Add embedding mode with arg flag. Currently working (#282)

* working but ugly

* add arg flag, not working on embedding mode

* typo

* Working! Thanks to @nullhook

* make params argument instead of hardcoded boolean. remove useless time check

* start doing the instructions but not finished. This probably doesnt compile

* Embeddings extraction support

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

.devops/tools.sh

@@ -16,11 +16,7 @@ elif [[ $arg1 == '--quantize' || $arg1 == '-q' ]]; then
     ./quantize $arg2
 elif [[ $arg1 == '--run' || $arg1 == '-r' ]]; then
     ./main $arg2
-elif [[ $arg1 == '--download' || $arg1 == '-d' ]]; then
-    python3 ./download-pth.py $arg2
 elif [[ $arg1 == '--all-in-one' || $arg1 == '-a' ]]; then
-    echo "Downloading model..."
-    python3 ./download-pth.py "$1" "$2"
     echo "Converting PTH to GGML..."
     for i in `ls $1/$2/ggml-model-f16.bin*`; do
         if [ -f "${i/f16/q4_0}" ]; then
@@ -39,8 +35,6 @@ else
     echo "              ex: \"/models/7B/\" 1"
     echo "  --quantize (-q): Optimize with quantization process ggml"
     echo "              ex: \"/models/7B/ggml-model-f16.bin\" \"/models/7B/ggml-model-q4_0.bin\" 2"
-    echo "  --download (-d): Download original llama model from CDN: https://agi.gpt4.org/llama/"
-    echo "              ex: \"/models/\" 7B"
-    echo "  --all-in-one (-a): Execute --download, --convert & --quantize"
+    echo "  --all-in-one (-a): Execute --convert & --quantize"
     echo "              ex: \"/models/\" 7B"
 fi

CMakeLists.txt

@@ -218,6 +218,9 @@ add_library(utils OBJECT
 target_include_directories(utils PUBLIC .)
 target_compile_features(utils PUBLIC cxx_std_11) # don't bump
 target_link_libraries(utils PRIVATE ${LLAMA_EXTRA_LIBS})
+if (BUILD_SHARED_LIBS)
+    set_target_properties(utils PROPERTIES POSITION_INDEPENDENT_CODE ON)
+endif()
 
 add_library(ggml OBJECT
             ggml.c
@@ -226,6 +229,9 @@ add_library(ggml OBJECT
 target_include_directories(ggml PUBLIC .)
 target_compile_features(ggml PUBLIC c_std_11) # don't bump
 target_link_libraries(ggml PRIVATE Threads::Threads ${LLAMA_EXTRA_LIBS})
+if (BUILD_SHARED_LIBS)
+    set_target_properties(ggml PROPERTIES POSITION_INDEPENDENT_CODE ON)
+endif()
 
 add_library(llama
             llama.cpp
@@ -234,6 +240,10 @@ add_library(llama
 target_include_directories(llama PUBLIC .)
 target_compile_features(llama PUBLIC cxx_std_11) # don't bump
 target_link_libraries(llama PRIVATE utils ggml ${LLAMA_EXTRA_LIBS})
+if (BUILD_SHARED_LIBS)
+    set_target_properties(llama PROPERTIES POSITION_INDEPENDENT_CODE ON)
+    target_compile_definitions(llama PRIVATE LLAMA_SHARED LLAMA_BUILD)
+endif()
 
 #
 # Executables

README.md

@@ -7,8 +7,8 @@ Inference of [LLaMA](https://arxiv.org/abs/2302.13971) model in pure C/C++
 
 **Hot topics:**
 
+- [Roadmap (short-term)](https://github.com/ggerganov/llama.cpp/discussions/457)
 - New C-style API is now available: https://github.com/ggerganov/llama.cpp/pull/370
-- [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
 

convert-gptq-to-ggml.py

@@ -36,7 +36,8 @@ fname_out = sys.argv[3]
 
 fout = open(fname_out, "wb")
 
-fout.write(struct.pack("i", 0x67676d6c)) # magic: ggml in hex
+fout.write(struct.pack("i", 0x67676d66)) # magic: ggmf in hex
+fout.write(struct.pack("i", 1)) # file version
 fout.write(struct.pack("i", n_vocab))
 fout.write(struct.pack("i", n_embd))
 fout.write(struct.pack("i", n_mult))
@@ -49,27 +50,21 @@ fout.write(struct.pack("i", 4))
 # This loop unchanged from convert-pth-to-ggml.py:
 for i in range(tokenizer.vocab_size()):
     if tokenizer.is_unknown(i):
-        # "<unk>" token (translated as ??)
         text = " \u2047 ".encode("utf-8")
-        fout.write(struct.pack("i", len(text)))
-        fout.write(text)
     elif tokenizer.is_control(i):
-        # "<s>"/"</s>" tokens
-        fout.write(struct.pack("i", 0))
+        text = b""
     elif tokenizer.is_byte(i):
-        # "<U+XX>" tokens (which may be invalid UTF-8)
         piece = tokenizer.id_to_piece(i)
         if len(piece) != 6:
-            print("Invalid token: " + piece)
+            print(f"Invalid token: {piece}")
             sys.exit(1)
         byte_value = int(piece[3:-1], 16)
-        fout.write(struct.pack("i", 1))
-        fout.write(struct.pack("B", byte_value))
+        text = struct.pack("B", byte_value)
     else:
-        # normal token. Uses U+2581 (LOWER ONE EIGHTH BLOCK) to represent spaces.
         text = tokenizer.id_to_piece(i).replace("\u2581", " ").encode("utf-8")
-        fout.write(struct.pack("i", len(text)))
-        fout.write(text)
+    fout.write(struct.pack("i", len(text)))
+    fout.write(text)
+    fout.write(struct.pack("f", tokenizer.get_score(i)))
 
 def write_header(shape, dst_name, ftype_cur):
     sname = dst_name.encode('utf-8')

download-pth.py

@@ -1,66 +0,0 @@
-import os
-import sys
-from tqdm import tqdm
-import requests
-
-if len(sys.argv) < 3:
-    print("Usage: download-pth.py dir-model model-type\n")
-    print("  model-type: Available models 7B, 13B, 30B or 65B")
-    sys.exit(1)
-
-modelsDir = sys.argv[1]
-model = sys.argv[2]
-
-num = {
-    "7B": 1,
-    "13B": 2,
-    "30B": 4,
-    "65B": 8,
-}
-
-if model not in num:
-    print(f"Error: model {model} is not valid, provide 7B, 13B, 30B or 65B")
-    sys.exit(1)
-
-print(f"Downloading model {model}")
-
-files = ["checklist.chk", "params.json"]
-
-for i in range(num[model]):
-    files.append(f"consolidated.0{i}.pth")
-
-resolved_path = os.path.abspath(os.path.join(modelsDir, model))
-os.makedirs(resolved_path, exist_ok=True)
-
-for file in files:
-    dest_path = os.path.join(resolved_path, file)
-    
-    if os.path.exists(dest_path):
-        print(f"Skip file download, it already exists: {file}")
-        continue
-
-    url = f"https://agi.gpt4.org/llama/LLaMA/{model}/{file}"
-    response = requests.get(url, stream=True)
-    with open(dest_path, 'wb') as f:
-        with tqdm(unit='B', unit_scale=True, miniters=1, desc=file) as t:
-            for chunk in response.iter_content(chunk_size=1024):
-                if chunk:
-                    f.write(chunk)
-                    t.update(len(chunk))
-
-files2 = ["tokenizer_checklist.chk", "tokenizer.model"]
-for file in files2:
-    dest_path = os.path.join(modelsDir, file)
-    
-    if os.path.exists(dest_path):
-        print(f"Skip file download, it already exists: {file}")
-        continue
-    
-    url = f"https://agi.gpt4.org/llama/LLaMA/{file}"
-    response = requests.get(url, stream=True)
-    with open(dest_path, 'wb') as f:
-        with tqdm(unit='B', unit_scale=True, miniters=1, desc=file) as t:
-            for chunk in response.iter_content(chunk_size=1024):
-                if chunk:
-                    f.write(chunk)
-                    t.update(len(chunk))

llama.cpp

@@ -102,6 +102,9 @@ struct llama_context {
     // decode output (2-dimensional array: [n_tokens][n_vocab])
     std::vector<float> logits;
     bool logits_all = false;
+
+    // input embedding (1-dimensional array: [n_embd])
+    std::vector<float> embedding;
 };
 
 struct llama_context_params llama_context_default_params() {
@@ -112,6 +115,7 @@ struct llama_context_params llama_context_default_params() {
         /*.f16_kv     =*/ false,
         /*.logits_all =*/ false,
         /*.vocab_only =*/ false,
+        /*.embedding  =*/ false,
     };
 
     return result;
@@ -592,8 +596,6 @@ static bool llama_model_load(
         fin.close();
     }
 
-    lctx.logits.reserve(lctx.model.hparams.n_ctx);
-
     lctx.t_load_us = ggml_time_us() - t_start_us;
 
     return true;
@@ -727,11 +729,13 @@ static bool llama_eval_internal(
 
             // V_trans = Vmem.view(n_embd/n_head, n_head, n_past + N).permute(1, 2, 0, 3).contiguous()
             struct ggml_tensor * V_trans =
-                ggml_permute(ctx0,
-                        ggml_reshape_3d(ctx0,
-                            ggml_view_1d(ctx0, model.memory_v, (n_past + N)*n_embd, il*n_ctx*ggml_element_size(model.memory_v)*n_embd),
-                            n_embd/n_head, n_head, n_past + N),
-                        1, 2, 0, 3);
+                ggml_cpy(ctx0,
+                    ggml_permute(ctx0,
+                            ggml_reshape_3d(ctx0,
+                                ggml_view_1d(ctx0, model.memory_v, (n_past + N)*n_embd, il*n_ctx*ggml_element_size(model.memory_v)*n_embd),
+                                n_embd/n_head, n_head, n_past + N),
+                            1, 2, 0, 3),
+                    ggml_new_tensor_3d(ctx0, GGML_TYPE_F32, n_past + N, n_embd/n_head, n_head));
 
             // KQV = transpose(V) * KQ_soft_max
             struct ggml_tensor * KQV = ggml_mul_mat(ctx0, V_trans, KQ_soft_max);
@@ -789,6 +793,9 @@ static bool llama_eval_internal(
         inpL = cur;
     }
 
+    // used at the end to optionally extract the embeddings
+    struct ggml_tensor * embeddings = NULL;
+
     // norm
     {
         inpL = ggml_rms_norm(ctx0, inpL);
@@ -797,6 +804,8 @@ static bool llama_eval_internal(
         inpL = ggml_mul(ctx0,
                     ggml_repeat(ctx0, model.norm, inpL),
                     inpL);
+
+        embeddings = inpL;
     }
 
     // lm_head
@@ -819,15 +828,26 @@ static bool llama_eval_internal(
     //embd_w.resize(n_vocab*N);
     //memcpy(embd_w.data(), ggml_get_data(inpL), sizeof(float)*n_vocab*N);
 
-    auto & logits_out = lctx.logits;
+    // extract logits
+    {
+        auto & logits_out = lctx.logits;
 
-    if (lctx.logits_all) {
-        logits_out.resize(n_vocab * N);
-        memcpy(logits_out.data(), (float *) ggml_get_data(inpL), sizeof(float)*n_vocab*N);
-    } else {
-        // return result for just the last token
-        logits_out.resize(n_vocab);
-        memcpy(logits_out.data(), (float *) ggml_get_data(inpL) + (n_vocab*(N-1)), sizeof(float)*n_vocab);
+        if (lctx.logits_all) {
+            logits_out.resize(n_vocab * N);
+            memcpy(logits_out.data(), (float *) ggml_get_data(inpL), sizeof(float)*n_vocab*N);
+        } else {
+            // return result for just the last token
+            logits_out.resize(n_vocab);
+            memcpy(logits_out.data(), (float *) ggml_get_data(inpL) + (n_vocab*(N-1)), sizeof(float)*n_vocab);
+        }
+    }
+
+    // extract embeddings
+    if (lctx.embedding.size()) {
+        auto & embedding_out = lctx.embedding;
+
+        embedding_out.resize(n_embd);
+        memcpy(embedding_out.data(), (float *) ggml_get_data(embeddings) + (n_embd*(N - 1)), sizeof(float)*n_embd);
     }
 
     if (mem_per_token == 0) {
@@ -1414,6 +1434,20 @@ struct llama_context * llama_init_from_file(
         return nullptr;
     }
 
+    // reserve memory for context buffers
+    {
+        const auto & hparams = ctx->model.hparams;
+        if (params.logits_all) {
+            ctx->logits.reserve(hparams.n_ctx*hparams.n_vocab);
+        } else {
+            ctx->logits.reserve(hparams.n_ctx);
+        }
+
+        if (params.embedding){
+            ctx->embedding.reserve(hparams.n_embd);
+        }
+    }
+
     return ctx;
 }
 
@@ -1482,6 +1516,10 @@ float * llama_get_logits(struct llama_context * ctx) {
     return ctx->logits.data();
 }
 
+float * llama_get_embeddings(struct llama_context * ctx) {
+    return ctx->embedding.data();
+}
+
 const char * llama_token_to_str(struct llama_context * ctx, llama_token token) {
     if (token >= llama_n_vocab(ctx)) {
         return nullptr;

llama.h

@@ -53,6 +53,7 @@ extern "C" {
         bool f16_kv;     // use fp16 for KV cache
         bool logits_all; // the llama_eval() call computes all logits, not just the last one
         bool vocab_only; // only load the vocabulary, no weights
+        bool embedding;  // embedding mode only
     };
 
     LLAMA_API struct llama_context_params llama_context_default_params();
@@ -108,6 +109,10 @@ extern "C" {
     // Cols: n_vocab
     LLAMA_API float * llama_get_logits(struct llama_context * ctx);
 
+    // Get the embeddings for the input
+    // shape: [n_embd] (1-dimensional)
+    LLAMA_API float * llama_get_embeddings(struct llama_context * ctx);
+
     // Token Id -> String. Uses the vocabulary in the provided context
     LLAMA_API const char * llama_token_to_str(struct llama_context * ctx, llama_token token);
 

main.cpp

@@ -199,6 +199,7 @@ int main(int argc, char ** argv) {
         lparams.seed       = params.seed;
         lparams.f16_kv     = params.memory_f16;
         lparams.logits_all = params.perplexity;
+        lparams.embedding  = params.embedding;
 
         ctx = llama_init_from_file(params.model.c_str(), lparams);
 
@@ -258,6 +259,9 @@ int main(int argc, char ** argv) {
         params.interactive = true;
     }
 
+    // determine newline token
+    auto llama_token_newline = ::llama_tokenize(ctx, "\n", false);
+
     fprintf(stderr, "\n");
     fprintf(stderr, "%s: prompt: '%s'\n", __func__, params.prompt.c_str());
     fprintf(stderr, "%s: number of tokens in prompt = %zu\n", __func__, embd_inp.size());
@@ -289,6 +293,7 @@ int main(int argc, char ** argv) {
 
     std::vector<llama_token> embd;
 
+
     int last_n_size = params.repeat_last_n;
     std::vector<llama_token> last_n_tokens(last_n_size);
     std::fill(last_n_tokens.begin(), last_n_tokens.end(), 0);
@@ -321,6 +326,27 @@ int main(int argc, char ** argv) {
     // the first thing we will do is to output the prompt, so set color accordingly
     set_console_state(CONSOLE_STATE_PROMPT);
 
+    if (params.embedding){
+        embd = embd_inp;
+
+        if (embd.size() > 0) {
+            if (llama_eval(ctx, embd.data(), embd.size(), n_past, params.n_threads)) {
+                fprintf(stderr, "%s : failed to eval\n", __func__);
+                return 1;
+            }
+        }
+
+        const auto embeddings = llama_get_embeddings(ctx);
+
+        // TODO: print / use the embeddings
+
+        if (params.use_color) {
+            printf(ANSI_COLOR_RESET);
+        }
+
+        return 0;
+    }
+
     while (remaining_tokens > 0 || params.interactive) {
         // predict
         if (embd.size() > 0) {
@@ -359,6 +385,16 @@ int main(int argc, char ** argv) {
                 last_n_tokens.push_back(id);
             }
 
+            // replace end of text token with newline token when in interactive mode
+            if (id == llama_token_eos() && params.interactive) {
+                id = llama_token_newline.front();
+                if (params.antiprompt.size() != 0) {
+                    // tokenize and inject first reverse prompt
+                    const auto first_antiprompt = ::llama_tokenize(ctx, params.antiprompt.front(), false);
+                    embd_inp.insert(embd_inp.end(), first_antiprompt.begin(), first_antiprompt.end());
+                }
+            }
+
             // add it to the context
             embd.push_back(id);
 
@@ -451,12 +487,8 @@ int main(int argc, char ** argv) {
 
         // end of text token
         if (embd.back() == llama_token_eos()) {
-            if (params.interactive) {
-                is_interacting = true;
-            } else {
-                fprintf(stderr, " [end of text]\n");
-                break;
-            }
+            fprintf(stderr, " [end of text]\n");
+            break;
         }
 
         // In interactive mode, respect the maximum number of tokens and drop back to user input when reached.

quantize.py

@@ -57,6 +57,7 @@ def main():
     # )
 
     args = parser.parse_args()
+    args.models_path = os.path.abspath(args.models_path)
 
     if not os.path.isfile(args.quantize_script_path):
         print(

utils.cpp

@@ -117,6 +117,10 @@ bool gpt_params_parse(int argc, char ** argv, gpt_params & params) {
             params.model = argv[i];
         } else if (arg == "-i" || arg == "--interactive") {
             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;
         } else if (arg == "-ins" || arg == "--instruct") {

utils.h

@@ -32,13 +32,17 @@ struct gpt_params {
     std::string model  = "models/lamma-7B/ggml-model.bin"; // model path
     std::string prompt = "";
 
+
     std::vector<std::string> antiprompt; // string upon seeing which more user input is prompted
 
     bool memory_f16        = false; // use f16 instead of f32 for memory kv
     bool random_prompt     = false; // do not randomize prompt if none provided
     bool use_color         = false; // use color to distinguish generations and inputs
     bool interactive       = false; // interactive mode
+
+    bool embedding         = false; // get only sentence embedding
     bool interactive_start = 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
     bool perplexity        = false; // compute perplexity over the prompt