Merge b3327

b3327

.gitignore

@@ -47,6 +47,7 @@ build*
 !build-info.cpp.in
 !build-info.sh
 !build.zig
+!docs/build.md
 /libllama.so
 /llama-*
 android-ndk-*

common/common.cpp

@@ -190,6 +190,12 @@ int32_t cpu_get_num_math() {
 // CLI argument parsing
 //
 
+void gpt_params_handle_hf_token(gpt_params & params) {
+    if (params.hf_token.empty() && std::getenv("HF_TOKEN")) {
+        params.hf_token = std::getenv("HF_TOKEN");
+    }
+}
+
 void gpt_params_handle_model_default(gpt_params & params) {
     if (!params.hf_repo.empty()) {
         // short-hand to avoid specifying --hf-file -> default it to --model
@@ -237,6 +243,8 @@ bool gpt_params_parse_ex(int argc, char ** argv, gpt_params & params) {
 
     gpt_params_handle_model_default(params);
 
+    gpt_params_handle_hf_token(params);
+
     if (params.escape) {
         string_process_escapes(params.prompt);
         string_process_escapes(params.input_prefix);
@@ -652,6 +660,14 @@ bool gpt_params_find_arg(int argc, char ** argv, const std::string & arg, gpt_pa
         params.model_url = argv[i];
         return true;
     }
+    if (arg == "-hft" || arg == "--hf-token") {
+        if (++i >= argc) {
+          invalid_param = true;
+          return true;
+        }
+        params.hf_token = argv[i];
+        return true;
+    }
     if (arg == "-hfr" || arg == "--hf-repo") {
         CHECK_ARG
         params.hf_repo = argv[i];
@@ -1576,6 +1592,7 @@ void gpt_params_print_usage(int /*argc*/, char ** argv, const gpt_params & param
     options.push_back({ "*",           "-mu,   --model-url MODEL_URL",  "model download url (default: unused)" });
     options.push_back({ "*",           "-hfr,  --hf-repo REPO",         "Hugging Face model repository (default: unused)" });
     options.push_back({ "*",           "-hff,  --hf-file FILE",         "Hugging Face model file (default: unused)" });
+    options.push_back({ "*",           "-hft,  --hf-token TOKEN",       "Hugging Face access token (default: value from HF_TOKEN environment variable)" });
 
     options.push_back({ "retrieval" });
     options.push_back({ "retrieval",   "       --context-file FNAME",   "file to load context from (repeat to specify multiple files)" });
@@ -2015,9 +2032,9 @@ std::tuple<struct llama_model *, struct llama_context *> llama_init_from_gpt_par
     llama_model * model = nullptr;
 
     if (!params.hf_repo.empty() && !params.hf_file.empty()) {
-        model = llama_load_model_from_hf(params.hf_repo.c_str(), params.hf_file.c_str(), params.model.c_str(), mparams);
+        model = llama_load_model_from_hf(params.hf_repo.c_str(), params.hf_file.c_str(), params.model.c_str(), params.hf_token.c_str(), mparams);
     } else if (!params.model_url.empty()) {
-        model = llama_load_model_from_url(params.model_url.c_str(), params.model.c_str(), mparams);
+        model = llama_load_model_from_url(params.model_url.c_str(), params.model.c_str(), params.hf_token.c_str(), mparams);
     } else {
         model = llama_load_model_from_file(params.model.c_str(), mparams);
     }
@@ -2205,7 +2222,7 @@ static bool starts_with(const std::string & str, const std::string & prefix) {
     return str.rfind(prefix, 0) == 0;
 }
 
-static bool llama_download_file(const std::string & url, const std::string & path) {
+static bool llama_download_file(const std::string & url, const std::string & path, const std::string & hf_token) {
 
     // Initialize libcurl
     std::unique_ptr<CURL, decltype(&curl_easy_cleanup)> curl(curl_easy_init(), &curl_easy_cleanup);
@@ -2220,6 +2237,15 @@ static bool llama_download_file(const std::string & url, const std::string & pat
     curl_easy_setopt(curl.get(), CURLOPT_URL, url.c_str());
     curl_easy_setopt(curl.get(), CURLOPT_FOLLOWLOCATION, 1L);
 
+    // Check if hf-token or bearer-token was specified
+    if (!hf_token.empty()) {
+      std::string auth_header = "Authorization: Bearer ";
+      auth_header += hf_token.c_str();
+      struct curl_slist *http_headers = NULL;
+      http_headers = curl_slist_append(http_headers, auth_header.c_str());
+      curl_easy_setopt(curl.get(), CURLOPT_HTTPHEADER, http_headers);
+    }
+
 #if defined(_WIN32)
     // CURLSSLOPT_NATIVE_CA tells libcurl to use standard certificate store of
     //   operating system. Currently implemented under MS-Windows.
@@ -2415,14 +2441,15 @@ static bool llama_download_file(const std::string & url, const std::string & pat
 struct llama_model * llama_load_model_from_url(
         const char * model_url,
         const char * path_model,
+        const char * hf_token,
         const struct llama_model_params & params) {
     // Basic validation of the model_url
     if (!model_url || strlen(model_url) == 0) {
         fprintf(stderr, "%s: invalid model_url\n", __func__);
         return NULL;
     }
 
-    if (!llama_download_file(model_url, path_model)) {
+    if (!llama_download_file(model_url, path_model, hf_token)) {
         return NULL;
     }
 
@@ -2470,14 +2497,14 @@ struct llama_model * llama_load_model_from_url(
         // Prepare download in parallel
         std::vector<std::future<bool>> futures_download;
         for (int idx = 1; idx < n_split; idx++) {
-            futures_download.push_back(std::async(std::launch::async, [&split_prefix, &split_url_prefix, &n_split](int download_idx) -> bool {
+            futures_download.push_back(std::async(std::launch::async, [&split_prefix, &split_url_prefix, &n_split, hf_token](int download_idx) -> bool {
                 char split_path[PATH_MAX] = {0};
                 llama_split_path(split_path, sizeof(split_path), split_prefix, download_idx, n_split);
 
                 char split_url[LLAMA_CURL_MAX_URL_LENGTH] = {0};
                 llama_split_path(split_url, sizeof(split_url), split_url_prefix, download_idx, n_split);
 
-                return llama_download_file(split_url, split_path);
+                return llama_download_file(split_url, split_path, hf_token);
             }, idx));
         }
 
@@ -2496,6 +2523,7 @@ struct llama_model * llama_load_model_from_hf(
         const char * repo,
         const char * model,
         const char * path_model,
+        const char * hf_token,
         const struct llama_model_params & params) {
     // construct hugging face model url:
     //
@@ -2511,14 +2539,15 @@ struct llama_model * llama_load_model_from_hf(
     model_url += "/resolve/main/";
     model_url += model;
 
-    return llama_load_model_from_url(model_url.c_str(), path_model, params);
+    return llama_load_model_from_url(model_url.c_str(), path_model, hf_token, params);
 }
 
 #else
 
 struct llama_model * llama_load_model_from_url(
         const char * /*model_url*/,
         const char * /*path_model*/,
+        const char * /*hf_token*/,
         const struct llama_model_params & /*params*/) {
     fprintf(stderr, "%s: llama.cpp built without libcurl, downloading from an url not supported.\n", __func__);
     return nullptr;
@@ -2528,6 +2557,7 @@ struct llama_model * llama_load_model_from_hf(
         const char * /*repo*/,
         const char * /*model*/,
         const char * /*path_model*/,
+        const char * /*hf_token*/,
         const struct llama_model_params & /*params*/) {
     fprintf(stderr, "%s: llama.cpp built without libcurl, downloading from Hugging Face not supported.\n", __func__);
     return nullptr;
@@ -2592,51 +2622,35 @@ std::vector<llama_token> llama_tokenize(
 }
 
 std::string llama_token_to_piece(const struct llama_context * ctx, llama_token token, bool special) {
-    std::vector<char> result(8, 0);
-    const int n_tokens = llama_token_to_piece(llama_get_model(ctx), token, result.data(), result.size(), special);
-    if (n_tokens < 0) {
-        result.resize(-n_tokens);
-        int check = llama_token_to_piece(llama_get_model(ctx), token, result.data(), result.size(), special);
-        GGML_ASSERT(check == -n_tokens);
-    } else {
-        result.resize(n_tokens);
-    }
-
-    return std::string(result.data(), result.size());
-}
-
-std::string llama_detokenize_spm(llama_context * ctx, const std::vector<llama_token> & tokens) {
-    const llama_token bos_id = llama_token_bos(llama_get_model(ctx));
-
     std::string piece;
-    std::string result;
-
-    for (size_t i = 0; i < tokens.size(); ++i) {
-        piece = llama_token_to_piece(ctx, tokens[i]);
-
-        // remove the leading space of the first non-BOS token
-        if (((tokens[0] == bos_id && i == 1) || (tokens[0] != bos_id && i == 0)) && piece[0] == ' ') {
-            piece = piece.substr(1);
-        }
-
-        result += piece;
+    piece.resize(piece.capacity());  // using string internal cache, 15 bytes + '\n'
+    const int n_chars = llama_token_to_piece(llama_get_model(ctx), token, &piece[0], piece.size(), 0, special);
+    if (n_chars < 0) {
+        piece.resize(-n_chars);
+        int check = llama_token_to_piece(llama_get_model(ctx), token, &piece[0], piece.size(), 0, special);
+        GGML_ASSERT(check == -n_chars);
+    }
+    else {
+        piece.resize(n_chars);
     }
 
-    return result;
+    return piece;
 }
 
-std::string llama_detokenize_bpe(llama_context * ctx, const std::vector<llama_token> & tokens) {
-    std::string piece;
-    std::string result;
-
-    for (size_t i = 0; i < tokens.size(); ++i) {
-        piece = llama_token_to_piece(ctx, tokens[i]);
-
-        result += piece;
+std::string llama_detokenize(llama_context * ctx, const std::vector<llama_token> & tokens, bool special) {
+    std::string text;
+    text.resize(std::max(text.capacity(), tokens.size()));
+    int32_t n_chars = llama_detokenize(llama_get_model(ctx), tokens.data(), (int32_t)tokens.size(), &text[0], (int32_t)text.size(), false, special);
+    if (n_chars < 0) {
+        text.resize(-n_chars);
+        n_chars = llama_detokenize(llama_get_model(ctx), tokens.data(), (int32_t)tokens.size(), &text[0], (int32_t)text.size(), false, special);
+        GGML_ASSERT(n_chars <= (int32_t)text.size());  // whitespace trimming is performed after per-token detokenization
     }
 
+    text.resize(n_chars);
+
     // NOTE: the original tokenizer decodes bytes after collecting the pieces.
-    return result;
+    return text;
 }
 
 bool llama_should_add_bos_token(const llama_model * model) {

common/common.h

@@ -108,6 +108,7 @@ struct gpt_params {
     std::string model_draft          = ""; // draft model for speculative decoding
     std::string model_alias          = "unknown"; // model alias
     std::string model_url            = ""; // model url to download
+    std::string hf_token             = ""; // HF token
     std::string hf_repo              = ""; // HF repo
     std::string hf_file              = ""; // HF file
     std::string prompt               = "";
@@ -256,6 +257,7 @@ struct gpt_params {
     bool spm_infill = false; // suffix/prefix/middle pattern for infill
 };
 
+void gpt_params_handle_hf_token(gpt_params & params);
 void gpt_params_handle_model_default(gpt_params & params);
 
 bool gpt_params_parse_ex   (int argc, char ** argv, gpt_params & params);
@@ -311,8 +313,8 @@ std::tuple<struct llama_model *, struct llama_context *> llama_init_from_gpt_par
 struct llama_model_params   llama_model_params_from_gpt_params  (const gpt_params & params);
 struct llama_context_params llama_context_params_from_gpt_params(const gpt_params & params);
 
-struct llama_model * llama_load_model_from_url(const char * model_url, const char * path_model, const struct llama_model_params & params);
-struct llama_model * llama_load_model_from_hf(const char * repo, const char * file, const char * path_model, const struct llama_model_params & params);
+struct llama_model * llama_load_model_from_url(const char * model_url, const char * path_model, const char * hf_token, const struct llama_model_params & params);
+struct llama_model * llama_load_model_from_hf(const char * repo, const char * file, const char * path_model, const char * hf_token, const struct llama_model_params & params);
 
 // Batch utils
 
@@ -350,21 +352,13 @@ std::string llama_token_to_piece(
                        llama_token   token,
                        bool          special = true);
 
-// TODO: these should be moved in llama.h C-style API under single `llama_detokenize` function
-//       that takes into account the tokenizer type and decides how to handle the leading space
-//
-// detokenizes a vector of tokens into a string
-// should work similar to Python's `tokenizer.decode`
-// removes the leading space from the first non-BOS token
-std::string llama_detokenize_spm(
-                         llama_context * ctx,
-        const std::vector<llama_token> & tokens);
-
 // detokenizes a vector of tokens into a string
 // should work similar to Python's `tokenizer.decode`
-std::string llama_detokenize_bpe(
+// optionally renders special/control tokens
+std::string llama_detokenize(
                          llama_context * ctx,
-        const std::vector<llama_token> & tokens);
+        const std::vector<llama_token> & tokens,
+                                  bool   special = true);
 
 // Uses the value from the model metadata if possible, otherwise
 // defaults to true when model type is SPM, otherwise false.

docs/android.md

@@ -0,0 +1,56 @@
+
+# Android
+
+## Build on Android using Termux
+[Termux](https://github.com/termux/termux-app#installation) is a method to execute `llama.cpp` on an Android device (no root required).
+```
+apt update && apt upgrade -y
+apt install git make cmake
+```
+
+It's recommended to move your model inside the `~/` directory for best performance:
+```
+cd storage/downloads
+mv model.gguf ~/
+```
+
+[Get the code](https://github.com/ggerganov/llama.cpp#get-the-code) & [follow the Linux build instructions](https://github.com/ggerganov/llama.cpp#build) to build `llama.cpp`.
+
+## Building the Project using Android NDK
+Obtain the [Android NDK](https://developer.android.com/ndk) and then build with CMake.
+
+Execute the following commands on your computer to avoid downloading the NDK to your mobile. Alternatively, you can also do this in Termux:
+```
+$ mkdir build-android
+$ cd build-android
+$ export NDK=<your_ndk_directory>
+$ cmake -DCMAKE_TOOLCHAIN_FILE=$NDK/build/cmake/android.toolchain.cmake -DANDROID_ABI=arm64-v8a -DANDROID_PLATFORM=android-23 -DCMAKE_C_FLAGS=-march=armv8.4a+dotprod ..
+$ make
+```
+
+Install [termux](https://github.com/termux/termux-app#installation) on your device and run `termux-setup-storage` to get access to your SD card (if Android 11+ then run the command twice).
+
+Finally, copy these built `llama` binaries and the model file to your device storage. Because the file permissions in the Android sdcard cannot be changed, you can copy the executable files to the `/data/data/com.termux/files/home/bin` path, and then execute the following commands in Termux to add executable permission:
+
+(Assumed that you have pushed the built executable files to the /sdcard/llama.cpp/bin path using `adb push`)
+```
+$cp -r /sdcard/llama.cpp/bin /data/data/com.termux/files/home/
+$cd /data/data/com.termux/files/home/bin
+$chmod +x ./*
+```
+
+Download model [llama-2-7b-chat.Q4_K_M.gguf](https://huggingface.co/TheBloke/Llama-2-7B-Chat-GGUF/blob/main/llama-2-7b-chat.Q4_K_M.gguf), and push it to `/sdcard/llama.cpp/`, then move it to `/data/data/com.termux/files/home/model/`
+
+```
+$mv /sdcard/llama.cpp/llama-2-7b-chat.Q4_K_M.gguf /data/data/com.termux/files/home/model/
+```
+
+Now, you can start chatting:
+```
+$cd /data/data/com.termux/files/home/bin
+$./llama-cli -m ../model/llama-2-7b-chat.Q4_K_M.gguf -n 128 -cml
+```
+
+Here's a demo of an interactive session running on Pixel 5 phone:
+
+https://user-images.githubusercontent.com/271616/225014776-1d567049-ad71-4ef2-b050-55b0b3b9274c.mp4