diff --git a/site/en/gemma/docs/codegemma/code_assist_keras.ipynb b/site/en/gemma/docs/codegemma/code_assist_keras.ipynb
index 65119e45a..f49450c3f 100644
--- a/site/en/gemma/docs/codegemma/code_assist_keras.ipynb
+++ b/site/en/gemma/docs/codegemma/code_assist_keras.ipynb
@@ -21,7 +21,7 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 1,
"metadata": {
"cellView": "form",
"id": "tuOe1ymfHZPu"
@@ -47,7 +47,7 @@
"id": "SDEExiAk4fLb"
},
"source": [
- "# AI Assisted programming with CodeGemma and KerasNLP"
+ "# AI Assisted programming with CodeGemma and Keras Hub"
]
},
{
@@ -149,7 +149,7 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 4,
"metadata": {
"id": "DrBoa_Urw9Vx"
},
@@ -173,32 +173,13 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 8,
"metadata": {
"id": "ACnm31nfBqHj"
},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m508.4/508.4 kB\u001b[0m \u001b[31m3.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
- "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m950.8/950.8 kB\u001b[0m \u001b[31m18.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
- "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m5.2/5.2 MB\u001b[0m \u001b[31m51.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
- "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m589.8/589.8 MB\u001b[0m \u001b[31m1.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
- "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m4.8/4.8 MB\u001b[0m \u001b[31m59.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
- "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m2.2/2.2 MB\u001b[0m \u001b[31m32.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
- "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m5.5/5.5 MB\u001b[0m \u001b[31m42.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
- "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.1/1.1 MB\u001b[0m \u001b[31m45.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
- "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m311.2/311.2 kB\u001b[0m \u001b[31m38.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
- "\u001b[?25h\u001b[31mERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.\n",
- "tf-keras 2.15.1 requires tensorflow<2.16,>=2.15, but you have tensorflow 2.16.1 which is incompatible.\u001b[0m\u001b[31m\n",
- "\u001b[0m"
- ]
- }
- ],
+ "outputs": [],
"source": [
- "!pip install -q -U keras-nlp"
+ "!pip install -q -U keras_hub"
]
},
{
@@ -223,7 +204,7 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 5,
"metadata": {
"id": "ww83zI9ToPso"
},
@@ -240,18 +221,18 @@
"source": [
"### Import packages\n",
"\n",
- "Import Keras and KerasNLP."
+ "Import Keras and Keras Hub."
]
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 6,
"metadata": {
"id": "oQkqsyE1a2YD"
},
"outputs": [],
"source": [
- "import keras_nlp\n",
+ "import keras_hub\n",
"import keras\n",
"\n",
"# Run at half precision.\n",
@@ -277,7 +258,7 @@
"source": [
"### Load the model\n",
"\n",
- "KerasNLP provides implementations of all three CodeGemma variants (2B and 7B pre-trained (PT) and 7B instruction-tuned (IT)) using [`GemmaCausalLM`](https://keras.io/api/keras_nlp/models/gemma/gemma_causal_lm/){:.external}, an end-to-end Gemma model for causal language modeling. A causal language model predicts the next token based on previous tokens."
+ "Keras Hub provides implementations of all three CodeGemma variants (2B and 7B pre-trained (PT) and 7B instruction-tuned (IT)) using [`GemmaCausalLM`](https://keras.io/api/keras_nlp/models/gemma/gemma_causal_lm/){:.external}, an end-to-end Gemma model for causal language modeling. A causal language model predicts the next token based on previous tokens."
]
},
{
@@ -291,86 +272,174 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "source": [
+ "!pip install -U keras"
+ ],
+ "metadata": {
+ "id": "AJU3alRDWzkT",
+ "outputId": "f5616f63-6713-4585-b87b-f175b98d6293",
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ }
+ },
+ "execution_count": 7,
+ "outputs": [
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "Requirement already satisfied: keras in /usr/local/lib/python3.11/dist-packages (3.10.0)\n",
+ "Requirement already satisfied: absl-py in /usr/local/lib/python3.11/dist-packages (from keras) (1.4.0)\n",
+ "Requirement already satisfied: numpy in /usr/local/lib/python3.11/dist-packages (from keras) (2.0.2)\n",
+ "Requirement already satisfied: rich in /usr/local/lib/python3.11/dist-packages (from keras) (13.9.4)\n",
+ "Requirement already satisfied: namex in /usr/local/lib/python3.11/dist-packages (from keras) (0.1.0)\n",
+ "Requirement already satisfied: h5py in /usr/local/lib/python3.11/dist-packages (from keras) (3.13.0)\n",
+ "Requirement already satisfied: optree in /usr/local/lib/python3.11/dist-packages (from keras) (0.16.0)\n",
+ "Requirement already satisfied: ml-dtypes in /usr/local/lib/python3.11/dist-packages (from keras) (0.4.1)\n",
+ "Requirement already satisfied: packaging in /usr/local/lib/python3.11/dist-packages (from keras) (24.2)\n",
+ "Requirement already satisfied: typing-extensions>=4.6.0 in /usr/local/lib/python3.11/dist-packages (from optree->keras) (4.13.2)\n",
+ "Requirement already satisfied: markdown-it-py>=2.2.0 in /usr/local/lib/python3.11/dist-packages (from rich->keras) (3.0.0)\n",
+ "Requirement already satisfied: pygments<3.0.0,>=2.13.0 in /usr/local/lib/python3.11/dist-packages (from rich->keras) (2.19.1)\n",
+ "Requirement already satisfied: mdurl~=0.1 in /usr/local/lib/python3.11/dist-packages (from markdown-it-py>=2.2.0->rich->keras) (0.1.2)\n"
+ ]
+ }
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 8,
"metadata": {
- "id": "SQ6Yr7c4GKTx"
+ "id": "SQ6Yr7c4GKTx",
+ "outputId": "e1d9c345-6ede-4563-8fd8-4097a857f3e5",
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ }
},
"outputs": [
{
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "Downloading from https://www.kaggle.com/api/v1/models/keras/codegemma/keras/code_gemma_7b_en/3/download/model.weights.json...\n"
+ ]
+ },
+ {
+ "output_type": "stream",
"name": "stderr",
+ "text": [
+ "100%|██████████| 22.3k/22.3k [00:00<00:00, 39.7MB/s]\n"
+ ]
+ },
+ {
"output_type": "stream",
+ "name": "stdout",
"text": [
- "Downloading from https://www.kaggle.com/api/v1/models/keras/codegemma/keras/code_gemma_7b_en/1/download/config.json...\n",
- "100%|██████████| 556/556 [00:00<00:00, 790kB/s]\n",
- "Downloading from https://www.kaggle.com/api/v1/models/keras/codegemma/keras/code_gemma_7b_en/1/download/model.weights.h5...\n",
- "100%|██████████| 15.9G/15.9G [02:39<00:00, 107MB/s]\n",
- "Downloading from https://www.kaggle.com/api/v1/models/keras/codegemma/keras/code_gemma_7b_en/1/download/tokenizer.json...\n",
- "100%|██████████| 401/401 [00:00<00:00, 587kB/s]\n",
- "Downloading from https://www.kaggle.com/api/v1/models/keras/codegemma/keras/code_gemma_7b_en/1/download/assets/tokenizer/vocabulary.spm...\n",
- "100%|██████████| 4.04M/4.04M [00:00<00:00, 16.4MB/s]\n"
+ "Downloading from https://www.kaggle.com/api/v1/models/keras/codegemma/keras/code_gemma_7b_en/3/download/model_00000.weights.h5...\n"
+ ]
+ },
+ {
+ "output_type": "stream",
+ "name": "stderr",
+ "text": [
+ "100%|██████████| 9.95G/9.95G [01:59<00:00, 89.5MB/s]\n"
+ ]
+ },
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "Downloading from https://www.kaggle.com/api/v1/models/keras/codegemma/keras/code_gemma_7b_en/3/download/model_00001.weights.h5...\n"
+ ]
+ },
+ {
+ "output_type": "stream",
+ "name": "stderr",
+ "text": [
+ "100%|██████████| 5.95G/5.95G [01:08<00:00, 93.6MB/s]\n"
]
}
],
"source": [
- "gemma_lm_7b = keras_nlp.models.GemmaCausalLM.from_preset(\"code_gemma_7b_en\")"
+ "gemma_lm_7b = keras_hub.models.GemmaCausalLM.from_preset(\"code_gemma_7b_en\")"
]
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 9,
"metadata": {
- "id": "v0YFsh2a3n9P"
+ "id": "v0YFsh2a3n9P",
+ "outputId": "6ed376e9-4e7d-486d-e838-edc21ec082fb",
+ "colab": {
+ "base_uri": "https://localhost:8080/",
+ "height": 397
+ }
},
"outputs": [
{
+ "output_type": "display_data",
"data": {
+ "text/plain": [
+ "\u001b[1mPreprocessor: \"gemma_causal_lm_preprocessor\"\u001b[0m\n"
+ ],
"text/html": [
"Preprocessor: \"gemma_causal_lm_preprocessor\"\n",
"\n"
- ],
- "text/plain": [
- "\u001b[1mPreprocessor: \"gemma_causal_lm_preprocessor\"\u001b[0m\n"
]
},
- "metadata": {},
- "output_type": "display_data"
+ "metadata": {}
},
{
+ "output_type": "display_data",
"data": {
+ "text/plain": [
+ "┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┓\n",
+ "┃\u001b[1m \u001b[0m\u001b[1mLayer (type) \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m Config\u001b[0m\u001b[1m \u001b[0m┃\n",
+ "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┩\n",
+ "│ gemma_tokenizer (\u001b[38;5;33mGemmaTokenizer\u001b[0m) │ Vocab size: \u001b[38;5;34m256,000\u001b[0m │\n",
+ "└───────────────────────────────────────────────────────────────┴──────────────────────────────────────────┘\n"
+ ],
"text/html": [
- "┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┓\n",
- "┃ Tokenizer (type) ┃ Vocab # ┃\n",
- "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┩\n",
- "│ gemma_tokenizer (GemmaTokenizer) │ 256,000 │\n",
- "└────────────────────────────────────────────────────┴─────────────────────────────────────────────────────┘\n",
+ "┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┓\n",
+ "┃ Layer (type) ┃ Config ┃\n",
+ "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┩\n",
+ "│ gemma_tokenizer (GemmaTokenizer) │ Vocab size: 256,000 │\n",
+ "└───────────────────────────────────────────────────────────────┴──────────────────────────────────────────┘\n",
"\n"
- ],
- "text/plain": [
- "┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┓\n",
- "┃\u001b[1m \u001b[0m\u001b[1mTokenizer (type) \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m Vocab #\u001b[0m\u001b[1m \u001b[0m┃\n",
- "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┩\n",
- "│ gemma_tokenizer (\u001b[38;5;33mGemmaTokenizer\u001b[0m) │ \u001b[38;5;34m256,000\u001b[0m │\n",
- "└────────────────────────────────────────────────────┴─────────────────────────────────────────────────────┘\n"
]
},
- "metadata": {},
- "output_type": "display_data"
+ "metadata": {}
},
{
+ "output_type": "display_data",
"data": {
+ "text/plain": [
+ "\u001b[1mModel: \"gemma_causal_lm\"\u001b[0m\n"
+ ],
"text/html": [
"Model: \"gemma_causal_lm\"\n",
"\n"
- ],
- "text/plain": [
- "\u001b[1mModel: \"gemma_causal_lm\"\u001b[0m\n"
]
},
- "metadata": {},
- "output_type": "display_data"
+ "metadata": {}
},
{
+ "output_type": "display_data",
"data": {
+ "text/plain": [
+ "┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━┓\n",
+ "┃\u001b[1m \u001b[0m\u001b[1mLayer (type) \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mOutput Shape \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m Param #\u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mConnected to \u001b[0m\u001b[1m \u001b[0m┃\n",
+ "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━┩\n",
+ "│ padding_mask (\u001b[38;5;33mInputLayer\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;45mNone\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │ - │\n",
+ "├───────────────────────────────┼───────────────────────────┼─────────────────┼────────────────────────────┤\n",
+ "│ token_ids (\u001b[38;5;33mInputLayer\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;45mNone\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │ - │\n",
+ "├───────────────────────────────┼───────────────────────────┼─────────────────┼────────────────────────────┤\n",
+ "│ gemma_backbone │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m3072\u001b[0m) │ \u001b[38;5;34m8,537,680,896\u001b[0m │ padding_mask[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m], │\n",
+ "│ (\u001b[38;5;33mGemmaBackbone\u001b[0m) │ │ │ token_ids[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n",
+ "├───────────────────────────────┼───────────────────────────┼─────────────────┼────────────────────────────┤\n",
+ "│ token_embedding │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m256000\u001b[0m) │ \u001b[38;5;34m786,432,000\u001b[0m │ gemma_backbone[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n",
+ "│ (\u001b[38;5;33mReversibleEmbedding\u001b[0m) │ │ │ │\n",
+ "└───────────────────────────────┴───────────────────────────┴─────────────────┴────────────────────────────┘\n"
+ ],
"text/html": [
"┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━┓\n",
"┃ Layer (type) ┃ Output Shape ┃ Param # ┃ Connected to ┃\n",
@@ -386,64 +455,48 @@
"│ (ReversibleEmbedding) │ │ │ │\n",
"└───────────────────────────────┴───────────────────────────┴─────────────────┴────────────────────────────┘\n",
"\n"
- ],
- "text/plain": [
- "┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━┓\n",
- "┃\u001b[1m \u001b[0m\u001b[1mLayer (type) \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mOutput Shape \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m Param #\u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mConnected to \u001b[0m\u001b[1m \u001b[0m┃\n",
- "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━┩\n",
- "│ padding_mask (\u001b[38;5;33mInputLayer\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;45mNone\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │ - │\n",
- "├───────────────────────────────┼───────────────────────────┼─────────────────┼────────────────────────────┤\n",
- "│ token_ids (\u001b[38;5;33mInputLayer\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;45mNone\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │ - │\n",
- "├───────────────────────────────┼───────────────────────────┼─────────────────┼────────────────────────────┤\n",
- "│ gemma_backbone │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m3072\u001b[0m) │ \u001b[38;5;34m8,537,680,896\u001b[0m │ padding_mask[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m], │\n",
- "│ (\u001b[38;5;33mGemmaBackbone\u001b[0m) │ │ │ token_ids[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n",
- "├───────────────────────────────┼───────────────────────────┼─────────────────┼────────────────────────────┤\n",
- "│ token_embedding │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m256000\u001b[0m) │ \u001b[38;5;34m786,432,000\u001b[0m │ gemma_backbone[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n",
- "│ (\u001b[38;5;33mReversibleEmbedding\u001b[0m) │ │ │ │\n",
- "└───────────────────────────────┴───────────────────────────┴─────────────────┴────────────────────────────┘\n"
]
},
- "metadata": {},
- "output_type": "display_data"
+ "metadata": {}
},
{
+ "output_type": "display_data",
"data": {
+ "text/plain": [
+ "\u001b[1m Total params: \u001b[0m\u001b[38;5;34m8,537,680,896\u001b[0m (15.90 GB)\n"
+ ],
"text/html": [
" Total params: 8,537,680,896 (15.90 GB)\n",
"\n"
- ],
- "text/plain": [
- "\u001b[1m Total params: \u001b[0m\u001b[38;5;34m8,537,680,896\u001b[0m (15.90 GB)\n"
]
},
- "metadata": {},
- "output_type": "display_data"
+ "metadata": {}
},
{
+ "output_type": "display_data",
"data": {
+ "text/plain": [
+ "\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m8,537,680,896\u001b[0m (15.90 GB)\n"
+ ],
"text/html": [
" Trainable params: 8,537,680,896 (15.90 GB)\n",
"\n"
- ],
- "text/plain": [
- "\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m8,537,680,896\u001b[0m (15.90 GB)\n"
]
},
- "metadata": {},
- "output_type": "display_data"
+ "metadata": {}
},
{
+ "output_type": "display_data",
"data": {
+ "text/plain": [
+ "\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m0\u001b[0m (0.00 B)\n"
+ ],
"text/html": [
" Non-trainable params: 0 (0.00 B)\n",
"\n"
- ],
- "text/plain": [
- "\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m0\u001b[0m (0.00 B)\n"
]
},
- "metadata": {},
- "output_type": "display_data"
+ "metadata": {}
}
],
"source": [
@@ -481,7 +534,7 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 10,
"metadata": {
"id": "mHAjAdvB_5yN"
},
@@ -526,7 +579,7 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 11,
"metadata": {
"id": "eGU7XXk1SFYT"
},
@@ -538,14 +591,18 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 13,
"metadata": {
- "id": "GoRC_SzuAO7t"
+ "id": "GoRC_SzuAO7t",
+ "outputId": "0b56381d-ac3a-48f1-9021-a1f5d24eb7fb",
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ }
},
"outputs": [
{
- "name": "stdout",
"output_type": "stream",
+ "name": "stdout",
"text": [
"<|fim_prefix|>def fibonacci(n: int) -> int:\n",
" if n == 0:\n",
@@ -573,14 +630,18 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 14,
"metadata": {
- "id": "MpRJDxf4AO7t"
+ "id": "MpRJDxf4AO7t",
+ "outputId": "28255504-9751-4eab-c036-617f7b581987",
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ }
},
"outputs": [
{
- "name": "stdout",
"output_type": "stream",
+ "name": "stdout",
"text": [
"<|fim_prefix|>def fibonacci(n: int) -> int:\n",
" if n == 0:\n",
@@ -619,7 +680,7 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 15,
"metadata": {
"id": "kjaCaWcxqoq5"
},
@@ -635,14 +696,18 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 16,
"metadata": {
- "id": "nq8uV7DehsOt"
+ "id": "nq8uV7DehsOt",
+ "outputId": "a6c9affd-79a2-43e5-e93a-54071e761b23",
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ }
},
"outputs": [
{
- "name": "stdout",
"output_type": "stream",
+ "name": "stdout",
"text": [
"<|fim_prefix|>void dfs(node* root) {\n",
" if (root->left) {\n",
@@ -669,14 +734,18 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 17,
"metadata": {
- "id": "mCY-VI01hsOu"
+ "id": "mCY-VI01hsOu",
+ "outputId": "144a35a5-035a-4b11-f6d6-5355e3d80219",
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ }
},
"outputs": [
{
- "name": "stdout",
"output_type": "stream",
+ "name": "stdout",
"text": [
"<|fim_prefix|>void dfs(node* root) {\n",
" if (root->left) {\n",
@@ -707,7 +776,7 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 18,
"metadata": {
"id": "ECfsJ7JW-7ef"
},
@@ -724,14 +793,18 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 20,
"metadata": {
- "id": "-RZkx_0i_Vgj"
+ "id": "-RZkx_0i_Vgj",
+ "outputId": "2c02cb88-2d55-48ae-a758-f42ca68612bd",
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ }
},
"outputs": [
{
- "name": "stdout",
"output_type": "stream",
+ "name": "stdout",
"text": [
"Write a rust function to identify non-prime numbers.\n",
"Examples:\n",
@@ -740,17 +813,8 @@
">>> is_not_prime(10)\n",
"True\n",
"pub fn is_not_prime(n: i32) -> bool {\n",
- " if n <= 1 {\n",
- " return true;\n",
- " }\n",
- " for i in 2..n {\n",
- " if n % i == 0 {\n",
- " return true;\n",
- " }\n",
- " }\n",
- " false\n",
- "}\n",
- "\n"
+ " // your code here\n",
+ "}\n"
]
}
],
@@ -784,74 +848,165 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 21,
"metadata": {
- "id": "HxF9z5cFG5Yz"
+ "id": "HxF9z5cFG5Yz",
+ "outputId": "77d85e61-418a-46eb-ec2c-a271b08a0bdb",
+ "colab": {
+ "base_uri": "https://localhost:8080/",
+ "height": 605
+ }
},
"outputs": [
{
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "Downloading from https://www.kaggle.com/api/v1/models/keras/codegemma/keras/code_gemma_instruct_7b_en/3/download/config.json...\n"
+ ]
+ },
+ {
+ "output_type": "stream",
"name": "stderr",
+ "text": [
+ "100%|██████████| 787/787 [00:00<00:00, 1.43MB/s]\n"
+ ]
+ },
+ {
"output_type": "stream",
+ "name": "stdout",
"text": [
- "Downloading from https://www.kaggle.com/api/v1/models/keras/codegemma/keras/code_gemma_instruct_7b_en/1/download/config.json...\n",
- "100%|██████████| 556/556 [00:00<00:00, 754kB/s]\n",
- "Downloading from https://www.kaggle.com/api/v1/models/keras/codegemma/keras/code_gemma_instruct_7b_en/1/download/model.weights.h5...\n",
- "100%|██████████| 15.9G/15.9G [03:18<00:00, 86.2MB/s]\n",
- "Downloading from https://www.kaggle.com/api/v1/models/keras/codegemma/keras/code_gemma_instruct_7b_en/1/download/tokenizer.json...\n",
- "100%|██████████| 401/401 [00:00<00:00, 593kB/s]\n",
- "Downloading from https://www.kaggle.com/api/v1/models/keras/codegemma/keras/code_gemma_instruct_7b_en/1/download/assets/tokenizer/vocabulary.spm...\n",
- "100%|██████████| 4.04M/4.04M [00:00<00:00, 16.8MB/s]\n"
+ "Downloading from https://www.kaggle.com/api/v1/models/keras/codegemma/keras/code_gemma_instruct_7b_en/3/download/task.json...\n"
]
},
{
+ "output_type": "stream",
+ "name": "stderr",
+ "text": [
+ "100%|██████████| 2.91k/2.91k [00:00<00:00, 6.02MB/s]\n"
+ ]
+ },
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "Downloading from https://www.kaggle.com/api/v1/models/keras/codegemma/keras/code_gemma_instruct_7b_en/3/download/assets/tokenizer/vocabulary.spm...\n"
+ ]
+ },
+ {
+ "output_type": "stream",
+ "name": "stderr",
+ "text": [
+ "100%|██████████| 4.04M/4.04M [00:00<00:00, 16.4MB/s]\n"
+ ]
+ },
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "Downloading from https://www.kaggle.com/api/v1/models/keras/codegemma/keras/code_gemma_instruct_7b_en/3/download/model.weights.json...\n"
+ ]
+ },
+ {
+ "output_type": "stream",
+ "name": "stderr",
+ "text": [
+ "100%|██████████| 22.3k/22.3k [00:00<00:00, 26.3MB/s]\n"
+ ]
+ },
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "Downloading from https://www.kaggle.com/api/v1/models/keras/codegemma/keras/code_gemma_instruct_7b_en/3/download/model_00000.weights.h5...\n"
+ ]
+ },
+ {
+ "output_type": "stream",
+ "name": "stderr",
+ "text": [
+ "100%|██████████| 9.95G/9.95G [01:50<00:00, 96.9MB/s]\n"
+ ]
+ },
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "Downloading from https://www.kaggle.com/api/v1/models/keras/codegemma/keras/code_gemma_instruct_7b_en/3/download/model_00001.weights.h5...\n"
+ ]
+ },
+ {
+ "output_type": "stream",
+ "name": "stderr",
+ "text": [
+ "100%|██████████| 5.95G/5.95G [01:06<00:00, 96.3MB/s]\n"
+ ]
+ },
+ {
+ "output_type": "display_data",
"data": {
+ "text/plain": [
+ "\u001b[1mPreprocessor: \"gemma_causal_lm_preprocessor\"\u001b[0m\n"
+ ],
"text/html": [
"Preprocessor: \"gemma_causal_lm_preprocessor\"\n",
"\n"
- ],
- "text/plain": [
- "\u001b[1mPreprocessor: \"gemma_causal_lm_preprocessor\"\u001b[0m\n"
]
},
- "metadata": {},
- "output_type": "display_data"
+ "metadata": {}
},
{
+ "output_type": "display_data",
"data": {
+ "text/plain": [
+ "┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┓\n",
+ "┃\u001b[1m \u001b[0m\u001b[1mLayer (type) \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m Config\u001b[0m\u001b[1m \u001b[0m┃\n",
+ "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┩\n",
+ "│ gemma_tokenizer (\u001b[38;5;33mGemmaTokenizer\u001b[0m) │ Vocab size: \u001b[38;5;34m256,000\u001b[0m │\n",
+ "└───────────────────────────────────────────────────────────────┴──────────────────────────────────────────┘\n"
+ ],
"text/html": [
- "┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┓\n",
- "┃ Tokenizer (type) ┃ Vocab # ┃\n",
- "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┩\n",
- "│ gemma_tokenizer (GemmaTokenizer) │ 256,000 │\n",
- "└────────────────────────────────────────────────────┴─────────────────────────────────────────────────────┘\n",
+ "┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┓\n",
+ "┃ Layer (type) ┃ Config ┃\n",
+ "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┩\n",
+ "│ gemma_tokenizer (GemmaTokenizer) │ Vocab size: 256,000 │\n",
+ "└───────────────────────────────────────────────────────────────┴──────────────────────────────────────────┘\n",
"\n"
- ],
- "text/plain": [
- "┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┓\n",
- "┃\u001b[1m \u001b[0m\u001b[1mTokenizer (type) \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m Vocab #\u001b[0m\u001b[1m \u001b[0m┃\n",
- "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┩\n",
- "│ gemma_tokenizer (\u001b[38;5;33mGemmaTokenizer\u001b[0m) │ \u001b[38;5;34m256,000\u001b[0m │\n",
- "└────────────────────────────────────────────────────┴─────────────────────────────────────────────────────┘\n"
]
},
- "metadata": {},
- "output_type": "display_data"
+ "metadata": {}
},
{
+ "output_type": "display_data",
"data": {
+ "text/plain": [
+ "\u001b[1mModel: \"gemma_causal_lm\"\u001b[0m\n"
+ ],
"text/html": [
"Model: \"gemma_causal_lm\"\n",
"\n"
- ],
- "text/plain": [
- "\u001b[1mModel: \"gemma_causal_lm\"\u001b[0m\n"
]
},
- "metadata": {},
- "output_type": "display_data"
+ "metadata": {}
},
{
+ "output_type": "display_data",
"data": {
+ "text/plain": [
+ "┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━┓\n",
+ "┃\u001b[1m \u001b[0m\u001b[1mLayer (type) \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mOutput Shape \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m Param #\u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mConnected to \u001b[0m\u001b[1m \u001b[0m┃\n",
+ "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━┩\n",
+ "│ padding_mask (\u001b[38;5;33mInputLayer\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;45mNone\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │ - │\n",
+ "├───────────────────────────────┼───────────────────────────┼─────────────────┼────────────────────────────┤\n",
+ "│ token_ids (\u001b[38;5;33mInputLayer\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;45mNone\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │ - │\n",
+ "├───────────────────────────────┼───────────────────────────┼─────────────────┼────────────────────────────┤\n",
+ "│ gemma_backbone │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m3072\u001b[0m) │ \u001b[38;5;34m8,537,680,896\u001b[0m │ padding_mask[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m], │\n",
+ "│ (\u001b[38;5;33mGemmaBackbone\u001b[0m) │ │ │ token_ids[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n",
+ "├───────────────────────────────┼───────────────────────────┼─────────────────┼────────────────────────────┤\n",
+ "│ token_embedding │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m256000\u001b[0m) │ \u001b[38;5;34m786,432,000\u001b[0m │ gemma_backbone[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n",
+ "│ (\u001b[38;5;33mReversibleEmbedding\u001b[0m) │ │ │ │\n",
+ "└───────────────────────────────┴───────────────────────────┴─────────────────┴────────────────────────────┘\n"
+ ],
"text/html": [
"┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━┓\n",
"┃ Layer (type) ┃ Output Shape ┃ Param # ┃ Connected to ┃\n",
@@ -867,68 +1022,52 @@
"│ (ReversibleEmbedding) │ │ │ │\n",
"└───────────────────────────────┴───────────────────────────┴─────────────────┴────────────────────────────┘\n",
"\n"
- ],
- "text/plain": [
- "┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━┓\n",
- "┃\u001b[1m \u001b[0m\u001b[1mLayer (type) \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mOutput Shape \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m Param #\u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mConnected to \u001b[0m\u001b[1m \u001b[0m┃\n",
- "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━┩\n",
- "│ padding_mask (\u001b[38;5;33mInputLayer\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;45mNone\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │ - │\n",
- "├───────────────────────────────┼───────────────────────────┼─────────────────┼────────────────────────────┤\n",
- "│ token_ids (\u001b[38;5;33mInputLayer\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;45mNone\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │ - │\n",
- "├───────────────────────────────┼───────────────────────────┼─────────────────┼────────────────────────────┤\n",
- "│ gemma_backbone │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m3072\u001b[0m) │ \u001b[38;5;34m8,537,680,896\u001b[0m │ padding_mask[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m], │\n",
- "│ (\u001b[38;5;33mGemmaBackbone\u001b[0m) │ │ │ token_ids[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n",
- "├───────────────────────────────┼───────────────────────────┼─────────────────┼────────────────────────────┤\n",
- "│ token_embedding │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m256000\u001b[0m) │ \u001b[38;5;34m786,432,000\u001b[0m │ gemma_backbone[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n",
- "│ (\u001b[38;5;33mReversibleEmbedding\u001b[0m) │ │ │ │\n",
- "└───────────────────────────────┴───────────────────────────┴─────────────────┴────────────────────────────┘\n"
]
},
- "metadata": {},
- "output_type": "display_data"
+ "metadata": {}
},
{
+ "output_type": "display_data",
"data": {
+ "text/plain": [
+ "\u001b[1m Total params: \u001b[0m\u001b[38;5;34m8,537,680,896\u001b[0m (15.90 GB)\n"
+ ],
"text/html": [
" Total params: 8,537,680,896 (15.90 GB)\n",
"\n"
- ],
- "text/plain": [
- "\u001b[1m Total params: \u001b[0m\u001b[38;5;34m8,537,680,896\u001b[0m (15.90 GB)\n"
]
},
- "metadata": {},
- "output_type": "display_data"
+ "metadata": {}
},
{
+ "output_type": "display_data",
"data": {
+ "text/plain": [
+ "\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m8,537,680,896\u001b[0m (15.90 GB)\n"
+ ],
"text/html": [
" Trainable params: 8,537,680,896 (15.90 GB)\n",
"\n"
- ],
- "text/plain": [
- "\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m8,537,680,896\u001b[0m (15.90 GB)\n"
]
},
- "metadata": {},
- "output_type": "display_data"
+ "metadata": {}
},
{
+ "output_type": "display_data",
"data": {
+ "text/plain": [
+ "\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m0\u001b[0m (0.00 B)\n"
+ ],
"text/html": [
" Non-trainable params: 0 (0.00 B)\n",
"\n"
- ],
- "text/plain": [
- "\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m0\u001b[0m (0.00 B)\n"
]
},
- "metadata": {},
- "output_type": "display_data"
+ "metadata": {}
}
],
"source": [
- "gemma_lm_7b_it = keras_nlp.models.GemmaCausalLM.from_preset(\"code_gemma_instruct_7b_en\")\n",
+ "gemma_lm_7b_it = keras_hub.models.GemmaCausalLM.from_preset(\"code_gemma_instruct_7b_en\")\n",
"gemma_lm_7b_it.summary()"
]
},
@@ -945,7 +1084,7 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 22,
"metadata": {
"id": "llseiN-_5XXk"
},
@@ -972,7 +1111,7 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 23,
"metadata": {
"id": "-RJ6z5gbqTPA"
},
@@ -1000,14 +1139,18 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 24,
"metadata": {
- "id": "LlDJmIAz5f0R"
+ "id": "LlDJmIAz5f0R",
+ "outputId": "03fc8f62-b1af-4fc4-f869-7c2ea80fc94a",
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ }
},
"outputs": [
{
- "name": "stdout",
"output_type": "stream",
+ "name": "stdout",
"text": [
"user\n",
"\n",
@@ -1041,14 +1184,18 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 25,
"metadata": {
- "id": "rSBsedwN676V"
+ "id": "rSBsedwN676V",
+ "outputId": "a8384352-18fe-4880-b9d7-38cd1f95ce6d",
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ }
},
"outputs": [
{
- "name": "stdout",
"output_type": "stream",
+ "name": "stdout",
"text": [
"user\n",
"\n",
@@ -1062,8 +1209,6 @@
"```\n",
"\n",
"model\n",
- "Here is the C code equivalent of the Python code:\n",
- "\n",
"```c\n",
"int factorial(int n) {\n",
" int result = 1;\n",
@@ -1072,15 +1217,7 @@
" }\n",
" return result;\n",
"}\n",
- "```\n",
- "\n",
- "Here is a breakdown of the changes:\n",
- "\n",
- "* The function is declared with the `int` return type, as in Python.\n",
- "* The `for` loop is converted to a `for` loop with an `int` variable `i` initialized to 2 and incremented by 1 in each iteration.\n",
- "* The `range` function is replaced with a simple loop that iterates from 2 to `n` (inclusive).\n",
- "* The `result *= i` statement is used to multiply `result` by `i` in each iteration.\n",
- "* The `return` statement is used to return the final value of `result`.\n"
+ "```\n"
]
}
],
@@ -1099,7 +1236,7 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 26,
"metadata": {
"id": "yYW6VXt7qPTc"
},
@@ -1137,14 +1274,18 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 27,
"metadata": {
- "id": "To_5KvKJPw1H"
+ "id": "To_5KvKJPw1H",
+ "outputId": "deff28b8-a738-4473-c99b-90c38e194d76",
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ }
},
"outputs": [
{
- "name": "stdout",
"output_type": "stream",
+ "name": "stdout",
"text": [
"user\n",
"\n",
@@ -1180,14 +1321,18 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 28,
"metadata": {
- "id": "jHZg8YX8QuIe"
+ "id": "jHZg8YX8QuIe",
+ "outputId": "75ceab1d-8249-4b4f-813f-2d60bc4d06b1",
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ }
},
"outputs": [
{
- "name": "stdout",
"output_type": "stream",
+ "name": "stdout",
"text": [
"user\n",
"\n",
@@ -1212,43 +1357,28 @@
"```\n",
"\n",
"model\n",
- "Yes, the code is vulnerable to a memory access error.\n",
- "\n",
- "**Reasoning:**\n",
- "\n",
- "* The code allocates memory for `WidgetList` using `malloc` based on the value of `numWidgets`.\n",
- "* However, the loop iterates from `0` to `numWidgets`, which is one element beyond the allocated memory.\n",
- "* This means that accessing `WidgetList[numWidgets]` will result in a memory access error, as it is outside the bounds of the allocated memory.\n",
- "\n",
- "**Example of Memory Access Error:**\n",
- "\n",
- "When `numWidgets` is 5, the code allocates memory for `WidgetList` as follows:\n",
- "\n",
- "```\n",
- "WidgetList = (Widget **) malloc(5 * sizeof(Widget *));\n",
- "```\n",
+ "The code is vulnerable to a memory access error. The code allocates an array of pointers to `Widget` objects and then attempts to access the element at index `numWidgets`, which is out of bounds. This can lead to a memory access error if the value of `numWidgets` is greater than the maximum number of widgets allowed.\n",
"\n",
- "The loop iterates from 0 to 4, accessing the following elements:\n",
- "\n",
- "* `WidgetList[0]`\n",
- "* `WidgetList[1]`\n",
- "* `WidgetList[2]`\n",
- "* `WidgetList[3]`\n",
- "* `WidgetList[4]`\n",
- "\n",
- "However, the code then attempts to access `WidgetList[5]`, which is outside the allocated memory range. This will result in a memory access error.\n",
- "\n",
- "**Solution:**\n",
- "\n",
- "To resolve this vulnerability, the loop should be modified to iterate from 0 to `numWidgets - 1`:\n",
+ "To fix this vulnerability, the code should be modified to check if the value of `numWidgets` is within the valid range before attempting to access the array. For example, the code could be modified to the following:\n",
"\n",
"```cpp\n",
- "for (i = 0; i < numWidgets - 1; i++) {\n",
+ "int i;\n",
+ "unsigned int numWidgets;\n",
+ "Widget **WidgetList;\n",
+ "\n",
+ "numWidgets = GetUntrustedSizeValue();\n",
+ "if ((numWidgets == 0) || (numWidgets > MAX_NUM_WIDGETS)) {\n",
+ " ExitError(\"Incorrect number of widgets requested!\");\n",
+ "}\n",
+ "WidgetList = (Widget **) malloc(numWidgets * sizeof(Widget *));\n",
+ "printf(\"WidgetList ptr=%p\n",
+ "\", WidgetList);\n",
+ "for (i = 0; i < numWidgets; i++) {\n",
" WidgetList[i] = InitializeWidget();\n",
"}\n",
- "```\n",
- "\n",
- "This ensures that the loop does not access elements beyond the allocated memory range.\n"
+ "WidgetList[numWidgets - 1] = NULL;\n",
+ "showWidgets(WidgetList);\n",
+ "```\n"
]
}
],
@@ -1285,7 +1415,9 @@
"accelerator": "GPU",
"colab": {
"name": "code_assist_keras.ipynb",
- "toc_visible": true
+ "provenance": [],
+ "machine_shape": "hm",
+ "gpuType": "A100"
},
"kernelspec": {
"display_name": "Python 3",
@@ -1294,4 +1426,4 @@
},
"nbformat": 4,
"nbformat_minor": 0
-}
+}
\ No newline at end of file