.devops/tools.sh

@@ -16,7 +16,11 @@ 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
@@ -35,6 +39,8 @@ 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 "  --all-in-one (-a): Execute --convert & --quantize"
+    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 "              ex: \"/models/\" 7B"
 fi

CMakeLists.txt

@@ -218,9 +218,6 @@ 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
@@ -229,9 +226,6 @@ 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
@@ -240,10 +234,6 @@ 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

@@ -36,8 +36,7 @@ fname_out = sys.argv[3]
 
 fout = open(fname_out, "wb")
 
-fout.write(struct.pack("i", 0x67676d66)) # magic: ggmf in hex
-fout.write(struct.pack("i", 1)) # file version
+fout.write(struct.pack("i", 0x67676d6c)) # magic: ggml in hex
 fout.write(struct.pack("i", n_vocab))
 fout.write(struct.pack("i", n_embd))
 fout.write(struct.pack("i", n_mult))
@@ -50,21 +49,27 @@ 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):
-        text = b""
+        # "<s>"/"</s>" tokens
+        fout.write(struct.pack("i", 0))
     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(f"Invalid token: {piece}")
+            print("Invalid token: " + piece)
             sys.exit(1)
         byte_value = int(piece[3:-1], 16)
-        text = struct.pack("B", byte_value)
+        fout.write(struct.pack("i", 1))
+        fout.write(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("f", tokenizer.get_score(i)))
+        fout.write(struct.pack("i", len(text)))
+        fout.write(text)
 
 def write_header(shape, dst_name, ftype_cur):
     sname = dst_name.encode('utf-8')

download-pth.py

@@ -0,0 +1,66 @@
+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

@@ -727,13 +727,11 @@ 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_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));
+                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);
 
             // KQV = transpose(V) * KQ_soft_max
             struct ggml_tensor * KQV = ggml_mul_mat(ctx0, V_trans, KQ_soft_max);

main.cpp

@@ -258,9 +258,6 @@ 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());
@@ -362,16 +359,6 @@ 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);
 
@@ -464,8 +451,12 @@ int main(int argc, char ** argv) {
 
         // end of text token
         if (embd.back() == llama_token_eos()) {
-            fprintf(stderr, " [end of text]\n");
-            break;
+            if (params.interactive) {
+                is_interacting = true;
+            } else {
+                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

@@ -57,7 +57,6 @@ 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(