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

Merge branch 'master' into compilade/refactor-kv-cache

Browse source
This commit is contained in:
Francis Couture-Harpin 2024-06-30 15:31:25 -04:00
commit 10c3c419e9
518 changed files with 78202 additions and 66427 deletions
Download patch file Download diff file Expand all files Collapse all files

2
examples/main/CMakeLists.txt
View file

@ -1,4 +1,4 @@
set(TARGET main)
set(TARGET llama-cli)
add_executable(${TARGET} main.cpp)
install(TARGETS ${TARGET} RUNTIME)
target_link_libraries(${TARGET} PRIVATE common llama ${CMAKE_THREAD_LIBS_INIT})

24
examples/main/README.md
View file

@ -1,4 +1,4 @@
# llama.cpp/example/main
# llama.cpp/examples/main
This example program allows you to use various LLaMA language models in an easy and efficient way. It is specifically designed to work with the [llama.cpp](https://github.com/ggerganov/llama.cpp) project, which provides a plain C/C++ implementation with optional 4-bit quantization support for faster, lower memory inference, and is optimized for desktop CPUs. This program can be used to perform various inference tasks with LLaMA models, including generating text based on user-provided prompts and chat-like interactions with reverse prompts.
@ -20,13 +20,13 @@ To get started right away, run the following command, making sure to use the cor
#### Unix-based systems (Linux, macOS, etc.):
```bash
./main -m models/7B/ggml-model.bin --prompt "Once upon a time"
./llama-cli -m models/7B/ggml-model.bin --prompt "Once upon a time"
```
#### Windows:
```powershell
main.exe -m models\7B\ggml-model.bin --prompt "Once upon a time"
llama-cli.exe -m models\7B\ggml-model.bin --prompt "Once upon a time"
```
For an interactive experience, try this command:
@ -34,7 +34,7 @@ For an interactive experience, try this command:
#### Unix-based systems (Linux, macOS, etc.):
```bash
./main -m models/7B/ggml-model.bin -n -1 --color -r "User:" --in-prefix " " -i -p \
./llama-cli -m models/7B/ggml-model.bin -n -1 --color -r "User:" --in-prefix " " -i -p \
'User: Hi
AI: Hello. I am an AI chatbot. Would you like to talk?
User: Sure!
@ -45,7 +45,7 @@ User:'
#### Windows:
```powershell
main.exe -m models\7B\ggml-model.bin -n -1 --color -r "User:" --in-prefix " " -i -e -p "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:"
llama-cli.exe -m models\7B\ggml-model.bin -n -1 --color -r "User:" --in-prefix " " -i -e -p "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:"
```
The following command generates "infinite" text from a starting prompt (you can use `Ctrl-C` to stop it):
@ -53,18 +53,18 @@ The following command generates "infinite" text from a starting prompt (you can
#### Unix-based systems (Linux, macOS, etc.):
```bash
./main -m models/7B/ggml-model.bin --ignore-eos -n -1
./llama-cli -m models/7B/ggml-model.bin --ignore-eos -n -1
```
#### Windows:
```powershell
main.exe -m models\7B\ggml-model.bin --ignore-eos -n -1
llama-cli.exe -m models\7B\ggml-model.bin --ignore-eos -n -1
```
## Common Options
In this section, we cover the most commonly used options for running the `main` program with the LLaMA models:
In this section, we cover the most commonly used options for running the `llama-cli` program with the LLaMA models:
- `-m FNAME, --model FNAME`: Specify the path to the LLaMA model file (e.g., `models/7B/ggml-model.gguf`; inferred from `--model-url` if set).
- `-mu MODEL_URL --model-url MODEL_URL`: Specify a remote http url to download the file (e.g https://huggingface.co/ggml-org/models/resolve/main/phi-2/ggml-model-q4_0.gguf).
@ -74,7 +74,7 @@ In this section, we cover the most commonly used options for running the `main`
## Input Prompts
The `main` program provides several ways to interact with the LLaMA models using input prompts:
The `llama-cli` program provides several ways to interact with the LLaMA models using input prompts:
- `--prompt PROMPT`: Provide a prompt directly as a command-line option.
- `--file FNAME`: Provide a file containing a prompt or multiple prompts.
@ -82,7 +82,7 @@ The `main` program provides several ways to interact with the LLaMA models using
## Interaction
The `main` program offers a seamless way to interact with LLaMA models, allowing users to engage in real-time conversations or provide instructions for specific tasks. The interactive mode can be triggered using various options, including `--interactive` and `--interactive-first`.
The `llama-cli` program offers a seamless way to interact with LLaMA models, allowing users to engage in real-time conversations or provide instructions for specific tasks. The interactive mode can be triggered using various options, including `--interactive` and `--interactive-first`.
In interactive mode, users can participate in text generation by injecting their input during the process. Users can press `Ctrl+C` at any time to interject and type their input, followed by pressing `Return` to submit it to the LLaMA model. To submit additional lines without finalizing input, users can end the current line with a backslash (`\`) and continue typing.
@ -107,7 +107,7 @@ To overcome this limitation, you can use the `--in-prefix` flag to add a space o
The `--in-prefix` flag is used to add a prefix to your input, primarily, this is used to insert a space after the reverse prompt. Here's an example of how to use the `--in-prefix` flag in conjunction with the `--reverse-prompt` flag:
```sh
./main -r "User:" --in-prefix " "
./llama-cli -r "User:" --in-prefix " "
```
### In-Suffix
@ -115,7 +115,7 @@ The `--in-prefix` flag is used to add a prefix to your input, primarily, this is
The `--in-suffix` flag is used to add a suffix after your input. This is useful for adding an "Assistant:" prompt after the user's input. It's added after the new-line character (`\n`) that's automatically added to the end of the user's input. Here's an example of how to use the `--in-suffix` flag in conjunction with the `--reverse-prompt` flag:
```sh
./main -r "User:" --in-prefix " " --in-suffix "Assistant:"
./llama-cli -r "User:" --in-prefix " " --in-suffix "Assistant:"
```
## Context Management

58
examples/main/main.cpp
View file

@ -39,12 +39,12 @@ static std::ostringstream * g_output_ss;
static std::vector<llama_token> * g_output_tokens;
static bool is_interacting = false;
static bool file_exists(const std::string &path) {
static bool file_exists(const std::string & path) {
std::ifstream f(path.c_str());
return f.good();
}
static bool file_is_empty(const std::string &path) {
static bool file_is_empty(const std::string & path) {
std::ifstream f;
f.exceptions(std::ifstream::failbit | std::ifstream::badbit);
f.open(path.c_str(), std::ios::in | std::ios::binary | std::ios::ate);
@ -117,6 +117,14 @@ static void llama_log_callback_logTee(ggml_log_level level, const char * text, v
LOG_TEE("%s", text);
}
static std::string chat_add_and_format(struct llama_model * model, std::vector<llama_chat_msg> & chat_msgs, std::string role, std::string content) {
llama_chat_msg new_msg{role, content};
auto formatted = llama_chat_format_single(
model, g_params->chat_template, chat_msgs, new_msg, role == "user");
chat_msgs.push_back({role, content});
return formatted;
}
int main(int argc, char ** argv) {
gpt_params params;
g_params = &params;
@ -190,6 +198,7 @@ int main(int argc, char ** argv) {
llama_model * model;
llama_context * ctx;
llama_context * ctx_guidance = NULL;
std::vector<llama_chat_msg> chat_msgs;
g_model = &model;
g_ctx = &ctx;
@ -215,6 +224,8 @@ int main(int argc, char ** argv) {
__func__, n_ctx_train, n_ctx);
}
LOG_TEE("%s: chat template example: %s\n", __func__, llama_chat_format_example(model, params.chat_template).c_str());
// print system information
{
LOG_TEE("\n");
@ -249,16 +260,21 @@ int main(int argc, char ** argv) {
std::vector<llama_token> embd_inp;
if (params.interactive_first || !params.prompt.empty() || session_tokens.empty()) {
LOG("tokenize the prompt\n");
embd_inp = ::llama_tokenize(ctx, params.prompt, true, true);
} else {
LOG("use session tokens\n");
embd_inp = session_tokens;
}
{
auto prompt = (params.conversation && params.enable_chat_template)
? chat_add_and_format(model, chat_msgs, "system", params.prompt) // format the system prompt in conversation mode
: params.prompt;
if (params.interactive_first || !params.prompt.empty() || session_tokens.empty()) {
LOG("tokenize the prompt\n");
embd_inp = ::llama_tokenize(ctx, prompt, true, true);
} else {
LOG("use session tokens\n");
embd_inp = session_tokens;
}
LOG("prompt: \"%s\"\n", log_tostr(params.prompt));
LOG("tokens: %s\n", LOG_TOKENS_TOSTR_PRETTY(ctx, embd_inp).c_str());
LOG("prompt: \"%s\"\n", log_tostr(prompt));
LOG("tokens: %s\n", LOG_TOKENS_TOSTR_PRETTY(ctx, embd_inp).c_str());
}
// Should not run without any tokens
if (embd_inp.empty()) {
@ -481,6 +497,7 @@ int main(int argc, char ** argv) {
std::vector<int> input_tokens; g_input_tokens = &input_tokens;
std::vector<int> output_tokens; g_output_tokens = &output_tokens;
std::ostringstream output_ss; g_output_ss = &output_ss;
std::ostringstream assistant_ss; // for storing current assistant message, used in conversation mode
// the first thing we will do is to output the prompt, so set color accordingly
console::set_display(console::prompt);
@ -798,11 +815,20 @@ int main(int argc, char ** argv) {
is_antiprompt = true;
}
if (params.enable_chat_template) {
chat_add_and_format(model, chat_msgs, "assistant", assistant_ss.str());
}
is_interacting = true;
printf("\n");
}
}
// if current token is not EOG, we add it to current assistant message
if (params.conversation) {
auto id = llama_sampling_last(ctx_sampling);
assistant_ss << llama_token_to_piece(ctx, id, false);
}
if (n_past > 0 && is_interacting) {
LOG("waiting for user input\n");
@ -853,8 +879,13 @@ int main(int argc, char ** argv) {
string_process_escapes(buffer);
}
bool format_chat = params.conversation && params.enable_chat_template;
std::string user_inp = format_chat
? chat_add_and_format(model, chat_msgs, "user", std::move(buffer))
: std::move(buffer);
// TODO: one inconvenient of current chat template implementation is that we can't distinguish between user input and special tokens (prefix/postfix)
const auto line_pfx = ::llama_tokenize(ctx, params.input_prefix, false, true);
const auto line_inp = ::llama_tokenize(ctx, buffer, false, false);
const auto line_inp = ::llama_tokenize(ctx, user_inp, false, format_chat);
const auto line_sfx = ::llama_tokenize(ctx, params.input_suffix, false, true);
LOG("input tokens: %s\n", LOG_TOKENS_TOSTR_PRETTY(ctx, line_inp).c_str());
@ -869,6 +900,9 @@ int main(int argc, char ** argv) {
output_ss << llama_token_to_piece(ctx, token);
}
// reset assistant message
assistant_ss.str("");
n_remain -= line_inp.size();
LOG("n_remain: %d\n", n_remain);
} else {