diff --git a/examples/parallel/parallel.cpp b/examples/parallel/parallel.cpp index 886de08f8..f0e49249b 100644 --- a/examples/parallel/parallel.cpp +++ b/examples/parallel/parallel.cpp @@ -398,7 +398,11 @@ int main(int argc, char ** argv) { print_date_time(); LOG_TEE("\n%s: n_parallel = %d, n_sequences = %d, cont_batching = %d, system tokens = %d\n", __func__, n_clients, n_seq, cont_batching, n_tokens_system); - printf("external prompt file (if any): %s\n\n", params.prompt_file.c_str()); + if (params.prompt_file.empty()) { + params.prompt_file = "used build-in defaults"; + } + printf("External prompt file: \033[32m%s\033[0m\n", params.prompt_file.c_str()); + printf("Model and path used: \033[32m%s\033[0m\n\n", params.model.c_str()); LOG_TEE("Total prompt tokens: %6d, speed: %5.2f t/s\n", n_total_prompt, (double) (n_total_prompt ) / (t_main_end - t_main_start) * 1e6); LOG_TEE("Total gen tokens: %6d, speed: %5.2f t/s\n", n_total_gen, (double) (n_total_gen ) / (t_main_end - t_main_start) * 1e6); diff --git a/prompts/LLM-questions.txt b/prompts/LLM-questions.txt new file mode 100644 index 000000000..79fa98855 --- /dev/null +++ b/prompts/LLM-questions.txt @@ -0,0 +1,39 @@ +In the context of LLMs, what is "Attention"? +In the context of LLMs, what is a completion? +In the context of LLMs, what is a prompt? +In the context of LLMs, what is GELU? +In the context of LLMs, what is RELU? +In the context of LLMs, what is softmax? +In the context of LLMs, what is decoding? +In the context of LLMs, what is encoding? +In the context of LLMs, what is tokenizing? +In the context of LLMs, what is an embedding? +In the context of LLMs, what is an quantization? +In the context of LLMs, what is a tensor? +In the context of LLMs, what is a sparse tensor? +In the context of LLMs, what is a vector? +In the context of LLMs, how is attention implemented? +In the context of LLMs, why is attention all you need? +In the context of LLMs, what is "RoPe" and what is it used for? +In the context of LLMs, what is "LoRA" and what is it used for? +In the context of LLMs, what are weights? +In the context of LLMs, what are biases? +In the context of neural nets, what is a hidden layer? +In the context of neural nets, what is a convolution? +In the context of neural nets, what is dropout? +In the context of neural nets, what is cross-entropy? +In the context of neural nets, what is over-fitting? +In the context of neural nets, what is under-fitting? +What is the difference between an interpreted computer language and a compiled computer language? +What is a debugger? +When processing using a GPU, what is off-loading? +When processing using a GPU, what is a batch? +When processing using a GPU, what is a block? +When processing using a GPU, what is the difference between a batch and a block? +When processing using a GPU, what is a scratch tensor? +When processing using a GPU, what is a layer? +When processing using a GPU, what is a cache? +When processing using a GPU, what is unified memory? +When processing using a GPU, what is VRAM? +When processing using a GPU, what is a kernel? +When processing using a GPU, what is "metal"? \ No newline at end of file diff --git a/prompts/parallel-questions.txt b/prompts/parallel-questions.txt index e946f209b..0ef9d8893 100644 --- a/prompts/parallel-questions.txt +++ b/prompts/parallel-questions.txt @@ -29,4 +29,14 @@ Which sense would you surrender if you could? Was Henry Ford a hero or a villain? Do we need leaders? What is nucleosynthesis? -Who is the greatest scientist of all time so far? \ No newline at end of file +Who is the greatest scientist of all time? +Who first observed what came to be known as the photovoltaic effect? +What is nuclear fusion and why does it release energy? +Can you know that you exist? +What is an exoplanet? +Do you like cream? +What is the difference? +Can I know that I exist while I'm dreaming that I'm Descartes? +Who said "I didn't know I thought that until I heard myself saying it"? +Does anything really matter? +Can you explain the unreasonable effectiveness of mathematics? \ No newline at end of file