wikisql download

.gitignore

@@ -1 +1,3 @@
-.venv
+.venv
+WikiSQL
+data

README.md

@@ -15,6 +15,7 @@ I had to uninstall some cuda stuff that torch installed to make this work.
 https://github.com/tloen/alpaca-lora
 https://huggingface.co/docs/transformers/main/en/model_doc/llama#llama
 https://huggingface.co/docs/transformers/index
+https://github.com/salesforce/WikiSQL
 
 
 https://arxiv.org/pdf/1910.13461.pdf

llama_test.ipynb

@@ -22,6 +22,14 @@
     "torch.cuda.is_available()"
    ]
   },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Check that we can load the tokenizer and the model.  The first time this runs it will take a while.  The files go under ~/.cache/huggingface"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 2,
@@ -39,7 +47,7 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "37df56d6ddb747f3a91bc9100b33f47b",
+       "model_id": "fc0f4312aa7c4009a912c66dd1443763",
        "version_major": 2,
        "version_minor": 0
       },
@@ -65,11 +73,27 @@
     ")\n"
    ]
   },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Construct a basic example to interact with the model"
+   ]
+  },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 3,
    "metadata": {},
    "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/home/matt/hf/sqllama-V0/.venv/lib/python3.7/site-packages/transformers/generation/utils.py:1220: UserWarning: You have modified the pretrained model configuration to control generation. This is a deprecated strategy to control generation and will be removed soon, in a future version. Please use a generation configuration file (see https://huggingface.co/docs/transformers/main_classes/text_generation)\n",
+      "  \"You have modified the pretrained model configuration to control generation. This is a\"\n"
+     ]
+    },
     {
      "name": "stdout",
      "output_type": "stream",
@@ -97,6 +121,42 @@
     "r = ask('whats the capital of georgia?')\n",
     "print(r)\n"
    ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Get the WikiSQL project so we can get the dataset"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "fatal: destination path 'WikiSQL' already exists and is not an empty directory.\n",
+      "data/\n",
+      "data/train.jsonl\n",
+      "data/test.tables.jsonl\n",
+      "data/test.db\n",
+      "data/dev.tables.jsonl\n",
+      "data/dev.db\n",
+      "data/test.jsonl\n",
+      "data/train.tables.jsonl\n",
+      "data/train.db\n",
+      "data/dev.jsonl\n"
+     ]
+    }
+   ],
+   "source": [
+    "! git clone https://github.com/salesforce/WikiSQL\n",
+    "! tar xvjf WikiSQL/data.tar.bz2"
+   ]
   }
  ],
  "metadata": {

requirements.txt

@@ -5,4 +5,9 @@ torch
 sentencepiece
 transformers
 accelerate
-bitsandbytes
+bitsandbytes
+peft
+tqdm
+records
+babel
+tabulate