Update workspace & configuration for personal use

Author: mattgauf

.gitignore

@@ -3,6 +3,7 @@
 .cache/
 .vs/
 .vscode/
+.venv
 .DS_Store
 
 .build/

convert-pth-to-ggml.py

@@ -1,3 +1,4 @@
+#!/usr/bin/env python3
 # Convert a LLaMA model checkpoint to a ggjt compatible file
 #
 # Load the model using Torch

download-pth.py

@@ -0,0 +1,67 @@
+#!/usr/bin/env python3
+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))

examples/alpaca.sh

@@ -7,4 +7,4 @@
 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
+./main --color -f ./prompts/alpaca.txt -ins -b 256 --top_k 10000 --temp 0.2 --repeat_penalty 1 -t 7

llama.sh

@@ -0,0 +1,7 @@
+#!/bin/bash
+#
+# Temporary script - will be removed in the future
+#
+
+./main -m ../models/13B/ggml-model-q4_0.bin -n 256 --repeat_penalty 1.0 --color -i -r "User:" -f prompts/chat.txt
+

prompts/chat-with-bob.txt

@@ -0,0 +1,7 @@
+Transcript of a dialog, where the User interacts with an Assistant named Maia. Maia is helpful, kind, honest, good at writing, and never fails to answer the User's requests immediately and with precision.
+
+User: Hello, Maia.
+Maia: Hello. How may I help you today?
+User: Please tell me the largest city in Europe.
+Maia: Sure. The largest city in Europe is Moscow, the capital of Russia.
+User: