From 9b0a4d421459f4e5e1af735c9784c3247b379025 Mon Sep 17 00:00:00 2001 From: mgroeber9110 <45620825+mgroeber9110@users.noreply.github.com> Date: Mon, 24 Apr 2023 17:45:32 +0200 Subject: [PATCH] examples/main README improvements and some light refactoring (#1131) --- README.md | 2 +- examples/common.cpp | 4 +--- examples/common.h | 2 +- examples/main/README.md | 14 ++++++++++++-- examples/main/main.cpp | 6 +++--- 5 files changed, 18 insertions(+), 10 deletions(-) diff --git a/README.md b/README.md index 7bf2cc1..44cf721 100644 --- a/README.md +++ b/README.md @@ -241,7 +241,7 @@ Here is an example of a few-shot interaction, invoked with the command ./main -m ./models/13B/ggml-model-q4_0.bin -n 256 --repeat_penalty 1.0 --color -i -r "User:" -f prompts/chat-with-bob.txt ``` -Note the use of `--color` to distinguish between user input and generated text. +Note the use of `--color` to distinguish between user input and generated text. Other parameters are explained in more detail in the [README](examples/main/README.md) for the `main` example program. ![image](https://user-images.githubusercontent.com/1991296/224575029-2af3c7dc-5a65-4f64-a6bb-517a532aea38.png) diff --git a/examples/common.cpp b/examples/common.cpp index a0b6f10..c0e87eb 100644 --- a/examples/common.cpp +++ b/examples/common.cpp @@ -156,10 +156,8 @@ bool gpt_params_parse(int argc, char ** argv, gpt_params & params) { params.interactive = true; } else if (arg == "--embedding") { params.embedding = true; - } else if (arg == "--interactive-start") { - params.interactive = true; } else if (arg == "--interactive-first") { - params.interactive_start = true; + params.interactive_first = true; } else if (arg == "-ins" || arg == "--instruct") { params.instruct = true; } else if (arg == "--color") { diff --git a/examples/common.h b/examples/common.h index 0470368..6f26b51 100644 --- a/examples/common.h +++ b/examples/common.h @@ -43,7 +43,7 @@ struct gpt_params { bool interactive = false; // interactive mode bool embedding = false; // get only sentence embedding - bool interactive_start = false; // wait for user input immediately + bool interactive_first = false; // wait for user input immediately bool instruct = false; // instruction mode (used for Alpaca models) bool ignore_eos = false; // do not stop generating after eos diff --git a/examples/main/README.md b/examples/main/README.md index 5cbc503..234bf2e 100644 --- a/examples/main/README.md +++ b/examples/main/README.md @@ -21,12 +21,20 @@ To get started right away, run the following command, making sure to use the cor ./main -m models/7B/ggml-model.bin --prompt "Once upon a time" ``` +The following command generates "infinite" text from a starting prompt (you can use `Ctrl-C` to stop it): + +```bash +./main -m models/7B/ggml-model.bin --ignore-eos --n_predict -1 --keep -1 --prompt "Once upon a time" +``` + For an interactive experience, try this command: ```bash ./main -m models/7B/ggml-model.bin -n -1 --color -r "User:" --in-prefix " " --prompt $'User: Hi\nAI: Hello. I am an AI chatbot. Would you like to talk?\nUser: Sure!\nAI: What would you like to talk about?\nUser:' ``` +Note that the newline characters in the prompt string above only work on Linux. On Windows, you will have to use the ``--file`` option (see below) to load a multi-line prompt from file instead. + ## Common Options In this section, we cover the most commonly used options for running the `main` program with the LLaMA models: @@ -84,6 +92,8 @@ Instruction mode is particularly useful when working with Alpaca models, which a - `-ins, --instruct`: Enable instruction mode to leverage the capabilities of Alpaca models in completing tasks based on user-provided instructions. +Technical detail: the user's input is internally prefixed with the reverse prompt (or ``### Instruction:`` as the default), and followed by ``### Response:`` (except if you just press Return without any input, to keep generating a longer response). + By understanding and utilizing these interaction options, you can create engaging and dynamic experiences with the LLaMA models, tailoring the text generation process to your specific needs. ## Context Management @@ -114,7 +124,7 @@ The following options are related to controlling the text generation process, in The `--n_predict` option controls the number of tokens the model generates in response to the input prompt. By adjusting this value, you can influence the length of the generated text. A higher value will result in longer text, while a lower value will produce shorter text. A value of -1 will cause text to be generated without limit. -It is important to note that the generated text may be shorter than the specified number of tokens if an End-of-Sequence (EOS) token or a reverse prompt is encountered. In interactive mode text generation will pause and control will be returned to the user. In non-interactive mode, the program will end. In both cases, the text generation may stop before reaching the specified `n_predict` value. +It is important to note that the generated text may be shorter than the specified number of tokens if an End-of-Sequence (EOS) token or a reverse prompt is encountered. In interactive mode text generation will pause and control will be returned to the user. In non-interactive mode, the program will end. In both cases, the text generation may stop before reaching the specified `n_predict` value. If you want the model to keep going without ever producing End-of-Sequence on its own, you can use the ``--ignore-eos`` parameter. ### RNG Seed @@ -126,7 +136,7 @@ The RNG seed is used to initialize the random number generator that influences t - `--temp N`: Adjust the randomness of the generated text (default: 0.8). -Temperature is a hyperparameter that controls the randomness of the generated text. It affects the probability distribution of the model's output tokens. A higher temperature (e.g., 1.5) makes the output more random and creative, while a lower temperature (e.g., 0.5) makes the output more focused, deterministic, and conservative. The default value is 0.8, which provides a balance between randomness and determinism. +Temperature is a hyperparameter that controls the randomness of the generated text. It affects the probability distribution of the model's output tokens. A higher temperature (e.g., 1.5) makes the output more random and creative, while a lower temperature (e.g., 0.5) makes the output more focused, deterministic, and conservative. The default value is 0.8, which provides a balance between randomness and determinism. At the extreme, a temperature of 0 will always pick the most likely next token, leading to identical outputs in each run. Example usage: `--temp 0.8` diff --git a/examples/main/main.cpp b/examples/main/main.cpp index decf41a..f9c9e9d 100644 --- a/examples/main/main.cpp +++ b/examples/main/main.cpp @@ -178,12 +178,12 @@ int main(int argc, char ** argv) { // in instruct mode, we inject a prefix and a suffix to each input by the user if (params.instruct) { - params.interactive_start = true; + params.interactive_first = true; params.antiprompt.push_back("### Instruction:\n\n"); } // enable interactive mode if reverse prompt or interactive start is specified - if (params.antiprompt.size() != 0 || params.interactive_start) { + if (params.antiprompt.size() != 0 || params.interactive_first) { params.interactive = true; } @@ -246,7 +246,7 @@ int main(int argc, char ** argv) { #endif " - Press Return to return control to LLaMa.\n" " - If you want to submit another line, end your input in '\\'.\n\n"); - is_interacting = params.interactive_start; + is_interacting = params.interactive_first; } bool is_antiprompt = false;