr, " --ignore-eos ignore end of stream token and continue generating\n");
fprintf(stderr, " --memory_f32 use f32 instead of f16 for memory key+value\n");
fprintf(stderr, " --temp N temperature (default: %.1f)\n", params.temp);
fprintf(stderr, " --temp N temperature (default: %.1f)\n", (double)params.temp);
fprintf(stderr, " --n_parts N number of model parts (default: -1 = determine from dimensions)\n");
fprintf(stderr, " -b N, --batch_size N batch size for prompt processing (default: %d)\n", params.n_batch);
fprintf(stderr, " --perplexity compute perplexity over the prompt\n");