I tried using the new AI agent framework "smolagents". The code is simple and easy to use, and I recommend it for AI agent beginners!

At the end of last year, a new AI agent framework called "smolagents" was released from Hugging Face (1). The code is simple and easy to use, and it even supports multi-agents. This time, I actually created a data analysis AI agent and tried various things. I hope it will be helpful.

1. Features of "smolagents"
The newly released "smolagents" has features that existing frameworks do not have. 1) First, it has a simple structure. You can execute an AI agent by writing 3 to 5 lines of code. It's perfect for those who want to start with AI agents. 2) Also, since it was released by Hugging Face, there are already a huge number of open-source models on the Hub. You can easily call and use them. Of course, it also supports proprietary models such as GPT4o, so you can use it for both open and closed models. 3) Finally, when you execute an agent, python code is generated and acted upon. Therefore, you can use the assets of the vast Python ecosystem, which is very convenient. Especially for those who specialize in data analysis like me, it is a perfect framework because you can use Python libraries such as sklearn.

2. An Agent for Predicting Credit Card Defaults

Now, let's actually build an AI agent. The theme is "AI agent by smolagent predicts credit card defaults". Normally, when building a default prediction model, you would code using machine learning libraries such as sklearn, but this time, I want to give it data and have the AI agent itself code internally using Python and automatically display the default probabilities of the first 10 customers.

For how to write the code, please refer to the official documentation , but here I would like to present what kind of prompts I actually wrote to make the AI agent predict defaults. The point is to specifically instruct it to "use sklearn's HistGradientBoostingClassifier for data analysis". This library is highly evaluated for creating machine learning models with high accuracy and ease of use. This is domain knowledge of data analysis, but by including that knowledge in the prompt, we expect to obtain higher accuracy.

Furthermore, as a question, I will add an instruction to specifically calculate "the default probability of 10 customers". The AI agent is input in the form of "prompt + question".

Then, the AI agent automatically generated the following Python code. Normally, this is what I would write myself, but the AI agent does it for me. And as a result, the default probabilities for 10 people are also shown. Amazing!

In this way, the user only needs to instruct "use sklearn to calculate the default probability", and the AI agent writes the code to calculate the default probability for each customer. And you will be able to make default predictions for each customer. I tried it with default prediction this time, but I think it can be covered to the probability in any business, such as marketing, customer churn and human resources. I'm looking forward to future developments.

3. Impressions after using "smolagents" for the first time

Until now, I used LangGraph to implement AI agents. I liked it because I could make various detailed settings, but it was necessary to code each of state, tool, node, edge, etc., and I felt that the hurdle was high for beginners to start with. After implementing it with "smolagents" this time, I found that if I coded according to the template, it would run by writing a few lines, so anyone could start. Of course, it fully meets the needs of AI developers, so I plan to actively use it in 2025 to develop various AI agents. I have published the code this time in a notebook (2). Please look forward to the next AI agent article. Stay tuned!

(1) Introducing smolagents, a simple library to build agents,  Aymeric Roucher, Merve Noyan, Thomas Wolf, Hugging Face, Dec 31,2024   
(2) AI-agent-to-predict-default-of-credit-card-with-smolagent_20250121

Notice: ToshiStats Co., Ltd. and I do not accept any responsibility or liability for loss or damage occasioned to any person or property through using materials, instructions, methods, algorithms or ideas contained herein, or acting or refraining from acting as a result of such use. ToshiStats Co., Ltd. and I expressly disclaim all implied warranties, including merchantability or fitness for any particular purpose. There will be no duty on ToshiStats Co., Ltd. and me to correct any errors or defects in the codes and the software.

OpenAI o1-preview: A Breakthrough in Generative AI, Introducing a Novel Paradigm

Last week, we introduced OpenAI o1(1). Despite still being in preview, it boasts high performance, and as evidenced by the leaderboard below(2), it seems to be widely regarded as having overwhelming performance, especially in mathematics and coding. In this article, we'd like to explore why OpenAI o1 demonstrates higher accuracy compared to existing generative AI models like GPT4.

Scores of various generative AIs in the mathematics field

1. Chain of Thought is Key

The star of the OpenAI o1 model is "Chain of Thought." This refers to "a series of intermediate reasoning steps," which was previously considered an important element of prompts created by users for existing generative AI models. By incorporating "Chain of Thought" into prompts, users enabled generative AI to engage in deeper and broader thinking before providing an answer, thereby improving accuracy. "Chain of Thought" became known to the public through a 2022 research paper(3). Please refer to it for details.

2. OpenAI o1 Can Generate Chain of Thought Independently

OpenAI o1 can generate Chain of Thought internally on its own. Users don't need to devise Chain of Thought themselves; it's generated automatically. This is why it achieved high accuracy in mathematics and coding. Unfortunately, OpenAI seems to have decided not to disclose the Chain of Thought itself. Users can only see a summary of it. If you're like most users, you're probably thinking, "I'd really like to see that!" We hope that OpenAI will change its policy and release it in the future.

3. Creating a Reward Model

OpenAI has released very little information about what we'll discuss from here on. Please note that the following is based on speculation drawn from previously published research papers and information shared by OpenAI researchers. To enable generative AI to automatically generate task-specific Chain of Thought for practical use, we must evaluate whether the generated Chain of Thought is actually correct. This is where the Reward model comes into play. A 2023 research paper(4) from OpenAI provides a detailed explanation of how to train a Reward model, so let's look to it for clues.

The data for training the Reward model takes the form of Chain of Thought, as shown below. This research paper limits the tasks to mathematics. Since it's challenging for humans to manually create Chain of Thought for each task, they are automatically generated using GPT4. This is called the Generator. Humans then label each step of the Chain of Thought generated by the Generator on a three-point scale (correct, incorrect, or neither). This completes the training data. In the example below, you can see that each step is assigned a three-point label. It must have been quite a task for humans to label a large amount of such data.

Training data for the Reward model

4. Training Generative AI Through Reinforcement Learning

Once the Reward model is complete, we can train the generative AI using reinforcement learning. As a result, the generative AI can generate the correct Chain of Thought for the task. We, the users, actually run OpenAI o1 and benefit from the generated Chain of Thought. Unfortunately, OpenAI has not disclosed the specific method for training OpenAI o1 using reinforcement learning. Since this directly affects accuracy, it's unlikely to be released in the future. However, researchers worldwide are working on this issue and have published several promising results. As this is a technology that will support the future development of generative AI, we would like to revisit it in a future article.

5. A New Paradigm for Generative AI

OpenAI's website includes the following statement and chart:

“Our large-scale reinforcement learning algorithm teaches the model how to think productively using its chain of thought in a highly data-efficient training process. We have found that the performance of o1 consistently improves with more reinforcement learning (train-time compute) and with more time spent thinking (test-time compute). The constraints on scaling this approach differ substantially from those of LLM pretraining, and we are continuing to investigate them.”

Model computational cost and accuracy

Until now, there has been much discussion about how increasing the computational cost (time and number of parameters) in pre-training improves the accuracy of generative AI, but there hasn't been much in-depth discussion about the relationship between inference computational cost and accuracy. However, it has now become clear that by generating Chain of Thought itself and then providing an answer, generative AI can answer tasks requiring complex logical reasoning with high accuracy, albeit with significantly increased inference computational cost. The chart on the right above shows that accuracy improves as the computational cost at inference time increases. We believe this is a groundbreaking development. Therefore, it will be important to consider both training and inference computational costs for generative AI in the future. This marks the dawn of a new paradigm for generative AI.

OpenAI o1 has not only improved accuracy but has also brought about a new paradigm for the development of generative AI. We look forward to seeing how future generative AIs will follow in its footsteps. That's all for today. Stay tuned!

1) Introducing OpenAI o1, OpenAI, Sep 12, 2024
2) LMSYS Chatbot Arena Leader board
3) Chain-of-Thought Prompting Elicits Reasoning in Large Language Models, Google Research, Brain Team, Jan 2023
4) Let’s Verify Step by Step, Hunter Lightman , Vineet Kosaraju, Yura Burda, Harri Edwards,  Bowen Baker, Teddy Lee, Jan Leike, John Schulman, Ilya Sutskever, Karl Cobbe,  OpenAI, May 2023

Notice: ToshiStats Co., Ltd. and I do not accept any responsibility or liability for loss or damage occasioned to any person or property through using materials, instructions, methods, algorithms or ideas contained herein, or acting or refraining from acting as a result of such use. ToshiStats Co., Ltd. and I expressly disclaim all implied warranties, including merchantability or fitness for any particular purpose. There will be no duty on ToshiStats Co., Ltd. and me to correct any errors or defects in the codes and the software.

OpenAI's "o1-preview" Arrives: Is This the Next Leap Towards Artificial General Intelligence?!

On September 12, 2024, OpenAI released its new generative AI model "o1" (pronounced "oh-one"), which had been the subject of much speculation. I had the opportunity to try it out, and here are my initial impressions.

1. Model Overview

As a new generative AI model, o1 has various features, but the key points are as follows:

• Specialized for scientific, coding, and mathematical reasoning.

• Available in two versions: OpenAI o1 and OpenAI o1-mini.

• Currently in preview with limited functionality and performance.

• Not a successor to GPT-4.

• OpenAI o1 has a limited usage of 30 requests per week.

• Price: OpenAI o1 is about six times more expensive than GPT-4o.

For more details, please refer to the official website (1).

Compared to GPT-4o, o1-preview demonstrates superior performance in coding, data analysis, and mathematics, as shown below. It seems likely that o1 will excel in fields where existing generative AI has struggled to achieve satisfactory accuracy. However, because it utilizes Chain of Thought reasoning to arrive at answers, it can take a considerable amount of time to respond, making it unsuitable for tasks requiring real-time answers.

GPT-4o vs. o1-preview: Task Performance Comparison

2. Challenging o1 with Game24

Let's test the capabilities of o1-preview. A common example of a task that generative AI struggles with is Game24.

This is a simple mathematical puzzle with the following rules:

• Use the four given numbers and basic arithmetic operations (addition, subtraction, multiplication, division).

• Create a mathematical expression that results in 24.

• Each of the four given numbers can be used only once.

Example: 13, 10, 9, 4 → (10 - 4) × (13 - 9)

When attempting this with o1-preview, it produced the following result. It successfully solved the puzzle! The response took about 15 seconds, likely due to internal trial-and-error processes.

Game24 instruction

o1-preview Game24 Trial Result

When trying the same with GPT-4o:

GPT4o Game24 Trial Result

GPT-4o fails to provide a correct answer. This highlights o1's superiority in tasks that require strong logical reasoning.

3. The Impact on the Future of Generative AI

o1's newfound capabilities are attributed to its incorporation of Chain of Thought reasoning, enabling it to generate task-specific chains of thought and produce more reliable correct answers. However, the Chain of Thought process, which demonstrates how the correct answer is derived, is not revealed to the user. This is somewhat disappointing, as users typically want to understand not only the correct answer but also "why" that answer was reached. Therefore, it's understandable that some may perceive it as a black box. We hope that the open-source development community will further research this aspect and share their findings with the world. With excellent open-source generative AI models like Llama and Gemma currently available, we believe that user verification of Chain of Thought will become possible in the near future.

Conclusion

o1-preview seems to have been received with a level of excitement not seen since the release of GPT-4 in March 2023. In the next installment, I plan to explore the technology behind this impressive generative AI, based on external speculation. That's all for today. Stay tuned!

1) Introducing OpenAI o1, OpenAI, Sep 12, 2024 

Notice: ToshiStats Co., Ltd. and I do not accept any responsibility or liability for loss or damage occasioned to any person or property through using materials, instructions, methods, algorithms or ideas contained herein, or acting or refraining from acting as a result of such use. ToshiStats Co., Ltd. and I expressly disclaim all implied warranties, including merchantability or fitness for any particular purpose. There will be no duty on ToshiStats Co., Ltd. and me to correct any errors or defects in the codes and the software.

Gemma2-2B: A Small Yet Powerful Generative AI - A Hands-On Review

Today, we'll be diving into Google DeepMind's recently announced compact generative AI model, "Gemma2-2B" (1), and running a simple demo. Gemma is an open-source library. While medium-sized models with 70B and 9B parameters are already available, this latest release boasts a significantly smaller 2B parameter model. It promises remarkable performance despite its size, generating considerable excitement. Let's take a closer look.

1. Remarkable Fundamental Performance

Despite its compact size, the Gemma model exhibits impressive performance, as detailed below. Surpassing GPT3.5 is a feat unimaginable just a year ago. The rapid advancements in open-source models continue to amaze.

Google's website describes it as follows (1):

""This lightweight model produces outsized results by learning from larger models through distillation. In fact, Gemma 2 2B surpasses all GPT-3.5 models on the Chatbot Arena, demonstrating its exceptional conversational AI abilities.

The "distillation" technique mentioned here is key to enhancing the performance of smaller models. It's employed not only in Gemma but also in Llama3 and various other small models, making it a concept worth remembering. With the performance of a 2B parameter model reaching such heights, it's tempting to explore its capabilities. Let's move on to the demo.

2. Performance Check with a News Article Classification Task

For this demo, we'll tackle the task of classifying Japanese articles from the publicly available Livedoor-news dataset (2) into five genres. We'll fine-tune the Gemma2-2B model and evaluate its classification accuracy. Since we're using Japanese articles, this will also assess its multilingual capabilities. Let's get started!

The following article is an example from the validation data. The model's task is to identify this article as belonging to the sports category.

　　　　　　　　　　　　　　　　Example of validation data

Specifically, each article is categorized into one of the following categories. The goal of today's demo is to improve the accuracy of this classification.

• 'kaden-channel' (Electronics)

• 'topic-news' (General News)

• 'sports-watch' (Sports)

• 'it-life-hack' (IT/Life Hacks)

• 'movie-enter' (Movies/Entertainment)

We prepared 100 samples for training data and 1000 samples for validation data. We'll apply fine-tuning using the impressive quantization tool Unsloth, and the data will be in the Alpaca format. For details, please refer to this link (3).

Without extensive tuning, we achieved an accuracy of 81.5%, as shown below. Considering the small training dataset of only 100 samples, this is an impressive result. With further optimization, the accuracy could likely be improved. It's hard to believe this performance comes from a model with only 2B parameters. Its ability to handle Japanese text is also commendable. The notebook used for the demo can be found here.

3. Limitless Potential Applications

With such high performance in a small model, the possibility of implementation on devices like smartphones, previously deemed impractical, becomes a reality. It also opens doors for applications where cost and computational speed were prohibitive. It seems particularly well-suited for customer service applications requiring real-time responses. Additionally, it could be deployed in developing countries where the cost of using frontier models like GPT4 has been a barrier. The future possibilities are truly exciting.

So, what did you think? The Gemma2-2B model can run on Google Colab's free T4 GPU, making it a valuable asset for startups like ours. It's truly remarkable. The small yet powerful Gemma2-2B model is poised for widespread adoption. At ToshiStats, we're committed to developing tuning techniques to maximize the benefits of open-source libraries. We'll be sharing more on this blog in the future. That's all for today. Stay tuned!

(1) Smaller, Safer, More Transparent: Advancing Responsible AI with Gemma
(2) Livedoor-news Japanese articles
(3) Alpaca +  Gemma2-2B full example.ipynb

Notice: ToshiStats Co., Ltd. and I do not accept any responsibility or liability for loss or damage occasioned to any person or property through using materials, instructions, methods, algorithms or ideas contained herein, or acting or refraining from acting as a result of such use. ToshiStats Co., Ltd. and I expressly disclaim all implied warranties, including merchantability or fitness for any particular purpose. There will be no duty on ToshiStats Co., Ltd. and me to correct any errors or defects in the codes and the software.

Google introduces new open-weight generative AI "Gemma2". The competition with Llama3 has finally begun!

Google has finally introduced a new type of open-weight generative AI, "Gemma2" (1). Although it had been previously announced, it came out sooner than expected. As shown below, the 27B model boasts an impressive 12th place on the leaderboard, closely rivaling larger models. A technical report (2) is also available, so let's take a look at what kind of evolution has occurred.

LMSYS Chatbot Arena Leaderboard

1. Model Architecture

Gemma2 adopts the familiar decoder-only transformer architecture. It's the same as GPT4. The context window, which indicates the amount of information that can be input and output at once, is 8192 tokens. The model structure is largely the same as Gemma1, but according to the technical report, the following points have been updated:

“We alternate between a local sliding window attention (Beltagy et al., 2020) and global attention (Luong et al., 2015) in every other layer. The sliding window size of local attention layers is set to 4096 tokens, while the span of the global attention layers is set to 8192 tokens.”

Global attentional model (3)

Comparison of full self-attention pattern and other attention patterns (4)

2. Pre-training

Gemma2's training data is as follows:

• 27B model: 13 trillion tokens, primarily English data

• 9B model: 8 trillion tokens

• 2.6B model: 2 trillion tokens

"These tokens come from a variety of data sources, including web documents, code, and science articles.  Our models are not multimodal and are not trained for state-of-the-art multilingual capabilitiesthe.”

“same tokenizer as Gemma 1 and Gemini: a SentencePiece tokenizer with split digits, preserved whitespace, and byte-level encodings. The resulting vocabulary has 256k entries."

Knowledge distillation was also adopted for the 9B and 2.6B models. In my opinion, this might be the most evolved point of Gemma2. It's a Google-specific strategy to leverage the advantages of their existing large-scale generative AI to improve the performance of smaller models. The technical report explains in detail: "Given a large model used as a teacher, we learn smaller 9B and 2.6B models by distilling from the probability given by the teacher of each token 𝑥 given its context 𝑥𝑐, i.e., 𝑃𝑇(𝑥 | 𝑥𝑐). More precisely, we minimize the negative log-likelihood between the probabilities from the teacher and the student.

where 𝑃𝑆 is the parameterized probability of the student. In practice, we run inference on the teacher once and store the probabilities. Since the vocabulary has 256k entries, we only store a sampled subset of the teacher probabilities."

3. Post-training

This part uses techniques commonly seen in other generative AIs. According to the technical report, it is implemented in the following process:

“For post-training, we fine-tune our pre-trained models into instruction-tuned models. First, we apply supervised fine-tuning (SFT) on a mix of text-only, English-only synthetic and humangenerated prompt-response pairs. We then apply RLHF on top of these models with the reward model trained on labelled English-only preference data and the policy based on the same prompts as the SFT phase. Finally, we average the models obtained after each phase to improve their overall performance.“

It's noteworthy that knowledge distillation is adopted again. "We run behavioral cloning on synthetic and real prompts, and responses predominantly synthetically generated by the teacher, that is a larger model. We also run distillation from the teacher on the student’s distribution." In the future, knowledge distillation from large models to small models may become common practice. It's exciting to see.

What do you think? Gemma2 seems to be a model with high potential even in small sizes, and it's promising. The 2.6B model is also expected to be released soon. By the way, Google, which created Gemma2, and Meta, which created Llama3 that we covered last time, have been rivals in the open-source world for more than 8 years with "Tensorflow vs PyTorch". It seems that a similar battle has begun in generative AI as well. Next time, I'd like to try various things with the Gemma2 model. Stay tuned!

1) Gemma 2 is now available to researchers and developers, Google, 27 June 2024
2) Gemma 2 technical paper,  Google DeepMind, 27 June 2024
3) Effective Approaches to Attention-based Neural Machine Translation, Minh-Thang Luong Hieu Pham Christopher D. Manning Computer Science Department, Stanford University, 20 Sep 2015
4) Longformer: The Long-Document Transformer, Iz Beltagy,  Matthew E. Peters,  Arman Cohan, Allen Institute for Artificial Intelligence, 2 Dec 2020
5) On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes, Rishabh Agarwal12, Nino Vieillard1, Yongchao Zhou13, Piotr Stanczyk1, Sabela Ramos1, Matthieu Geist1, Olivier Bachem1, 1Google DeepMind, 2Mila, 3University of Toronto, 17 Jan 2024

Notice: ToshiStats Co., Ltd. and I do not accept any responsibility or liability for loss or damage occasioned to any person or property through using materials, instructions, methods, algorithms or ideas contained herein, or acting or refraining from acting as a result of such use. ToshiStats Co., Ltd. and I expressly disclaim all implied warranties, including merchantability or fitness for any particular purpose. There will be no duty on ToshiStats Co., Ltd. and me to correct any errors or defects in the codes and the software.

Llama3: Exceeding Expectations and Expanding Horizons!

The release of the new LLM "Llama3" by Meta on April 18th has created quite a stir in the AI community (1). As a highly anticipated open-source model with performance expectations on par with GPT-4, its potential applications seem limitless.

Examining the performance on leaderboards (2), Llama3 is available in two sizes: 70B and 8B parameters. The larger 70B model, in particular, demonstrates capabilities that rival proprietary models such as GPT-4, Claude3-Opus, and Gemini 1.5 Pro.

To assess Llama3's performance, a test was conducted using a bank customer complaint classification task. The objective was to evaluate the model's accuracy in categorizing complaints without any fine-tuning.

1.To what extent can we discriminate between six categories of customer complaints without training?

The dataset consisted of customer complaints from a US bank, categorized into six product areas:

• Mortgage

• Checking or savings account

• Student loan

• Money transfer, virtual currency, or money service

• Bank account or service

• Consumer loan

Examples of these complaints, all in English, were provided.

A random sample of 500 complaints was used with a prompt instructing Llama3-70B to assign a product category to each complaint. The results were astounding, achieving an accuracy rate of 88.6%. This near 90% accuracy was unprecedented and speaks volumes about Llama3's potential.

2. Maintaining Accuracy with Japanese Data?

Considering the potential use of Llama3 in Japan, the English dataset was translated into Japanese using Google Translate. The classification task was then repeated with the translated data.

Despite Llama3's training data being predominantly English (around 95%), the model maintained an impressive accuracy rate of 82.8% with the Japanese data. This suggests that Llama3's capabilities extend beyond English and hold promise for multilingual applications.

3. Conclusion and Future Prospects

Llama3 has proven to be a top-tier performer, despite being open-source. This achievement deserves appreciation for Meta's contribution to the AI community. Hopefully, other companies like Google will follow suit and release their own open-source models more.

Further experiments are planned to evaluate the accuracy and computational speed of the smaller 8B model. Stay tuned for the results!

1) meta website https://llama.meta.com/llama3/
2) LMSYS Chatbot Arena Leaderboard　https://chat.lmsys.org/?leaderboard
3) https://github.com/TOSHISTATS/Classification-of-Consumer-Complaints-by-Llama3/tree/main

Notice: ToshiStats Co., Ltd. and I do not accept any responsibility or liability for loss or damage occasioned to any person or property through using materials, instructions, methods, algorithms or ideas contained herein, or acting or refraining from acting as a result of such use. ToshiStats Co., Ltd. and I expressly disclaim all implied warranties, including merchantability or fitness for any particular purpose. There will be no duty on ToshiStats Co., Ltd. and me to correct any errors or defects in the codes and the software.

The new generative AI "Google Gemini 1.5 Pro" is as amazing as expected!

Last month, I informed you that Google released a new generative AI called "Gemini 1.5 Pro" (1). And today, the "Gemini 1.5 Pro" finally arrived at Toshi Stats. I would like to experiment with it right away.

1. Can the 1 million token long context window really work?

Gemini 1.5 Pro boasts an incredibly long context window of 1 million tokens, which is unthinkable for previous LLMs. Because it is so amazing, anyone would wonder, "Can this really work?" Today, I would like to explore its capabilities here. I have prepared two experiments. The first one is to extract detailed information including numbers from relatively short materials, and the second one is to see if it can answer comprehensive questions well from materials over 200,000 tokens long. Let's begin.

2. Information extraction from Toyota Motor Corporation's financial results  

First, I will check if it can accurately extract numerical information from Toyota Motor Corporation's financial results for the fiscal year ended March 2023. The number of pages is 28, and the number of tokens is about 27,000, which is not a long material, but it is a task often seen in practice. This time, I have prepared 13 questions. Let's upload the material to Google AI Studio and ask the questions one by one.

Google AI Studio 

Here are the results. The correct answer rate is about 88%.

Questions and Results & Computation Time

For question 8, the financial results refer to ROE as "Return on equity attributable to owners of the parent company". This long phrase in Japanese (Kanji) may have been difficult for the American-born Gemini 1.5 Pro to understand. However, it showed the value by calculating from other related numbers by itself, so I gave it a △ evaluation with 0.5 points added. It seems to be able to handle Japanese quite well. By the way, the average computation time was around 30 seconds to output the results, so it seems that the computation resources have also been optimized. Just to note, this material was published on May 10, 2023, so it's possible that it has been incorporated into the training data.

3. Information extraction from the Financial Inspection Manual 

Next, I would like to analyze the lengthy financial administrative document "Financial Inspection Manual" with Gemini 1.5 Pro. This is an unforgettable document for those who have been in the financial industry since 2000 in Japan, as it sparked discussions on establishing risk management and governance frameworks. The number of pages is 366, and the number of tokens is 220,526, exceeding 200,000 tokens. Gemini 1.5 Pro is the world's first generative AI that can take in documents of this volume all at once. I was able to upload it smoothly as shown below. It answers properly when asked questions.

Uploading the Financial Inspection Manual

I actually asked, "What should be done to verify the appropriateness of the credit rating assignment process?" and received the following response (showing only 1 and 2 here as it is long).  To verify the appropriateness of the credit rating assignment process, the following items need to be examined:

* 1. Validity of rating criteria

    * Do the rating criteria appropriately reflect the credit risk of the debtors?

    * Are the rating criteria defined in an objective and verifiable manner?  

    * Are the rating criteria consistent with the debtor classifications?

    * Are the rating criteria periodically reviewed?

* 2. Appropriateness of rating assignment procedures      

    * Are the rating assignment procedures carried out appropriately in accordance with the rating criteria?

    * Are the rating assignment procedures implemented in an accurate and verifiable objective manner?

    * Can the rating assignment procedures timely reflect changes in the debtor's situation? 

    * Are the rating assignment procedures performed by an independent department not influenced by sales departments, etc.?

It continues with 3: Model Utilization, 4: Data Maintenance, 5: Internal Audit, and so on. It is a comprehensive and holistic answer that follows the principles of risk management and is also consistent with the descriptions around page 142 of the Financial Inspection Manual. Furthermore, the descriptions related to credit risk management are in the middle of this manual, and there were past comments that generative AIs tend to have lower accuracy in the middle parts of long data. However, Gemini 1.5 Pro does not seem to have any issues. Despite the specialized content, it provided a very good answer. The computation time was also around 90 seconds, which is sufficiently practical. It will surely make a good risk management assistant.  

How was that? It seems that it can analyze materials over 200,000 tokens quite accurately even in Japanese. It might also be useful for internal document search tasks at work. Next time, I would like to challenge even more difficult tasks in English. Stay tuned!"

1) Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context, Gemini Team, Google

Copyright © 2024 Toshifumi Kuga. All right reserved

Notice: ToshiStats Co., Ltd. and I do not accept any responsibility or liability for loss or damage occasioned to any person or property through using materials, instructions, methods, algorithms or ideas contained herein, or acting or refraining from acting as a result of such use. ToshiStats Co., Ltd. and I expressly disclaim all implied warranties, including merchantability or fitness for any particular purpose. There will be no duty on ToshiStats Co., Ltd. and me to correct any errors or defects in the codes and the software.

The Evolution of AI Accelerates: A Deep Dive into Google's "Gemini 1.5 Pro"

The pace of AI advancement is truly remarkable, and this year is no exception. Google has unveiled a new generative AI called "Gemini 1.5 Pro," which boasts a groundbreaking Mixture-of-Experts (MoE) architecture. Currently only available to a limited number of users, with broader testing to come, this technology presents intriguing breakthroughs that warrant a closer look.

1. Unprecedented Context Window of 1 Million Tokens

Gemini 1.5 Pro boasts a context window that is unfathomable by existing LLMs, capable of processing up to 1 million tokens. Research has even demonstrated data ingestion of up to 10 million tokens. This represents a revolutionary breakthrough, considering that GPT-4's context window is limited to 128,000 tokens (1).

Comparison of Context Windows for Different LLMs

With such an extensive context window, Gemini 1.5 Pro can ingest an entire book at once. Currently, when creating RAG systems and referencing internal documents, chunking is necessary to accommodate the LLM's context window. However, with Gemini 1.5 Pro, this requirement is minimized, simplifying RAG development and operation. Furthermore, the model maintains high accuracy, even with such a large context window, achieving over 99% accuracy in information retrieval tests (see chart below).

2. Remarkable In-Context Learning Capabilities

The ability to process vast amounts of data is not the only noteworthy aspect of Gemini 1.5 Pro. It also excels at understanding and applying this information to various tasks. This is evident in its in-context learning capabilities, showcased in a Kalamang language translation task. The model was trained using a Kalamang grammar book and dictionary, enabling it to translate between English and Kalamang.

English to Kalamang Translation Test

Gemini 1.5 Pro outperformed other models, achieving scores that rival those of human learners. This is an astonishing feat.

3. Towards Individualized Agents with Gemini 1.5 Pro

If a model can acquire translation capabilities simply by reading a grammar book, it stands to reason that it can also learn from knowledge systems in other domains and apply that knowledge to various tasks. In other words, Gemini 1.5 Pro has the potential to develop its own "frame of reference" that influences its understanding and values. The ability to incorporate a vast amount of data into its context through its extensive context window has significant implications in this regard. This is because it allows Gemini 1.5 Pro to potentially become an individualized agent with diverse perspectives in the future. The Kalamang translation experiment provides promising evidence of this potential.

Gemini 1.5 Pro is a remarkable advancement in AI technology, offering unprecedented capabilities in terms of context window size and in-context learning. "A host of improvements made across nearly the entire model stack (architecture, data, optimization and systems) allows Gemini 1.5 Pro to achieve comparable quality to Gemini 1.0 Ultra , while using significantly less training compute and being significantly more efficient to serve" according to the report(1). This is truly a testament to the rapid progress being made in the field of AI.

I am eager to experiment with Gemini 1.5 Pro once it becomes publicly available. Stay tuned for future updates!

Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context, Gemini Team, Google

Copyright © 2024 Toshifumi Kuga. All right reserved

Notice: ToshiStats Co., Ltd. and I do not accept any responsibility or liability for loss or damage occasioned to any person or property through using materials, instructions, methods, algorithms or ideas contained herein, or acting or refraining from acting as a result of such use. ToshiStats Co., Ltd. and I expressly disclaim all implied warranties, including merchantability or fitness for any particular purpose. There will be no duty on ToshiStats Co., Ltd. and me to correct any errors or defects in the codes and the software.

"REST MEETS REACT" is a new prompt-engineering method using synthetic data. It holds immense potential for enhancing AI without relying on human-generated data

Happy New Year! Thank you for your continued support. Promptly, Google DeepMind has announced a new, advanced prompt engineering method suitable for the new year. It is a paper titled "REST MEETS REACT: SELF-IMPROVEMENT FOR MULTI-STEP REASONING LLM AGENT"(1). It incorporates fine-tuning with synthetic data, which looks promising! Let's get started.

1.Prompt Structure

This prompt is designed with a web Q&A system in mind that answers complex questions. The structure is as follows:

The blue part in the figure above represents the flow of the agent described in the prompt, aiming to answer complex questions using web search. In the latter half, "Relevance self-check" and "Grounding self-check" are functions for the agent to check its own answers. It's a self-check function. For a detailed explanation of the entire flow, please refer to the paper.

2. "Reward Model" - The Key to Success

Now, let's explain the core part of self-improvement. In a nutshell, it's about "creating new high-quality data and fine-tuning the model with it." . This function consists of three parts:

• Grow: Start with a model capable of running Search Agent, using Google PaLM 2-L model for this purpose. Trajectories are collected based on a selected set of 2000 public questions. Trajectory, though an unfamiliar term, refers to the reasoning process and is commonly used in reinforcement learning.

• Improve: Convert trajectories into data for fine-tuning, using the Reward model to select only high-quality data. No external data, like labels, are used.

• Fine-tuning: Fine-tune a new model of the same size with this new data, ensuring it performs better than the original.

This process is repeated with the better model using the new data. As a result, accuracy improves while maintaining the original data, without adding external data. Therefore, the accuracy of the Reward model in ranking is crucial. The Reward model is constructed as a set of prompts in this paper. Let's look more closely at these prompts, showing only the initial part.

• The goal of this rating is to filter out bad actions so that they'll be excluded from the fine-tuning dataset.

• Overall, we want the agent to produce relevant and grounded answers with minimal steps. Anything deviating from this goal is considered bad.

• If any element (thoughts, comments, etc.) is empty, then it's automatically bad.

"Filter out" indicates a method of discarding items that don't meet the standards and adopting only the high-quality data that remains. Please see the paper (p19) for details.

3.Improve Accuracy with Synthetic Data

Papers including this one have been published in late 2023, focusing on using the Reward model to create high-quality synthetic data for model fine-tuning and accuracy improvement. Vigorous research is expected to continue in 2024, yielding various results. Especially in the LLM field, collecting high-quality training data is becoming increasingly difficult, and fine-tuning with synthetic data is anticipated as a solution.

How was it? The improvement in model accuracy with synthetic data is expected to be a very effective development method for startups like us, who cannot collect vast amounts of data independently. Our blog will continue to follow these synthetic data and other technological innovations, so stay tuned. Wishing you a great year!

1) “REST MEETS REACT: SELF-IMPROVEMENT FOR MULTI-STEP REASONING LLM AGENT" Renat Aksitov†1 , Sobhan Miryoosefi†1 , Zonglin Li†1 , Daliang Li†1 , Sheila Babayan†2 , Kavya Kopparapu†2 , Zachary Fisher1 , Ruiqi Guo1 , Sushant Prakash1 , Pranesh Srinivasan3 , Manzil Zaheer2 , Felix Yu1 , and Sanjiv Kumar1,    1Google Research, 2Google DeepMind, 3Google †Core contributors, 15 Dec 2023, https://arxiv.org/abs/2312.10003

Copyright © 2023 Toshifumi Kuga. All right reserved

Notice: ToshiStats Co., Ltd. and I do not accept any responsibility or liability for loss or damage occasioned to any person or property through using materials, instructions, methods, algorithms or ideas contained herein, or acting or refraining from acting as a result of such use. ToshiStats Co., Ltd. and I expressly disclaim all implied warranties, including merchantability or fitness for any particular purpose. There will be no duty on ToshiStats Co., Ltd. and me to correct any errors or defects in the codes and the software.

The era of "agent-style applications" has arrived, earlier than expected and seems to be accelerating even further

On November 6, the OpenAI DevDay was held, marking its first annual developer's conference. The technological developments since the debut of GPT-4 in March 2023 were introduced at once. There's too much to cover comprehensively, so I'll leave that to OpenAI CEO Sam Altman, but here I want to raise three key points I've considered and explore them further.

1. Price is Key

The anticipated price reduction has been realized. GPT-4 is roughly about 65% off. Of course, the reduction varies depending on usage. I've already tried the new GPT-4 Turbo for half a day, and it cost about $5, which would have definitely exceeded $10 before. This makes it more viable for Proof of Concept (PoC) use. It seems the time has come to utilize GPT-4's still unseen potential in various areas. A wallet-friendly approach is a welcome change for everyone.

2. Building AI Apps Without Being a Programmer

At this developer's conference, I noticed many features that operate with no-code. GPTs, which allow creation of customized ChatGPT in a dialogue format, is a prime example. The developer-oriented Assistants API also doesn't require coding if used with the Playground. With the code interpreter tool already implemented, writing prompts to invoke and execute it automates the rest. This is impressive.

I implemented a model to calculate default probabilities using a step-by-step prompt, from 1 to 5, with the code-interpreter turned on, without writing any specific code. When executed, the model was successfully created, and it performed tasks like calculating AUC and generating histograms as instructed.

3. Easy Construction of "Agent-Style Applications"

Listening to OpenAI CEO Sam Altman's presentation, I felt a strong emphasis on agents. The Playground Tool includes function calling, which seems to make it much easier to create agents that determine their next actions based on situations. While open-source implementations of agents have been increasing, I didn't expect them to be implemented this quickly on the OpenAI platform. Paired with GPTs, the year of 2024 feels like it could be the first year of "agent-style applications." This is truly exciting.

How about these new services? Following the announcements at DevDay, developers worldwide seem to be thinking about various AI applications. I'm also eager to start creating an agent-style application. Stay tuned!

Copyright © 2023 Toshifumi Kuga. All right reserved

Notice: ToshiStats Co., Ltd. and I do not accept any responsibility or liability for loss or damage occasioned to any person or property through using materials, instructions, methods, algorithms or ideas contained herein, or acting or refraining from acting as a result of such use. ToshiStats Co., Ltd. and I expressly disclaim all implied warranties, including merchantability or fitness for any particular purpose. There will be no duty on ToshiStats Co., Ltd. and me to correct any errors or defects in the codes and the software.

New Prompt Engineering Method from Google DeepMind Surpassing CoT in Accuracy !

Hello everyone, how have you been? There are only two months left in this year. It has truly been a year of incredible AI advancements, and it doesn't seem to be slowing down. Recently, Google DeepMind announced a new prompt-engineering method called "Step-Back Prompting (1)." Let's dive into the details right away.

1. Step-Back Prompting:

Coming from DeepMind, one might initially think it's a complicated method, but the concept turned out to be quite simple. Instead of directly answering the question input by the user, the process involves:

• Creating a more generalized and essential question (Stepback Question)

• Answering the generated question (Stepback Answer)

• Producing the final answer to the user based on the original question and the generated response (Final Answer)

The paper abstract has the following note which could give insights on the Stepback Answer:

"The purpose of abstraction is not to be vague, but to create a new semantic level in which one can be absolutely precise. — Edsger W. Dijkstra"

2. Automatic Generation of "Stepback Question":

The key to this method seems to be the effective creation of the Stepback Question. However, constantly coming up with the Stepback Question could be challenging. While searching for an easier way, an excellent automatic generation method was introduced in LangChain's cookbook (2), which seems to apply Few shot learning.

By presenting these two examples to the model first, when a new user question like "Was ChatGPT around when Trump was president?" is posed,

As shown, a more general question, "When was ChatGPT developed?" is generated. Using this to guide the final answer results in higher accuracy. Although not always 100% correct based on my own trials, the accuracy does seem notably higher. According to the paper, it even achieves accuracy surpassing GPT-4 in some instances.

3. Anticipation for Future Developments:

Since "Step-Back Prompting" has a simple structure, it seems versatile for various applications. It can also be combined with existing techniques like CoT. Looking forward to its future growth, it seems highly compatible with LangChain and easy to implement, which will likely lead to an increase in use cases.

So, what do you think? I will continue to experiment and if there are any significant findings, I'll share them here. Stay tuned!

1) “TAKE A STEP BACK: EVOKING REASONING VIA ABSTRACTION IN LARGE LANGUAGE MODELS" Huaixiu Steven Zheng∗ Swaroop Mishra∗ Xinyun Chen Heng-Tze Cheng Ed H. Chi Quoc V Le Denny Zhou Google DeepMind” Shunyu Yao, Dian Yu, Jeffrey Zhao, Izhak Shafran, Thomas L. Griffiths, Yuan Cao, Karthik Narasimhan, Google DeepMind, 9 Oct 2023, https://arxiv.org/abs/2310.06117

2) langchain/cookbook/stepback-qa.ipynb https://github.com/langchain-ai/langchain/blob/master/cookbook/stepback-qa.ipynb

Copyright © 2023 Toshifumi Kuga. All right reserved

Notice: ToshiStats Co., Ltd. and I do not accept any responsibility or liability for loss or damage occasioned to any person or property through using materials, instructions, methods, algorithms or ideas contained herein, or acting or refraining from acting as a result of such use. ToshiStats Co., Ltd. and I expressly disclaim all implied warranties, including merchantability or fitness for any particular purpose. There will be no duty on ToshiStats Co., Ltd. and me to correct any errors or defects in the codes and the software.

GPT-4V is here. I tried it immediately and was amazed. It can do this too!

Sorry to keep you waiting. OpenAI's GPT-4 now comes with image recognition capabilities. To be precise, it was demonstrated when it debuted in March of this year, but it has only now been made available to users after half a year. I recently tried the new feature in ChatGPT+ and, in a word, it's incredible!

By the way, the image mentioned above was also created with a combination of GPT-4 and DALL-E3.

Now, let's start the experiment!

First, we'll start with recognizing mobile-phones. It can accurately count the number of mobile-phones. This is a piece of cake.

I thought flight information would be challenging, but it identified the destination impeccably. Since it's originally an excellent language model, it seems proficient in deriving meaning from images.

It can even read Osaka's Tsutenkaku tower. Local information is no problem.

For a change, I inserted an image of analysis results. It can read graphs effortlessly. This is impressive!

What shocked me was that it could easily count cars. Of course, it's not a specialized object detection model, so errors will always occur. I believe there were about 48 cars in this photo, but for general use, this margin of error seems acceptable. It's astonishing what it can do by just being given an image.

It can count cans, but the error is relatively significant. It might struggle with cluttered items.

It works well to read English text in an OCR-like manner.

It can also easily read the time displayed on electronic signboards.

How did you find it? Without any fine-tuning, it achieved this much. GPT-4V has just been launched, and various use cases are likely to emerge in the future. I look forward to introducing interesting examples here as they arise. Stay tuned!

Copyright © 2023 Toshifumi Kuga. All right reserved

Notice: ToshiStats Co., Ltd. and I do not accept any responsibility or liability for loss or damage occasioned to any person or property through using materials, instructions, methods, algorithms or ideas contained herein, or acting or refraining from acting as a result of such use. ToshiStats Co., Ltd. and I expressly disclaim all implied warranties, including merchantability or fitness for any particular purpose. There will be no duty on ToshiStats Co., Ltd. and me to correct any errors or defects in the codes and the software.

Fine-tuning GPT-3.5 with synthetic text generated by GPT-4. The accuracy has improved! In the future, we might not even need training text???

Hello, despite being in the latter half of September, it is still quite hot in Japan. The photos feel mismatched, but I'm deliberately sticking to the autumn theme, hoping it will get cooler soon. However, it might stay hot for the rest of the month.

Now, about the fine-tuning of ChatGPT-3.5 that I introduced the other day, it's certainly a hot topic. I think there is a strong demand in companies to specialize its performance for specific tasks. For this reason, we conducted an experiment assuming cases where you would want to proceed even without data at hand by generating synthetic text and then fine-tuning it.

1. Experiment Details

Just like the previous experiment, we set a task to determine which financial product a given English-language complaint is about. They are complaints for the banking industry, so the task involves differentiating between six types of financial products such as mortgages and bank accounts. The data used for fine-tuning was minimal, with 100 samples for validation, just like last time. However, the training data is different this time. We generated customer complaint emails using GPT-4, and they are indistinguishable from real ones at a glance. GPT-4's performance is indeed impressive. We generated 15 similar customer complaints for training and then proceeded with fine-tuning.

synthetic text generated by GPT-4

2. Experiment Results

Since this was our first time using synthetic text, we were worried about the outcome, but we were able to confirm the effectiveness of fine-tuning as follows. Though the improvement isn't dramatic with just 15 samples, the accuracy for this task has improved compared to the base GPT-3.5, which had an accuracy of 0.5 to 0.55.

For more details on the experiment, please refer to this notebook.

3. Discussion

Fine-tuning with synthetic text was a method not even considered before, but with the arrival of GPT-4, it's becoming more realistic. There are several points to consider, such as the number of samples and how to write prompts, but the advantage of being able to start even without data is significant. Currently, GPT-4 is the only option for generation models, but it seems like new models like Gemini from Google will also be available next year. Technology is advancing rapidly, so we can expect a lot more in the future.

So, what did you think? We will continue to conduct various experiments and share our findings here. See you again soon!

Copyright © 2023 Toshifumi Kuga. All right reserved

Notice: ToshiStats Co., Ltd. and I do not accept any responsibility or liability for loss or damage occasioned to any person or property through using materials, instructions, methods, algorithms or ideas contained herein, or acting or refraining from acting as a result of such use. ToshiStats Co., Ltd. and I expressly disclaim all implied warranties, including merchantability or fitness for any particular purpose. There will be no duty on ToshiStats Co., Ltd. and me to correct any errors or defects in the codes and the software.

The "Graph of Thoughts" might pave the way for new avenues in "human and LLM (Large Language Model) collaboration"!

Last week, I came across an intriguing paper on Large Language Models (LLMs). It appears to further develop the "Tree of Thoughts" (ToT) reasoning method I mentioned before, introducing a new technique called the "Graph of Thoughts" (GoT). Let's take a closer look.

1. Features of GoT

First, let's compare various methods using the chart provided in the paper.

The far right shows the newly introduced GoT. Key differences from ToT may be that GoT allows for the merging of thoughts, and that users can define the shape of the GoT themselves. Incidentally, this merging is referred to as "aggregation" within the paper. While it may seem similar to ToT, the differences might be significant. Let's explore this in more detail.

2. Four Key Modules

GoT (Graph of Thoughts) has the following four crucial modules. Understanding these will clarify the differences between it and ToT (Tree of Thoughts).

• Prompter

• Parser

• Scoring & Validation

• Controller

Let's look at each one in detail. The Prompter, as the name suggests, is the module responsible for creating prompts. The Parser extracts the required information, or "thoughts," from the LLM (Large Language Model). You might think of the Prompter as handling input and the Parser as managing output. Scoring & Validation is the module that evaluates the gathered thoughts. This evaluation allows us to select the thoughts worth keeping. Finally, let's elaborate on the Controller. It is responsible for adding new thoughts or merging multiple thoughts, a process referred to as "transform." The Controller decides which transformations should be applied to which thoughts and passes this information to the Prompter. It is a critical module for executing problem-solving strategies. It has two functions: Graph of Operations (GoO), which is an execution plan for operations defined by the user, and Graph Reasoning State (GRS), which maintains the ongoing LLM reasoning process based on the thought state.

3. Considering the Number Sorting Problem

Since merely talking abstractly may not advance understanding, let's consider an actual task. This time we will consider sorting a list of 64 numbers in ascending order. Here, we'll see how the Graph of Operations (GoO) comes into play. In the chart below, each thought is tagged with operations like G (Generate), S (Sort), K (Keep the best), and A (Merge). Initially, we take a list of 64 numbers and divide it into four lists, each containing 16 numbers. Each of these lists is then sorted and evaluated. Only the list with the highest accuracy is kept. These are then further merged to form a new list containing 32 numbers. You'll see various operations functioning as the process progresses.

For those who want to delve deeper, detailed explanations are available here, particularly in the green part of the chart above.

It might feel complex at a glance, but it's user-controllable, allowing you to incorporate your domain knowledge. I am excited to conduct various experiments in the future.

Thank you for your attention! I will keep you updated on the progress of GoT and hope to share more with you soon. Stay tuned!

1) "Graph of Thoughts: Solving Elaborate Problems with Large Language Models",  Maciej Besta, Nils Blach, Ales Kubicek, Robert Gerstenberger, Lukas Gianinazzi, Joanna Gajda, Tomasz Lehmann, Michal Podstawski, Hubert Niewiadomski, Piotr Nyczyk, Torsten Hoefler, 21 Aug 2023, https://arxiv.org/abs/2308.09687v2

Copyright © 2023 Toshifumi Kuga. All right reserved

Notice: ToshiStats Co., Ltd. and I do not accept any responsibility or liability for loss or damage occasioned to any person or property through using materials, instructions, methods, algorithms or ideas contained herein, or acting or refraining from acting as a result of such use. ToshiStats Co., Ltd. and I expressly disclaim all implied warranties, including merchantability or fitness for any particular purpose. There will be no duty on ToshiStats Co., Ltd. and me to correct any errors or defects in the codes and the software.

Fine-tuning has come to ChatGPT. Its effects are outstanding, and if implemented according to the task, we can perhaps expect significant improvements in accuracy!!

Hello everyone, how are you doing? Although the illustration is autumn-like, it seems that summer will stick around for a while in Japan

While that was happening, I suddenly received a message from OpenAI saying, "The fine-tuning feature has been implemented." I have always fine-tuned open-source models, so I was a little disappointed that ChatGPT didn't have this feature. But it seems that it has finally made its appearance. I guess OpenAI got a little serious. Let's get started right away.

1. Is fine-tuning effective for ChatGPT?

I'm sure you all want to know, "Does fine-tuning work well with ChatGPT?" So I created a small dataset and conducted a simple experiment. To put it briefly, "Something amazing is happening!" Below is the table with the results.

Accuracy for 100 samples

I had GPT3.5 perform a 6-class classification task and expected some fine-tuning effects. However, exceeding an accuracy of 0.8 was unexpected. The normal GPT3.5 only barely surpassed 0.5, so I initially thought that the model's potential was lacking. However, an accuracy of 0.88 appeared on the first fine-tuning, which was hard to believe. Upon changing the seed and refreshing the data, it still yielded an accuracy near 0.8, completely different from the normal accuracy. The compatibility between fine-tuning and ChatGPT must be outstanding.

2. Experiment Details

In this experiment, the task was to identify what type of financial product a given English complaint was about. This is a task of classifying 6 different financial products such as home loans or bank accounts, and the data used for fine-tuning consisted of 100 samples each for training and validation, which is a minimum configuration. The training results show a decrease in training loss and eventually seem to reach zero (actually it continues to go down further). Quick conclusion: it went well. Using this fine-tuned model yielded the results mentioned in section 1.

3. Discussion

Just by looking at the results of this experiment, we can't definitively say that fine-tuning always succeeds. Various cases will emerge in the future, and it will be important to make comprehensive judgments based on those results. Especially this time, minimal prompt engineering was done. Combining prompt engineering and fine-tuning to achieve the best performance is a future challenge. There are many points to consider, like cost and computation time. It will require trial and error. While GPT-4 indeed performs well with an accuracy around 0.8 for this task, its cost is high, and implementation isn't always straightforward. Even in such cases, the new weapon of fine-tuning has come into our hands, increasing our options and potentially moving us a step forward in problem-solving.

How was it? I would like to introduce more experiments and their results here in the future. Stay tuned!

Copyright © 2023 Toshifumi Kuga. All right reserved

Notice: ToshiStats Co., Ltd. and I do not accept any responsibility or liability for loss or damage occasioned to any person or property through using materials, instructions, methods, algorithms or ideas contained herein, or acting or refraining from acting as a result of such use. ToshiStats Co., Ltd. and I expressly disclaim all implied warranties, including merchantability or fitness for any particular purpose. There will be no duty on ToshiStats Co., Ltd. and me to correct any errors or defects in the codes and the software.

"Llama2" is a great LLM as it is Open source and for commercial use. I want to try many applications with this language model.

Llama2 website https://ai.meta.com/llama/

Hi friend, I would like to introduce a new LLM, which was released from Meta on July 18,2023. It is called “Llama2”. I have some experiments with this model. Let us start!

1. What is Llama2?

“Llama2” is language model from Meta AI. Many researchers are very excited because it is a open source and available for commercial usage. Its specs are explained in the table below.

Llama2 website https://ai.meta.com/llama/

2. Let us extract information from the article in English

I want to perform a small experiment to extract information from text.

• sentiment

• root cause of the sentiment

• name of product

• name of makers of product

I made my prompt and fiction story in the mail. Then run Llama2 13B chat. Here are the results

Woh, looks good! I can obtain the information I need from text. Unfortunately the model cannot output it in Japanese.

3. Let us see how it works against Japanese sentences

Next, I would like to apply the same prompt against Japanese sentences here.

Woh, looks good, too! Although the model cannot output it in Japanese, either.

4. Llama2 has a great potential for AI applications in the future!

Today I found that Llama2 works in English very well. When we want to minimize running costs for AI applications or keep secret/confidential data within our organization, this model can be a good candidate for AI models in our applications. It is great to have many choices of LLMs in addition to proprietary models, such as ChatGPT.

I want to mention a great repo on GitHub. It makes it easier to compare many open source LLMs, It is a strong recommendation for everyone who is interested in LLMs. Thanks camenduru!

Thanks for your attention! would like to follow the progress of Llama2 and share it with you soon. Stay tuned!

Copyright  ©  2023  Toshifumi Kuga  All right reserved

Notice: ToshiStats Co., Ltd. and I do not accept any responsibility or liability for loss or damage occasioned to any person or property through using materials, instructions, methods, algorithms or ideas contained herein, or acting or refraining from acting as a result of such use. ToshiStats Co., Ltd. and I expressly disclaim all implied warranties, including merchantability or fitness for any particular purpose. There will be no duty on ToshiStats Co., Ltd. and me to correct any errors or defects in the codes and the software.

"Tree of Thoughts" can go mainstream in prompt engineering!

Today, I found a very interesting paper called “Tree of Thoughts (ToT)”(1). With ToT, we can solve the tasks, where we could not do it before. So I want to share it with you and consider how it works together. Let us start now!

1.Chain of Thoughts (CoT)

This paper provides four kinds of prompting as the chart below says. The left one is called “IO prompting” and is relatively simple. The right one is the most complex, called “Tree of Thoughts (ToT)”.

Among four kinds of prompting, I focus on Chain of Thoughts (CoT) first because it gives us a fundamental space to explore. The paper says “The key idea is to introduce a chain of thoughts z1, · · · , zn to bridge x and y, where each zi is a coherent language sequence that serves as a meaningful intermediate step toward problem solving“. By CoT, we explore a prompting method for improving the reasoning abilities of LLMs and solve complex tasks effectively. Once we understand how CoT works, let us move on ToT.

2. Tree of Thoughts (ToT)

Let us expand CoT with tree search so that we can apply it to more complex tasks effectively. This paper says “we introduce a new framework for language model inference, Tree of Thoughts (ToT), which generalizes over the popular Chain of Thought approach to prompting language models, and enables exploration over coherent units of text (thoughts) that serve as intermediate steps toward problem solving.”. Sounds great! OK, let us consider how it works.

ToT has four steps to implement it. I would like to explain them step by step.

• decompose the process into thoughts

  • each thought should be small enough so that LLMs can generate promising and diverse samples

• generate states

  • generate potential thoughts from each state. There are two kinds of methods to do this according to this paper.

• evaluate each state

  • LLMs evaluate each state to decide how a tree should grow

• search for the best state

  • If the current state is not good enough, we should search into other branches. There are several search algorithms to do that.

3. ToT can be solved by MCTS

Although ToT can be solved with relatively simple Tree Search algorithms, we can use more advanced algorithms, such as Monte Carlo Tree Search (MCTS). It has been famous since AlphaGo defeated a professional human Go player in March 2016. In AlphaGo, MCTS is combined with Neural network. This is sometimes called “model guided Tree Search” and we do not need to search for the whole possible state anymore. In the picture, Demis Hassabis, Google DeepMind CEO, explained how it works(2).

It must be exciting when ToT can be searched by MTCS in the near future as wider and deeper states can be explored and it must provide us good results.

Thanks for your attention! I would like to follow the progress of ToT and share it with you soon. Stay tuned!

1) “Tree of Thoughts: Deliberate Problem Solving with Large Language Models” Shunyu Yao, Dian Yu, Jeffrey Zhao, Izhak Shafran, Thomas L. Griffiths, Yuan Cao, Karthik Narasimhan, 17 May 2023, https://arxiv.org/abs/2305.10601

2) Using AI to Accelerate Scientific Discovery | Campus Lecture with Demis Hassabis, https://www.youtube.com/watch?v=Ds132TzmLRQ&t=1381s

Copyright  ©  2023  Toshifumi Kuga  All right reserved

Notice: ToshiStats Co., Ltd. and I do not accept any responsibility or liability for loss or damage occasioned to any person or property through using materials, instructions, methods, algorithms or ideas contained herein, or acting or refraining from acting as a result of such use. ToshiStats Co., Ltd. and I expressly disclaim all implied warranties, including merchantability or fitness for any particular purpose. There will be no duty on ToshiStats Co., Ltd. and me to correct any errors or defects in the codes and the software.

“Function calling” is a game changer as GPT can access outside and be converted to our agents easily!

Today, I want to create web-site with a description of the Japanese sweets collection, just like “Dorayaki“ in the picture above. So I ordered my AI agent to create an awesome web-site. But is it really possible? I am sure yes, it is!. As you know, OpenAI created GPT, which is very intelligent large language model (LLM). On 13 June 2023, “Function calling” was introduced by OpenAI. It can bridge GPT to other systems, APIs and functions outside. Let me explain step by step!

1.What is the advantage of “Function calling”?

Function calling makes it easy for GPT to access functions outside. For example, when you want to create a web-site where Japanese sweets are explained to customers, you need to connect GPT to the function that can write code of web-site with HTML/CSS. With “Function calling”, GPT can call this function and pass the parameters, such as “explanations of Japanese sweets” to this function. Official documents says “The latest models (gpt-3.5-turbo-0613 and gpt-4-0613) have been fine-tuned to both detect when a function should to be called (depending on the input) and to respond with JSON that adheres to the function signature.”

2. The list of “functions” is key to set “function calling” up

“Function calling”looks great! But how can we implement in our code. I think it is so simple. Just prepare the list of functions. This should have

• "name"

• "description"

• "parameters" : "type" , "properties", "required"

In ChatCompletion.create, we should add “functions=functions” because we want to call the function. The other part of the code has not changed so much. The code below shows us an example of functions, which comes from Official documents. Please look at these docs for the details if needed.

3. Let us see how the generated web looks like

OK, it is the time that we see the result from our agent. I instruct "Create a web-site for a pretty Japanese sweets collection" to our agent. Text of “title” and “explanation” are generated by GPT3.5-turbo and are sent to the function that creates a web. Here is the result. All are written in Japanese. The title means “a pretty Japanese sweets collection". The sentences of the explanation are pretty good! I do not think there is a need to fix or modify these sentences at all.

If you want to know more details with the code, you can see it here.

https://github.com/TOSHISTATS/Wagashi-Collection-Web-Generation-agent-by-GPT3.5#readme

Hope you can understand how AI agents work. I think potential use-cases of “Function calling”are limitless. I tried several use cases by “Function calling” and found that it can be a game changer to develop LLM application systems. I would like to update my article about AI agents by OpenAI GPT soon. Stay tuned!

Copyright ©  2023  Toshifumi Kuga.  All right reserved

Notice: ToshiStats Co., Ltd. and I do not accept any responsibility or liability for loss or damage occasioned to any person or property through using materials, instructions, methods, algorithms or ideas contained herein, or acting or refraining from acting as a result of such use. ToshiStats Co., Ltd. and I expressly disclaim all implied warranties, including merchantability or fitness for any particular purpose. There will be no duty on ToshiStats Co., Ltd. and me to correct any errors or defects in the codes and the software.

"Large Language Models as Tool Makers" is a good idea to enhance the accuracy of the model while keeping the cost of computation low!

Since GPT4 , one of the most intelligent Large Language Model (LLM) in the world, was released on 14 March 2023, many people are surprised because it is very intelligent. This is great. But there is one problem for users. It is not free service. Users should pay the fee of GPT4, based on how much tokens they use on GPT4. Therefore when we continue to use GPT4 all day long, it must be very expensive. Of course we prefer more intelligence. But we should consider the cost of it. There is a trade off between them. What should we do to solve it? Last week, I found a good research paper called “Large Language Models as Tool Makers“(1). All charts below come from this awesome paper. The idea is simple and looks promising to tackle these problems. So let me explain more details.

1. Tool user and Tool maker

The basic idea is as follows. Let us have two LLMs, one is called “Tool maker” and another is called “Tool user”. When a new task comes to us, Tool maker create “tools” for this task. Once “tools” are ready, they are passed to Tool user for inference. These tools are reusable to solve similar tasks in the future. So GPT4 can be used only as Tool maker as it should be more intelligent. Light weights models, such as GPT3.5, can be used as a Tool user. Then we can reduce the cost of computation for inference. It sounds great! The chart below explains how it works.

2. How can we create tools for our task?

As we want to keep the accuracy of the results, Tool maker should create better tools. There are three steps to do that.

• Tool Proposing: The tool maker generates a Python function to solve the given task. If the proposed tool makes errors, the tool maker makes another tool.

• Tool Verification: The tool maker generates unit tests using validation samples and subsequently executes these tests. 3 validation samples are prepared here. If the tool fails any of these tests, the tool makes an attempt to fix the issues. The paper explains it as follows “This stage fulfills two key roles: 1) it provides examples that demonstrate how to convert natural language questions into function calls, and 2) it verifies the tool’s reliability, enabling the entire process to be fully automated.”

• Tool Wrapping: If the execution or verification passes the preset threshold, tool maker prepares the wrapped tool for tool user. This step involves wrapping up the function code and providing demonstrations of how to convert a task into a function call. This final product is then ready for use by the tool user.

The chart below shows us how it works.

Once the tool is ready, the tool is passed to the tool-user. The tool user should solve various instances of the task by using tools made by the Tool maker. The prompt for this stage is the wrapped tool which contains the function for solving the task and demonstrations of how to convert a task query into a function call. With the demonstrations, tool user can then generate the required function call in an in-context learning fashion. The function calls are then executed to solve the task. The chart below shows us how the processes from Tool maker to Tool user are going.

3. Can we confirm if tools that fit our tasks are available or not?

Here, we use a third LLM called “the dispatcher”. Because the dispatcher maintains a record of existing tools produced by the tool maker, it can confirm if tools that fit our task are available at the time when a task is received, If no appropriate tool is found, the dispatcher identifies the instance as a new task and solves the instance with a powerful model, such as GPT4. The dispatcher’s workflow is shown here.

That is it! This is a major part of “Large Language Models as Tool Makers” or “LATM” in short. By LATM, we might reduce computational cost for heavy models, such as GPT4. It is amazing! Hope you enjoy the article today. I will update new technologies around LLM in the near future. Stay tuned!

1) “Large Language Models as Tool Makers” Tianle Cai, Xuezhi Wang, Tengyu Ma, Xinyun Chen, Denny Zhou, 26 May 2023, https://arxiv.org/abs/2305.17126

Copyright  ©  2023  Toshifumi Kuga  All right reserved

Notice: ToshiStats Co., Ltd. and I do not accept any responsibility or liability for loss or damage occasioned to any person or property through using materials, instructions, methods, algorithms or ideas contained herein, or acting or refraining from acting as a result of such use. ToshiStats Co., Ltd. and I expressly disclaim all implied warranties, including merchantability or fitness for any particular purpose. There will be no duty on ToshiStats Co., Ltd. and me to correct any errors or defects in the codes and the software.

LLM can be "reasoning engine" to create our agents. It must be a game changer!

Recently, Large Language model (LLM) is getting more attractions all over the world. Google released their new LLM called “PaLM 2” on 10 May 2023. It starts competing against “ChatGPT” which was released in Nov 2022 and attracts over 100 million users in just two months. LLM is expected to be more intelligent in a short period as competition between big IT companies is getting tough. What does it mean to us? . Let us consider step by step!

1. How can we create our own agent?

In my article in Feb 2023, I said AI can be our agent which understands our languages. Let us consider how it is possible step by step. When I want to eat lunch. I just order my agent, saying “I would like to have lunch”, LLM can understand what I say and try to order my favorite hamburger at the restaurant. For LLM to act against the outside world (such as call restaurants), it needs some tools, which can be created with libraries such as “LangChain”. Then LLM can order my lunch and finally I can have lunch, anyway. It sounds good. Let us move deeper.

2. LLM is not just an “interface” to us with natural languages.

As I said in Feb this year, the first time I used ChatGPT, I felt like it could understand what I said. But now I do not think it is just an“interface” any more. Because LLM is trained with massive amounts of text from the web, books and other sources, LLM obtains a lot of knowledge of human beings from the past to the present. Since Chat GPT appeared in front of us last year, I performed many experiments with LLM and found that LLM has an ability to make decisions. Although it is not perfect, it sometimes performs at the same level as human beings. It is amazing! In addition to that, LLM is still in the early stage and evolves on a daily basis!

3. LLM will be more and more intelligent as a “reasoning engine”!

Mr. Sam Altman, OpenAI CEO says in youtube “ChatGPT may be a reasoning engine”(1). I completely agree with his opinion. When we create our agents, LLM works as a “reasoning engine” to make decisions to solve complex tasks. Around LLM, there are many systems to act against the outside world, such as “search web” or “shop in e-commerce”. All we have to do is think “how can we enable LLM make the right decisions”. Because LLM is very new for everyone, no one knows the right answer. Fortunately, LLM can understand our languages, it may not need programming anymore. It is very important for us. So let us consider step by step!

I would like to update the progress of AI agents. Stay tuned!

1) Sam Altman: OpenAI CEO on GPT-4, ChatGPT, and the Future of AI | Lex Fridman Podcast #367 https://www.youtube.com/watch?v=L_Guz73e6fw&t=867s (around 14:25)

Copyright  ©  2023  Toshifumi Kuga  All right reserved

Notice: ToshiStats Co., Ltd. and I do not accept any responsibility or liability for loss or damage occasioned to any person or property through using materials, instructions, methods, algorithms or ideas contained herein, or acting or refraining from acting as a result of such use. ToshiStats Co., Ltd. and I expressly disclaim all implied warranties, including merchantability or fitness for any particular purpose. There will be no duty on ToshiStats Co., Ltd. and me to correct any errors or defects in the codes and the software.