DEV Community

Evan Lin
Evan Lin

Posted on • Originally published at evanlin.com on

NV TW LLM Developer Day 2024: Conference Notes

title: [Conference Notes] NV TW LLM Developer Day 2024
published: false
date: 2024-01-11 00:00:00 UTC
tags: 
canonical_url: http://www.evanlin.com/conf-nv-llm-devday/
---

# Event Information

NVIDIA LLM Developer Day https://www.nvidia.com/zh-tw/events/llm-developer-day/ "LLM Developer Day"

09:30 - 11:00 Taiwan Time - Session 1: A Fast Path to Developing Large Language Models (LLMs): [slide](https://on24static.akamaized.net/event/44/33/88/7/rt/1/documents/resourceList1704771459472/llmdevdaysession1taiwanwilliam1704771459472.pdf)

11:10 - 12:50 Taiwan Time - Session 2a: Customizing Your Own Large Language Model Applications: [slides](https://on24static.akamaized.net/event/44/33/90/1/rt/1/documents/resourceList1704769052626/llmdevdaysession2taiwan11704769052626.pdf)

15:30 Taiwan Time - Session 2b: Large Language Models and Generative AI in Biosciences:

17:10 Taiwan Time - Session 3: Running Your Own Large Language Model: https://event.on24.com/wcc/r/4434877/5BF24840196B1DF37683894D98322008

# Session 1: A Fast Path to Developing Large Language Models (LLMs)

## Case (1) - Customer Service System for a Music Company

![image-20240111095051777](http://www.evanlin.com/images/2022/image-20240111095051777.png) ![image-20240111095054776](http://www.evanlin.com/images/2022/image-20240111095054776.png)

- The first case: Using LLM for the customer service system of a musical instrument company.
- Receive customer emails, customer tags
- Find possible RAG responses based on the questions. (Displayed below), helping customer service respond.

**Thoughts:**

- It's a bit strange to use OpenAI instead of LLAMA for NV DevDay.
- The OpenAI version inside is < 1.0, but the OpenAI package was already updated to 1.0 on 11/07. (Because I was also caught off guard at the time)

### 1.1 Interpreting the email prompt

![image-20240111095509845](http://www.evanlin.com/images/2022/image-20240111095509845.png)

- List the good and bad points separately.
- Classify urgency.
- Determine the tone of the email
- Structured output

### 1.2 Analysis Prompt

![image-20240111095935738](http://www.evanlin.com/images/2022/image-20240111095935738.png)

- Data processing prompt

![image-20240111100529570](http://www.evanlin.com/images/2022/image-20240111100529570.png)

- Formatting output prompt

![image-20240111100620053](http://www.evanlin.com/images/2022/image-20240111100620053.png)

- Define user data flow through [COLANG](https://www.colanginstitute.org/).

### Unreleased product Nemotron-3

![image-20240111102836188](http://www.evanlin.com/images/2022/image-20240111102836188.png)

- NeVA (NeMo Vision and Language Assistant)

#### Other:

GTC 2024 - Physical GTC 03/18

# More References:

- [COLANG](https://www.colanginstitute.org/)
Enter fullscreen mode Exit fullscreen mode

Top comments (0)