Add link to Roadmap discussion

This reverts commit 4870e455b3.

Will provide the correct fix later

.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 "  --all-in-one (-a): Execute --convert & --quantize"
-    echo "              ex: \"/models/\" 7B"
-    echo "  --all-in-one (-a): Execute --download, --convert & --quantize"
     echo "              ex: \"/models/\" 7B"
 fi

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
 

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

@@ -727,11 +727,13 @@ 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_cpy(ctx0,
-                        ggml_reshape_3d(ctx0,
+                    ggml_permute(ctx0,
-                            ggml_view_1d(ctx0, model.memory_v, (n_past + N)*n_embd, il*n_ctx*ggml_element_size(model.memory_v)*n_embd),
+                            ggml_reshape_3d(ctx0,
-                            n_embd/n_head, n_head, n_past + N),
+                                ggml_view_1d(ctx0, model.memory_v, (n_past + N)*n_embd, il*n_ctx*ggml_element_size(model.memory_v)*n_embd),
-                        1, 2, 0, 3);
+                                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);

main.cpp

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

@@ -57,6 +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(