bugfix: default should not be interactive (#304)

* fix coloring of last `n_batch` of prompt, and refactor line input
* forgot the newline that needs to be sent to the model
* (per #283) try to force flush of color reset in SIGINT handler

README.md

@@ -7,7 +7,7 @@ Inference of [LLaMA](https://arxiv.org/abs/2302.13971) model in pure C/C++
 
 **Hot topics:**
 
-- RMSNorm implementation / fixes: https://github.com/ggerganov/llama.cpp/issues/173
+- [Added Alpaca support](https://github.com/ggerganov/llama.cpp#instruction-mode-with-alpaca)
 - Cache input prompts for faster initialization: https://github.com/ggerganov/llama.cpp/issues/64
 - Create a `llama.cpp` logo: https://github.com/ggerganov/llama.cpp/issues/105
 
@@ -147,7 +147,7 @@ python3 -m pip install torch numpy sentencepiece
 python3 convert-pth-to-ggml.py models/7B/ 1
 
 # quantize the model to 4-bits
-./quantize.sh 7B
+python3 quantize.py 7B
 
 # run the inference
 ./main -m ./models/7B/ggml-model-q4_0.bin -n 128

alpaca.sh

@@ -0,0 +1,6 @@
+#!/bin/bash
+#
+# Temporary script - will be removed in the future
+#
+
+./main -m ./models/ggml-alpaca-7b-q4.bin --color -f ./prompts/alpaca.txt -ins --top_k 10000 --temp 0.96 --repeat_penalty 1 -t 7

main.cpp

@@ -7,6 +7,7 @@
 #include <cstdio>
 #include <cstring>
 #include <fstream>
+#include <iostream>
 #include <map>
 #include <string>
 #include <vector>
@@ -27,6 +28,8 @@
 #define ANSI_COLOR_RESET   "\x1b[0m"
 #define ANSI_BOLD          "\x1b[1m"
 
+static const int EOS_TOKEN_ID = 2;
+
 // determine number of model parts based on the dimension
 static const std::map<int, int> LLAMA_N_PARTS = {
     { 4096, 1 },
@@ -86,7 +89,7 @@ struct llama_model {
 };
 
 // load the model's weights from a file
-bool llama_model_load(const std::string & fname, llama_model & model, gpt_vocab & vocab, int n_ctx) {
+bool llama_model_load(const std::string & fname, llama_model & model, gpt_vocab & vocab, int n_ctx, ggml_type memory_type = GGML_TYPE_F32) {
     fprintf(stderr, "%s: loading model from '%s' - please wait ...\n", __func__, fname.c_str());
 
     std::vector<char> f_buf(1024*1024);
@@ -207,8 +210,8 @@ bool llama_model_load(const std::string & fname, llama_model & model, gpt_vocab
         ctx_size += n_layer*(n_ff*n_embd*ggml_type_sizef(wtype)); // w2
         ctx_size += n_layer*(n_ff*n_embd*ggml_type_sizef(wtype)); // w3
 
-        ctx_size += n_ctx*n_layer*n_embd*ggml_type_sizef(GGML_TYPE_F32); // memory_k
-        ctx_size += n_ctx*n_layer*n_embd*ggml_type_sizef(GGML_TYPE_F32); // memory_v
+        ctx_size += n_ctx*n_layer*n_embd*ggml_type_sizef(memory_type); // memory_k
+        ctx_size += n_ctx*n_layer*n_embd*ggml_type_sizef(memory_type); // memory_v
 
         ctx_size += (5 + 10*n_layer)*256; // object overhead
 
@@ -293,8 +296,8 @@ bool llama_model_load(const std::string & fname, llama_model & model, gpt_vocab
         const int n_mem      = n_layer*n_ctx;
         const int n_elements = n_embd*n_mem;
 
-        model.memory_k = ggml_new_tensor_1d(ctx, GGML_TYPE_F32, n_elements);
-        model.memory_v = ggml_new_tensor_1d(ctx, GGML_TYPE_F32, n_elements);
+        model.memory_k = ggml_new_tensor_1d(ctx, memory_type, n_elements);
+        model.memory_v = ggml_new_tensor_1d(ctx, memory_type, n_elements);
 
         const size_t memory_size = ggml_nbytes(model.memory_k) + ggml_nbytes(model.memory_v);
 
@@ -747,6 +750,7 @@ static bool is_interacting = false;
 #if defined (__unix__) || (defined (__APPLE__) && defined (__MACH__)) || defined (_WIN32)
 void sigint_handler(int signo) {
     printf(ANSI_COLOR_RESET);
+    printf("\n"); // this also force flush stdout.
     if (signo == SIGINT) {
         if (!is_interacting) {
             is_interacting=true;
@@ -800,7 +804,7 @@ int main(int argc, char ** argv) {
     fprintf(stderr, "%s: seed = %d\n", __func__, params.seed);
 
     std::mt19937 rng(params.seed);
-    if (params.prompt.empty()) {
+    if (params.random_prompt) {
         params.prompt = gpt_random_prompt(rng);
     }
 
@@ -814,8 +818,9 @@ int main(int argc, char ** argv) {
 
     // load the model
     {
+        const ggml_type memory_type = params.memory_f16 ? GGML_TYPE_F16 : GGML_TYPE_F32;
         const int64_t t_start_us = ggml_time_us();
-        if (!llama_model_load(params.model, model, vocab, params.n_ctx)) {
+        if (!llama_model_load(params.model, model, vocab, params.n_ctx, memory_type)) {
             fprintf(stderr, "%s: failed to load model from '%s'\n", __func__, params.model.c_str());
             return 1;
         }
@@ -851,14 +856,18 @@ 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 = true;
-        params.antiprompt = "### Instruction:\n\n";
+        params.antiprompt.push_back("### Instruction:\n\n");
     }
 
     // tokenize the reverse prompt
-    std::vector<gpt_vocab::id> antiprompt_inp = ::llama_tokenize(vocab, params.antiprompt, false);
+    std::vector<std::vector<gpt_vocab::id>> antipromptv_inp;
+    
+    for (auto antiprompt : params.antiprompt) {
+        antipromptv_inp.push_back(::llama_tokenize(vocab, antiprompt, false));
+    }
 
     // enable interactive mode if reverse prompt is specified
-    if (!antiprompt_inp.empty()) {
+    if (antipromptv_inp.size() != 0) {
         params.interactive = true;
     }
 
@@ -882,13 +891,16 @@ int main(int argc, char ** argv) {
 
         fprintf(stderr, "%s: interactive mode on.\n", __func__);
 
-        if (antiprompt_inp.size()) {
-            fprintf(stderr, "%s: reverse prompt: '%s'\n", __func__, params.antiprompt.c_str());
-            fprintf(stderr, "%s: number of tokens in reverse prompt = %zu\n", __func__, antiprompt_inp.size());
-            for (int i = 0; i < (int) antiprompt_inp.size(); i++) {
-                fprintf(stderr, "%6d -> '%s'\n", antiprompt_inp[i], vocab.id_to_token.at(antiprompt_inp[i]).c_str());
+        if(antipromptv_inp.size()) {
+            for (size_t apindex = 0; apindex < antipromptv_inp.size(); ++apindex) {
+                auto antiprompt_inp = antipromptv_inp.at(apindex);
+                fprintf(stderr, "%s: reverse prompt: '%s'\n", __func__, params.antiprompt.at(apindex).c_str());
+                fprintf(stderr, "%s: number of tokens in reverse prompt = %zu\n", __func__, antiprompt_inp.size());
+                for (int i = 0; i < (int) antiprompt_inp.size(); i++) {
+                    fprintf(stderr, "%6d -> '%s'\n", antiprompt_inp[i], vocab.id_to_token.at(antiprompt_inp[i]).c_str());
+                }
+                fprintf(stderr, "\n");
             }
-            fprintf(stderr, "\n");
         }
     }
     fprintf(stderr, "sampling parameters: temp = %f, top_k = %d, top_p = %f, repeat_last_n = %i, repeat_penalty = %f\n", params.temp, params.top_k, params.top_p, params.repeat_last_n, params.repeat_penalty);
@@ -954,6 +966,11 @@ int main(int argc, char ** argv) {
             {
                 const int64_t t_start_sample_us = ggml_time_us();
 
+                if (params.ignore_eos) {
+                    // set the logit of the eos token to zero to avoid sampling it
+                    logits[logits.size() - n_vocab + EOS_TOKEN_ID] = 0;
+                }
+
                 id = llama_sample_top_p_top_k(vocab, logits.data() + (logits.size() - n_vocab), last_n_tokens, repeat_penalty, top_k, top_p, temp, rng);
 
                 last_n_tokens.erase(last_n_tokens.begin());
@@ -981,11 +998,6 @@ int main(int argc, char ** argv) {
                     break;
                 }
             }
-
-            // reset color to default if we there is no pending user input
-            if (!input_noecho && params.use_color && (int) embd_inp.size() == input_consumed) {
-                printf(ANSI_COLOR_RESET);
-            }
         }
 
         // display text
@@ -995,14 +1007,21 @@ int main(int argc, char ** argv) {
             }
             fflush(stdout);
         }
+        // reset color to default if we there is no pending user input
+        if (!input_noecho && params.use_color && (int)embd_inp.size() == input_consumed) {
+            printf(ANSI_COLOR_RESET);
+        }
 
         // in interactive mode, and not currently processing queued inputs;
         // check if we should prompt the user for more
         if (params.interactive && embd_inp.size() <= input_consumed) {
             // check for reverse prompt
-            if (antiprompt_inp.size() && std::equal(antiprompt_inp.rbegin(), antiprompt_inp.rend(), last_n_tokens.rbegin())) {
-                // reverse prompt found
-                is_interacting = true;
+            for (auto antiprompt_inp : antipromptv_inp) {
+                if (antiprompt_inp.size() && std::equal(antiprompt_inp.rbegin(), antiprompt_inp.rend(), last_n_tokens.rbegin())) {
+                    // reverse prompt found
+                    is_interacting = true;
+                    break;
+                }
             }
             if (is_interacting) {
                 if (params.instruct) {
@@ -1013,47 +1032,37 @@ int main(int argc, char ** argv) {
                 }
 
                 // currently being interactive
+                if (params.use_color) printf(ANSI_BOLD ANSI_COLOR_GREEN);
+                std::string buffer;
+                std::string line;
                 bool another_line = true;
-                while (another_line) {
-                    fflush(stdout);
-                    char buf[256] = {0};
-                    int n_read;
-                    if (params.use_color) printf(ANSI_BOLD ANSI_COLOR_GREEN);
-                    if (scanf("%255[^\n]%n%*c", buf, &n_read) <= 0) {
-                        // presumable empty line, consume the newline
-                        std::ignore = scanf("%*c");
-                        n_read=0;
-                    }
-                    if (params.use_color) printf(ANSI_COLOR_RESET);
-
-                    if (n_read > 0 && buf[n_read-1]=='\\') {
-                        another_line = true;
-                        buf[n_read-1] = '\n';
-                        buf[n_read] = 0;
-                    } else {
+                do {
+                    std::getline(std::cin, line);
+                    if (line.empty() || line.back() != '\\') {
                         another_line = false;
-                        buf[n_read] = '\n';
-                        buf[n_read+1] = 0;
+                    } else {
+                        line.pop_back(); // Remove the continue character
                     }
+                    buffer += line + '\n'; // Append the line to the result
+                } while (another_line);
+                if (params.use_color) printf(ANSI_COLOR_RESET);
 
-                    std::vector<gpt_vocab::id> line_inp = ::llama_tokenize(vocab, buf, false);
-                    embd_inp.insert(embd_inp.end(), line_inp.begin(), line_inp.end());
+                std::vector<gpt_vocab::id> line_inp = ::llama_tokenize(vocab, buffer, false);
+                embd_inp.insert(embd_inp.end(), line_inp.begin(), line_inp.end());
 
-                    if (params.instruct) {
-                        embd_inp.insert(embd_inp.end(), inp_sfx.begin(), inp_sfx.end());
-                    }
-
-                    remaining_tokens -= line_inp.size();
-
-                    input_noecho = true; // do not echo this again
+                if (params.instruct) {
+                    embd_inp.insert(embd_inp.end(), inp_sfx.begin(), inp_sfx.end());
                 }
 
-                is_interacting = false;
+                remaining_tokens -= line_inp.size();
+
+                input_noecho = true; // do not echo this again
             }
+            is_interacting = false;
         }
 
         // end of text token
-        if (embd.back() == 2) {
+        if (embd.back() == EOS_TOKEN_ID) {
             if (params.interactive) {
                 is_interacting = true;
             } else {
@@ -1061,6 +1070,12 @@ int main(int argc, char ** argv) {
                 break;
             }
         }
+
+        // In interactive mode, respect the maximum number of tokens and drop back to user input when reached.
+        if (params.interactive && remaining_tokens <= 0) {
+            remaining_tokens = params.n_predict;
+            is_interacting = true;
+        }
     }
 
 #if defined (_WIN32)

quantize.py

@@ -0,0 +1,126 @@
+#!/usr/bin/env python3
+
+"""Script to execute the "quantize" script on a given set of models."""
+
+import subprocess
+import argparse
+import glob
+import sys
+import os
+
+
+def main():
+    """Update the quantize binary name depending on the platform and parse
+    the command line arguments and execute the script.
+    """
+
+    if "linux" in sys.platform or "darwin" in sys.platform:
+        quantize_script_binary = "quantize"
+
+    elif "win32" in sys.platform or "cygwin" in sys.platform:
+        quantize_script_binary = "quantize.exe"
+
+    else:
+        print("WARNING: Unknown platform. Assuming a UNIX-like OS.\n")
+        quantize_script_binary = "quantize"
+
+    parser = argparse.ArgumentParser(
+        prog='python3 quantize.py',
+        description='This script quantizes the given models by applying the '
+        f'"{quantize_script_binary}" script on them.'
+    )
+    parser.add_argument(
+        'models', nargs='+', choices=('7B', '13B', '30B', '65B'),
+        help='The models to quantize.'
+    )
+    parser.add_argument(
+        '-r', '--remove-16', action='store_true', dest='remove_f16',
+        help='Remove the f16 model after quantizing it.'
+    )
+    parser.add_argument(
+        '-m', '--models-path', dest='models_path',
+        default=os.path.join(os.getcwd(), "models"),
+        help='Specify the directory where the models are located.'
+    )
+    parser.add_argument(
+        '-q', '--quantize-script-path', dest='quantize_script_path',
+        default=os.path.join(os.getcwd(), quantize_script_binary),
+        help='Specify the path to the "quantize" script.'
+    )
+
+    # TODO: Revise this code
+    # parser.add_argument(
+    #     '-t', '--threads', dest='threads', type='int',
+    #     default=os.cpu_count(),
+    #     help='Specify the number of threads to use to quantize many models at '
+    #     'once. Defaults to os.cpu_count().'
+    # )
+
+    args = parser.parse_args()
+
+    if not os.path.isfile(args.quantize_script_path):
+        print(
+            f'The "{quantize_script_binary}" script was not found in the '
+            "current location.\nIf you want to use it from another location, "
+            "set the --quantize-script-path argument from the command line."
+        )
+        sys.exit(1)
+
+    for model in args.models:
+        # The model is separated in various parts
+        # (ggml-model-f16.bin, ggml-model-f16.bin.0, ggml-model-f16.bin.1...)
+        f16_model_path_base = os.path.join(
+            args.models_path, model, "ggml-model-f16.bin"
+        )
+
+        f16_model_parts_paths = map(
+            lambda filename: os.path.join(f16_model_path_base, filename),
+            glob.glob(f"{f16_model_path_base}*")
+        )
+
+        for f16_model_part_path in f16_model_parts_paths:
+            if not os.path.isfile(f16_model_part_path):
+                print(
+                    f"The f16 model {os.path.basename(f16_model_part_path)} "
+                    f"was not found in {args.models_path}{os.path.sep}{model}"
+                    ". If you want to use it from another location, set the "
+                    "--models-path argument from the command line."
+                )
+                sys.exit(1)
+
+            __run_quantize_script(
+                args.quantize_script_path, f16_model_part_path
+            )
+
+            if args.remove_f16:
+                os.remove(f16_model_part_path)
+
+
+# This was extracted to a top-level function for parallelization, if
+# implemented. See https://github.com/ggerganov/llama.cpp/pull/222/commits/f8db3d6cd91bf1a1342db9d29e3092bc12dd783c#r1140496406
+
+def __run_quantize_script(script_path, f16_model_part_path):
+    """Run the quantize script specifying the path to it and the path to the
+    f16 model to quantize.
+    """
+
+    new_quantized_model_path = f16_model_part_path.replace("f16", "q4_0")
+    subprocess.run(
+        [script_path, f16_model_part_path, new_quantized_model_path, "2"],
+        check=True
+    )
+
+
+if __name__ == "__main__":
+    try:
+        main()
+
+    except subprocess.CalledProcessError:
+        print("\nAn error ocurred while trying to quantize the models.")
+        sys.exit(1)
+
+    except KeyboardInterrupt:
+        sys.exit(0)
+
+    else:
+        print("\nSuccesfully quantized all models.")

quantize.sh

@@ -1,15 +0,0 @@
-#!/usr/bin/env bash
-
-if ! [[ "$1" =~ ^[0-9]{1,2}B$ ]]; then
-    echo
-    echo "Usage: quantize.sh 7B|13B|30B|65B [--remove-f16]"
-    echo
-    exit 1
-fi
-
-for i in `ls models/$1/ggml-model-f16.bin*`; do
-    ./quantize "$i" "${i/f16/q4_0}" 2
-    if [[ "$2" == "--remove-f16" ]]; then
-        rm "$i"
-    fi
-done

utils.cpp

@@ -49,6 +49,8 @@ bool gpt_params_parse(int argc, char ** argv, gpt_params & params) {
             params.top_k = std::stoi(argv[++i]);
         } else if (arg == "-c" || arg == "--ctx_size") {
             params.n_ctx = std::stoi(argv[++i]);
+        } else if (arg == "--memory_f16") {
+            params.memory_f16 = true;
         } else if (arg == "--top_p") {
             params.top_p = std::stof(argv[++i]);
         } else if (arg == "--temp") {
@@ -68,10 +70,14 @@ bool gpt_params_parse(int argc, char ** argv, gpt_params & params) {
         } else if (arg == "--color") {
             params.use_color = true;
         } else if (arg == "-r" || arg == "--reverse-prompt") {
-            params.antiprompt = argv[++i];
+            params.antiprompt.push_back(argv[++i]);
+        } else if (arg == "--ignore-eos") {
+            params.ignore_eos = true;
         } else if (arg == "-h" || arg == "--help") {
             gpt_print_usage(argc, argv, params);
             exit(0);
+        } else if (arg == "--random-prompt") {
+            params.random_prompt = true;
         } else {
             fprintf(stderr, "error: unknown argument: %s\n", arg.c_str());
             gpt_print_usage(argc, argv, params);
@@ -90,12 +96,14 @@ void gpt_print_usage(int /*argc*/, char ** argv, const gpt_params & params) {
     fprintf(stderr, "  -i, --interactive     run in interactive mode\n");
     fprintf(stderr, "  -ins, --instruct      run in instruction mode (use with Alpaca models)\n");
     fprintf(stderr, "  -r PROMPT, --reverse-prompt PROMPT\n");
-    fprintf(stderr, "                        in interactive mode, poll user input upon seeing PROMPT\n");
+    fprintf(stderr, "                        in interactive mode, poll user input upon seeing PROMPT (can be\n");
+    fprintf(stderr, "                        specified more than once for multiple prompts).\n");
     fprintf(stderr, "  --color               colorise output to distinguish prompt and user input from generations\n");
     fprintf(stderr, "  -s SEED, --seed SEED  RNG seed (default: -1)\n");
     fprintf(stderr, "  -t N, --threads N     number of threads to use during computation (default: %d)\n", params.n_threads);
     fprintf(stderr, "  -p PROMPT, --prompt PROMPT\n");
-    fprintf(stderr, "                        prompt to start generation with (default: random)\n");
+    fprintf(stderr, "                        prompt to start generation with (default: empty)\n");
+    fprintf(stderr, "  --random-prompt       start with a randomized prompt.\n");
     fprintf(stderr, "  -f FNAME, --file FNAME\n");
     fprintf(stderr, "                        prompt file to start generation.\n");
     fprintf(stderr, "  -n N, --n_predict N   number of tokens to predict (default: %d)\n", params.n_predict);
@@ -104,6 +112,8 @@ void gpt_print_usage(int /*argc*/, char ** argv, const gpt_params & params) {
     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, "  -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_f16          use f16 instead of f32 for memory key+value\n");
     fprintf(stderr, "  --temp N              temperature (default: %.1f)\n", params.temp);
     fprintf(stderr, "  -b N, --batch_size N  batch size for prompt processing (default: %d)\n", params.n_batch);
     fprintf(stderr, "  -m FNAME, --model FNAME\n");

utils.h

@@ -18,6 +18,7 @@ struct gpt_params {
     int32_t n_predict = 128; // new tokens to predict
     int32_t repeat_last_n = 64;  // last n tokens to penalize
     int32_t n_ctx = 512; //context size
+    bool memory_f16 = false; // use f16 instead of f32 for memory kv
 
     // sampling parameters
     int32_t top_k = 40;
@@ -29,12 +30,16 @@ struct gpt_params {
 
     std::string model      = "models/lamma-7B/ggml-model.bin"; // model path
     std::string prompt     = "";
-    std::string antiprompt = ""; // string upon seeing which more user input is prompted
+
+    bool random_prompt = false;
 
     bool use_color = false; // use color to distinguish generations and inputs
 
     bool interactive = false; // interactive mode
+    bool interactive_start = false; // reverse prompt immediately
+    std::vector<std::string> antiprompt; // string upon seeing which more user input is prompted
     bool instruct    = false; // instruction mode (used for Alpaca models)
+    bool ignore_eos = false; // do not stop generating after eos
 };
 
 bool gpt_params_parse(int argc, char ** argv, gpt_params & params);