From e66e711b406f24fd2c3131ec03a5c34447854d0b Mon Sep 17 00:00:00 2001
From: JuanBindez <juanbindez780@gmail.com>
Date: Thu, 9 Jan 2025 09:21:50 -0300
Subject: [PATCH] 0.0.4 (update)

---
 build.sh               |  2 +-
 ctesibioAI_colab.ipynb | 19 +++++++++++++------
 prompt.py              |  2 +-
 3 files changed, 15 insertions(+), 8 deletions(-)

diff --git a/build.sh b/build.sh
index 760e936..459789e 100755
--- a/build.sh
+++ b/build.sh
@@ -2,7 +2,7 @@
 
 VERSION=0
 MINOR=0
-PATCH=3
+PATCH=4
 EXTRAVERSION=""
 
 NOTES="(update)"
diff --git a/ctesibioAI_colab.ipynb b/ctesibioAI_colab.ipynb
index 18d982e..390e10d 100644
--- a/ctesibioAI_colab.ipynb
+++ b/ctesibioAI_colab.ipynb
@@ -4,7 +4,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# CtesibioAI v0.0.2"
+    "# CtesibioAI v0.0.4"
    ]
   },
   {
@@ -56,11 +56,18 @@
    },
    "outputs": [],
    "source": [
-    "datas = [\n",
-    "    {\"pergunta\": \"Qual é a capital do Brasil?\", \"resposta\": \"A capital do Brasil é Brasília.\"},\n",
-    "    {\"pergunta\": \"Quem descobriu o Brasil?\", \"resposta\": \"O Brasil foi descoberto por Pedro Álvares Cabral.\"},\n",
-    "    {\"pergunta\": \"Qual é a maior floresta tropical do mundo?\", \"resposta\": \"A maior floresta tropical do mundo é a Floresta Amazônica.\"},\n",
-    "]"
+    "data = [\n",
+    "    {\"question\": \"What is a large language model (LLM)?\", \"answer\": \"An LLM is an artificial intelligence model trained on large volumes of text to understand and generate natural language.\"},\n",
+    "    {\"question\": \"What are some examples of famous LLMs?\", \"answer\": \"Examples of famous LLMs include GPT, BERT, T5, and ChatGPT.\"},\n",
+    "    {\"question\": \"What are LLMs used for?\", \"answer\": \"LLMs are used in tasks such as text generation, machine translation, text summarization, question answering, and more.\"},\n",
+    "    {\"question\": \"What does the term 'fine-tuning' mean?\", \"answer\": \"Fine-tuning is the process of adjusting a pre-trained LLM on a specific dataset for a particular application or domain.\"},\n",
+    "    {\"question\": \"What is 'tokenization'?\", \"answer\": \"Tokenization is the process of breaking text into smaller units, called tokens, which can be words, subwords, or characters.\"},\n",
+    "    {\"question\": \"How do LLMs learn to generate text?\", \"answer\": \"LLMs learn to generate text by predicting the next word or token in a sequence based on patterns in the training text.\"},\n",
+    "    {\"question\": \"What is the main challenge in training?\", \"answer\": \"The main challenges include the high computational cost, the need for large datasets, and the difficulty of avoiding biases in the models.\"},\n",
+    "    {\"question\": \"What are parameters?\", \"answer\": \"Parameters are adjustable values in the model that determine how it processes and generates text based on input data.\"},\n",
+    "    {\"question\": \"What is a transformer?\", \"answer\": \"Transformers are a neural network architecture that uses attention mechanisms to process data sequences, such as text.\"},\n",
+    "    {\"question\": \"What is the role of 'pre-training'?\", \"answer\": \"'Pre-training' involves training the model on a large corpus of text to learn general language patterns before fine-tuning it for specific tasks.\"},\n",
+    "]\n"
    ]
   },
   {
diff --git a/prompt.py b/prompt.py
index 7f6cad4..d98ef80 100644
--- a/prompt.py
+++ b/prompt.py
@@ -7,7 +7,7 @@
 tokenizer.bos_token = "<BOS>"
 tokenizer.eos_token = "<EOS>"
 
-input_text = "<BOS>capital do brasil?"
+input_text = "<BOS>capital of Brazil?"
 inputs = tokenizer.encode(input_text, return_tensors="pt")
 
 output = model.generate(