(Windows) Set console to UTF-8 on init (#420)

Sets console codepage to 65001 (CP_UTF8) on start for both input and output, should fix problems with UTF-8 characters.

README.md

@@ -179,7 +179,10 @@ Here is an example few-shot interaction, invoked with the command
 
 ```bash
 # default arguments using 7B model
-./chat.sh
+./examples/chat.sh
+
+# advanced chat with 13B model
+./examples/chat-13B.sh
 
 # custom arguments using 13B model
 ./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
@@ -195,7 +198,7 @@ Note the use of `--color` to distinguish between user input and generated text.
 2. Run the `main` tool like this:
 
 ```
-./main -m ./models/ggml-alpaca-7b-q4.bin --color -f ./prompts/alpaca.txt -ins
+./examples/alpaca.sh
 ```
 
 Sample run:

chat.sh

@@ -1,6 +0,0 @@
-#!/bin/bash
-#
-# Temporary script - will be removed in the future
-#
-
-./main -m ./models/7B/ggml-model-q4_0.bin -b 128 -n 256 --repeat_penalty 1.0 --color -i -r "User:" -f prompts/chat-with-bob.txt

examples/alpaca.sh

@@ -1,6 +1,10 @@
 #!/bin/bash
+
 #
 # Temporary script - will be removed in the future
 #
 
+cd `dirname $0`
+cd ..
+
 ./main -m ./models/ggml-alpaca-7b-q4.bin --color -f ./prompts/alpaca.txt -ins -b 256 --top_k 10000 --temp 0.2 --repeat_penalty 1 -t 7

examples/chat.sh

@@ -0,0 +1,16 @@
+#!/bin/bash
+
+#
+# Temporary script - will be removed in the future
+#
+
+cd `dirname $0`
+cd ..
+
+# Important:
+#
+#   "--keep 48" is based on the contents of prompts/chat-with-bob.txt
+#
+./main -m ./models/7B/ggml-model-q4_0.bin -c 512 -b 1024 -n 256 --keep 48 \
+    --repeat_penalty 1.0 --color -i \
+    -r "User:" -f prompts/chat-with-bob.txt

examples/common.cpp

@@ -112,6 +112,12 @@ bool gpt_params_parse(int argc, char ** argv, gpt_params & params) {
             }
             params.n_batch = std::stoi(argv[i]);
             params.n_batch = std::min(512, params.n_batch);
+        } else if (arg == "--keep") {
+            if (++i >= argc) {
+                invalid_param = true;
+                break;
+            }
+            params.n_keep = std::stoi(argv[i]);
         } else if (arg == "-m" || arg == "--model") {
             if (++i >= argc) {
                 invalid_param = true;
@@ -134,7 +140,7 @@ bool gpt_params_parse(int argc, char ** argv, gpt_params & params) {
             params.use_mlock = true;
         } else if (arg == "--mtest") {
             params.mem_test = true;
-        } else if (arg == "--verbose_prompt") {
+        } else if (arg == "--verbose-prompt") {
             params.verbose_prompt = true;
         } else if (arg == "-r" || arg == "--reverse-prompt") {
             if (++i >= argc) {
@@ -198,7 +204,7 @@ void gpt_print_usage(int /*argc*/, char ** argv, const gpt_params & params) {
     fprintf(stderr, "  --in-prefix STRING    string to prefix user inputs with (default: empty)\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);
+    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, "  --repeat_last_n N     last n tokens to consider for penalize (default: %d)\n", params.repeat_last_n);
@@ -210,6 +216,7 @@ void gpt_print_usage(int /*argc*/, char ** argv, const gpt_params & params) {
     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");
+    fprintf(stderr, "  --keep                number of tokens to keep from the initial prompt\n");
     if (ggml_mlock_supported()) {
         fprintf(stderr, "  --mlock               force system to keep model in RAM rather than swapping or compressing\n");
     }

examples/common.h

@@ -21,6 +21,7 @@ struct gpt_params {
     int32_t n_parts       = -1;   // amount of model parts (-1 = determine from model dimensions)
     int32_t n_ctx         = 512;  // context size
     int32_t n_batch       = 8;    // batch size for prompt processing
+    int32_t n_keep        = 0;    // number of tokens to keep from initial prompt
 
     // sampling parameters
     int32_t top_k = 40;

examples/embedding/embedding.cpp

@@ -1,15 +1,6 @@
 #include "common.h"
 #include "llama.h"
 
-#include <cassert>
-#include <cinttypes>
-#include <cmath>
-#include <cstdio>
-#include <cstring>
-#include <fstream>
-#include <string>
-#include <vector>
-
 int main(int argc, char ** argv) {
     gpt_params params;
     params.model = "models/llama-7B/ggml-model.bin";
@@ -94,9 +85,13 @@ int main(int argc, char ** argv) {
             }
         }
 
+        const int n_embd = llama_n_embd(ctx);
         const auto embeddings = llama_get_embeddings(ctx);
 
-        // TODO: print / use the embeddings
+        for (int i = 0; i < n_embd; i++) {
+            printf("%f ", embeddings[i]);
+        }
+        printf("\n");
     }
 
     llama_print_timings(ctx);

examples/main/main.cpp

@@ -23,6 +23,8 @@
 extern "C" __declspec(dllimport) void* __stdcall GetStdHandle(unsigned long nStdHandle);
 extern "C" __declspec(dllimport) int __stdcall GetConsoleMode(void* hConsoleHandle, unsigned long* lpMode);
 extern "C" __declspec(dllimport) int __stdcall SetConsoleMode(void* hConsoleHandle, unsigned long dwMode);
+extern "C" __declspec(dllimport) int __stdcall SetConsoleCP(unsigned int wCodePageID);
+extern "C" __declspec(dllimport) int __stdcall SetConsoleOutputCP(unsigned int wCodePageID);
 #endif
 
 #define ANSI_COLOR_RED     "\x1b[31m"
@@ -44,8 +46,7 @@ enum console_state {
 static console_state con_st = CONSOLE_STATE_DEFAULT;
 static bool con_use_color = false;
 
-void set_console_state(console_state new_st)
-{
+void set_console_state(console_state new_st) {
     if (!con_use_color) return;
     // only emit color code if state changed
     if (new_st != con_st) {
@@ -80,6 +81,32 @@ void sigint_handler(int signo) {
 }
 #endif
 
+#if defined (_WIN32)
+void win32_console_init(void) {
+    unsigned long dwMode = 0;
+    void* hConOut = GetStdHandle((unsigned long)-11); // STD_OUTPUT_HANDLE (-11)
+    if (!hConOut || hConOut == (void*)-1 || !GetConsoleMode(hConOut, &dwMode)) {
+        hConOut = GetStdHandle((unsigned long)-12); // STD_ERROR_HANDLE (-12)
+        if (hConOut && (hConOut == (void*)-1 || !GetConsoleMode(hConOut, &dwMode))) {
+            hConOut = 0;
+        }
+    }
+    if (hConOut) {
+        // Enable ANSI colors on Windows 10+
+        if (con_use_color && !(dwMode & 0x4)) {
+            SetConsoleMode(hConOut, dwMode | 0x4); // ENABLE_VIRTUAL_TERMINAL_PROCESSING (0x4)
+        }
+        // Set console output codepage to UTF8
+        SetConsoleOutputCP(65001); // CP_UTF8
+    }
+    void* hConIn = GetStdHandle((unsigned long)-10); // STD_INPUT_HANDLE (-10)
+    if (hConIn && hConIn != (void*)-1 && GetConsoleMode(hConIn, &dwMode)) {
+        // Set console input codepage to UTF8
+        SetConsoleCP(65001); // CP_UTF8
+    }
+}
+#endif
+
 int main(int argc, char ** argv) {
     gpt_params params;
     params.model = "models/llama-7B/ggml-model.bin";
@@ -88,6 +115,15 @@ int main(int argc, char ** argv) {
         return 1;
     }
 
+
+    // save choice to use color for later
+    // (note for later: this is a slightly awkward choice)
+    con_use_color = params.use_color;
+
+#if defined (_WIN32)
+    win32_console_init();
+#endif
+
     if (params.perplexity) {
         printf("\n************\n");
         printf("%s: please use the 'perplexity' tool for perplexity calculations\n", __func__);
@@ -96,6 +132,14 @@ int main(int argc, char ** argv) {
         return 0;
     }
 
+    if (params.embedding) {
+        printf("\n************\n");
+        printf("%s: please use the 'embedding' tool for embedding calculations\n", __func__);
+        printf("************\n\n");
+
+        return 0;
+    }
+
     if (params.n_ctx > 2048) {
         fprintf(stderr, "%s: warning: model does not support context sizes greater than 2048 tokens (%d specified);"
                 "expect poor results\n", __func__, params.n_ctx);
@@ -112,10 +156,6 @@ int main(int argc, char ** argv) {
         params.prompt = gpt_random_prompt(rng);
     }
 
-    // save choice to use color for later
-    // (note for later: this is a slightly awkward choice)
-    con_use_color = params.use_color;
-
 //    params.prompt = R"(// this function checks if the number n is prime
 //bool is_prime(int n) {)";
 
@@ -165,8 +205,6 @@ int main(int argc, char ** argv) {
         return 0;
     }
 
-    int n_past = 0;
-
     // Add a space in front of the first character to match OG llama tokenizer behavior
     params.prompt.insert(0, 1, ' ');
 
@@ -175,7 +213,12 @@ int main(int argc, char ** argv) {
 
     const int n_ctx = llama_n_ctx(ctx);
 
-    params.n_predict = std::min(params.n_predict, n_ctx - (int) embd_inp.size());
+    if ((int) embd_inp.size() > n_ctx - 4) {
+        fprintf(stderr, "%s: error: prompt is too long (%d tokens, max %d)\n", __func__, (int) embd_inp.size(), n_ctx - 4);
+        return 1;
+    }
+
+    params.n_keep    = std::min(params.n_keep,    (int) embd_inp.size());
 
     // prefix & suffix for instruct mode
     const auto inp_pfx = ::llama_tokenize(ctx, "\n\n### Instruction:\n\n", true);
@@ -206,6 +249,13 @@ int main(int argc, char ** argv) {
         for (int i = 0; i < (int) embd_inp.size(); i++) {
             fprintf(stderr, "%6d -> '%s'\n", embd_inp[i], llama_token_to_str(ctx, embd_inp[i]));
         }
+        if (params.n_keep > 0) {
+        fprintf(stderr, "%s: static prompt based on n_keep: '", __func__);
+            for (int i = 0; i < params.n_keep; i++) {
+                fprintf(stderr, "%s", llama_token_to_str(ctx, embd_inp[i]));
+            }
+            fprintf(stderr, "'\n");
+        }
         fprintf(stderr, "\n");
     }
 
@@ -222,7 +272,7 @@ int main(int argc, char ** argv) {
 
         fprintf(stderr, "%s: interactive mode on.\n", __func__);
 
-        if(params.antiprompt.size()) {
+        if (params.antiprompt.size()) {
             for (auto antiprompt : params.antiprompt) {
                 fprintf(stderr, "Reverse prompt: '%s'\n", antiprompt.c_str());
             }
@@ -232,14 +282,12 @@ int main(int argc, char ** argv) {
             fprintf(stderr, "Input prefix: '%s'\n", params.input_prefix.c_str());
         }
     }
-    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);
+    fprintf(stderr, "sampling: 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);
+    fprintf(stderr, "generate: n_ctx = %d, n_batch = %d, n_predict = %d, n_keep = %d\n", n_ctx, params.n_batch, params.n_predict, params.n_keep);
     fprintf(stderr, "\n\n");
 
-    std::vector<llama_token> embd;
-
-
-    int last_n_size = params.repeat_last_n;
-    std::vector<llama_token> last_n_tokens(last_n_size);
+    // TODO: replace with ring-buffer
+    std::vector<llama_token> last_n_tokens(n_ctx);
     std::fill(last_n_tokens.begin(), last_n_tokens.end(), 0);
 
     if (params.interactive) {
@@ -252,27 +300,41 @@ int main(int argc, char ** argv) {
         is_interacting = params.interactive_start || params.instruct;
     }
 
-    int input_consumed = 0;
     bool input_noecho = false;
 
-    int remaining_tokens = params.n_predict;
+    int n_past     = 0;
+    int n_remain   = params.n_predict;
+    int n_consumed = 0;
 
-#if defined (_WIN32)
-  if (params.use_color) {
-        // Enable ANSI colors on Windows 10+
-        unsigned long dwMode = 0;
-        void* hConOut = GetStdHandle((unsigned long)-11); // STD_OUTPUT_HANDLE (-11)
-        if (hConOut && hConOut != (void*)-1 && GetConsoleMode(hConOut, &dwMode) && !(dwMode & 0x4)) {
-            SetConsoleMode(hConOut, dwMode | 0x4); // ENABLE_VIRTUAL_TERMINAL_PROCESSING (0x4)
-        }
-    }
-#endif
     // the first thing we will do is to output the prompt, so set color accordingly
     set_console_state(CONSOLE_STATE_PROMPT);
 
-    while (remaining_tokens > 0 || params.interactive) {
+    std::vector<llama_token> embd;
+
+    while (n_remain != 0 || params.interactive) {
         // predict
         if (embd.size() > 0) {
+            // infinite text generation via context swapping
+            // if we run out of context:
+            // - take the n_keep first tokens from the original prompt (via n_past)
+            // - take half of the last (n_ctx - n_keep) tokens and recompute the logits in a batch
+            if (n_past + (int) embd.size() > n_ctx) {
+                const int n_left = n_past - params.n_keep;
+
+                n_past = params.n_keep;
+
+                // insert n_left/2 tokens at the start of embd from last_n_tokens
+                embd.insert(embd.begin(), last_n_tokens.begin() + n_ctx - n_left/2 - embd.size(), last_n_tokens.end() - embd.size());
+
+                //printf("\n---\n");
+                //printf("resetting: '");
+                //for (int i = 0; i < (int) embd.size(); i++) {
+                //    printf("%s", llama_token_to_str(ctx, embd[i]));
+                //}
+                //printf("'\n");
+                //printf("\n---\n");
+            }
+
             if (llama_eval(ctx, embd.data(), embd.size(), n_past, params.n_threads)) {
                 fprintf(stderr, "%s : failed to eval\n", __func__);
                 return 1;
@@ -282,7 +344,7 @@ int main(int argc, char ** argv) {
         n_past += embd.size();
         embd.clear();
 
-        if ((int) embd_inp.size() <= input_consumed && !is_interacting) {
+        if ((int) embd_inp.size() <= n_consumed && !is_interacting) {
             // out of user input, sample next token
             const float top_k          = params.top_k;
             const float top_p          = params.top_p;
@@ -298,7 +360,9 @@ int main(int argc, char ** argv) {
                     logits[llama_token_eos()] = 0;
                 }
 
-                id = llama_sample_top_p_top_k(ctx, last_n_tokens.data(), last_n_tokens.size(), top_k, top_p, temp, repeat_penalty);
+                id = llama_sample_top_p_top_k(ctx,
+                        last_n_tokens.data() + n_ctx - params.repeat_last_n,
+                        params.repeat_last_n, top_k, top_p, temp, repeat_penalty);
 
                 last_n_tokens.erase(last_n_tokens.begin());
                 last_n_tokens.push_back(id);
@@ -321,14 +385,14 @@ int main(int argc, char ** argv) {
             input_noecho = false;
 
             // decrement remaining sampling budget
-            --remaining_tokens;
+            --n_remain;
         } else {
             // some user input remains from prompt or interaction, forward it to processing
-            while ((int) embd_inp.size() > input_consumed) {
-                embd.push_back(embd_inp[input_consumed]);
+            while ((int) embd_inp.size() > n_consumed) {
+                embd.push_back(embd_inp[n_consumed]);
                 last_n_tokens.erase(last_n_tokens.begin());
-                last_n_tokens.push_back(embd_inp[input_consumed]);
-                ++input_consumed;
+                last_n_tokens.push_back(embd_inp[n_consumed]);
+                ++n_consumed;
                 if ((int) embd.size() >= params.n_batch) {
                     break;
                 }
@@ -343,13 +407,13 @@ int main(int argc, char ** argv) {
             fflush(stdout);
         }
         // reset color to default if we there is no pending user input
-        if (!input_noecho && (int)embd_inp.size() == input_consumed) {
+        if (!input_noecho && (int)embd_inp.size() == n_consumed) {
             set_console_state(CONSOLE_STATE_DEFAULT);
         }
 
         // in interactive mode, and not currently processing queued inputs;
         // check if we should prompt the user for more
-        if (params.interactive && (int) embd_inp.size() <= input_consumed) {
+        if (params.interactive && (int) embd_inp.size() <= n_consumed) {
             // check for reverse prompt
             std::string last_output;
             for (auto id : last_n_tokens) {
@@ -371,7 +435,7 @@ int main(int argc, char ** argv) {
                 set_console_state(CONSOLE_STATE_USER_INPUT);
 
                 if (params.instruct) {
-                    input_consumed = embd_inp.size();
+                    n_consumed = embd_inp.size();
                     embd_inp.insert(embd_inp.end(), inp_pfx.begin(), inp_pfx.end());
 
                     printf("\n> ");
@@ -405,7 +469,7 @@ int main(int argc, char ** argv) {
                     embd_inp.insert(embd_inp.end(), inp_sfx.begin(), inp_sfx.end());
                 }
 
-                remaining_tokens -= line_inp.size();
+                n_remain -= line_inp.size();
 
                 input_noecho = true; // do not echo this again
             }
@@ -426,8 +490,8 @@ int main(int argc, char ** argv) {
         }
 
         // 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;
+        if (params.interactive && n_remain <= 0) {
+            n_remain = params.n_predict;
             is_interacting = true;
         }
     }

examples/perplexity/perplexity.cpp

@@ -1,14 +1,6 @@
 #include "common.h"
 #include "llama.h"
 
-#include <cassert>
-#include <cinttypes>
-#include <cmath>
-#include <cstdio>
-#include <cstring>
-#include <string>
-#include <vector>
-
 std::vector<double> softmax(const std::vector<float>& logits) {
     std::vector<double> probs(logits.size());
     float max_logit = logits[0];

llama.cpp

@@ -1261,10 +1261,10 @@ static llama_vocab::id llama_sample_top_p_top_k(
         double repeat_penalty) {
     auto & rng = lctx.rng;
 
-    const auto & vocab = lctx.vocab;
-    const auto & logits = lctx.logits;
+    const int n_logits = lctx.model.hparams.n_vocab;
 
-    int n_logits = vocab.id_to_token.size();
+    const auto & logits = lctx.logits;
+    const auto * plogits = logits.data() + logits.size() - n_logits;
 
     std::vector<std::pair<double, llama_vocab::id>> logits_id;
     logits_id.reserve(n_logits);
@@ -1276,13 +1276,13 @@ static llama_vocab::id llama_sample_top_p_top_k(
             // credit https://github.com/facebookresearch/llama/compare/main...shawwn:llama:main
             if (std::find(last_n_tokens.begin(), last_n_tokens.end(), i) != last_n_tokens.end()) {
                 // if score < 0 then repetition penalty has to multiplied to reduce the previous token probability
-                if (logits[i] < 0.0) {
-                    logits_id.push_back(std::make_pair(logits[i]*scale*repeat_penalty, i));
+                if (plogits[i] < 0.0) {
+                    logits_id.push_back(std::make_pair(plogits[i]*scale*repeat_penalty, i));
                 } else {
-                    logits_id.push_back(std::make_pair(logits[i]*scale/repeat_penalty, i));
+                    logits_id.push_back(std::make_pair(plogits[i]*scale/repeat_penalty, i));
                 }
             } else {
-                logits_id.push_back(std::make_pair(logits[i]*scale, i));
+                logits_id.push_back(std::make_pair(plogits[i]*scale, i));
             }
         }
     }
@@ -1677,6 +1677,8 @@ struct llama_context * llama_init_from_file(
         }
 
         const auto & hparams = ctx->model.hparams;
+
+        // resized during inference
         if (params.logits_all) {
             ctx->logits.reserve(hparams.n_ctx*hparams.n_vocab);
         } else {
@@ -1684,7 +1686,7 @@ struct llama_context * llama_init_from_file(
         }
 
         if (params.embedding){
-            ctx->embedding.reserve(hparams.n_embd);
+            ctx->embedding.resize(hparams.n_embd);
         }
 
         ctx->buf_compute.resize(MEM_REQ_EVAL.at(ctx->model.type));
@@ -1761,6 +1763,10 @@ int llama_n_ctx(struct llama_context * ctx) {
     return ctx->model.hparams.n_ctx;
 }
 
+int llama_n_embd(struct llama_context * ctx) {
+    return ctx->model.hparams.n_embd;
+}
+
 float * llama_get_logits(struct llama_context * ctx) {
     return ctx->logits.data();
 }

llama.h

@@ -109,6 +109,7 @@ extern "C" {
 
     LLAMA_API int llama_n_vocab(struct llama_context * ctx);
     LLAMA_API int llama_n_ctx  (struct llama_context * ctx);
+    LLAMA_API int llama_n_embd (struct llama_context * ctx);
 
     // Token logits obtained from the last call to llama_eval()
     // The logits for the last token are stored in the last row