hendrycks/competition_math
Updated
•
141
liushuiyouyi
ntdas
AI & ML interests
Language Modeling, LLM Alignment
Recent Activity
liked
a dataset
3 months ago
hendrycks/competition_math
new activity
5 months ago
LR-AI-Labs/vbd-llama2-7B-50b-chat:Update README.md
liked
a dataset
6 months ago
longhoang06/vi-ovm-dataset
Organizations
ntdas's activity
liked
a
dataset
3 months ago
Update README.md
1
#1 opened 5 months ago
by
IAMJB
liked
a
dataset
6 months ago
reacted to
singhsidhukuldeep's
post with 🔥
6 months ago
Post
2763
What is the best LLM for RAG systems? 🤔
In a business setting, it will be the one that gives the best performance at a great price! 💼💰
And maybe it should be easy to fine-tune, cheap to fine-tune... FREE to fine-tune? 😲✨
That's @Google Gemini 1.5 Flash! 🚀🌟
It now supports fine-tuning, and the inference cost is the same as the base model! <coughs LORA adopters> 🤭🤖
So the base model must be expensive? 💸
For the base model, the input price is reduced by 78% to $0.075/1 million tokens and the output price by 71% to $0.3/1 million tokens. 📉💵
But is it any good? 🤷♂️
On the LLM Hallucination Index, Gemini 1.5 Flash achieved great context adherence scores of 0.94, 1, and 0.92 across short, medium, and long contexts. 📊🎯
Google has finally given a model that is free to tune and offers an excellent balance between performance and cost. ⚖️👌
Happy tuning... 🎶🔧
Gemini 1.5 Flash: https://developers.googleblog.com/en/gemini-15-flash-updates-google-ai-studio-gemini-api/ 🔗
LLM Hallucination Index: https://www.rungalileo.io/hallucinationindex 🔗
In a business setting, it will be the one that gives the best performance at a great price! 💼💰
And maybe it should be easy to fine-tune, cheap to fine-tune... FREE to fine-tune? 😲✨
That's @Google Gemini 1.5 Flash! 🚀🌟
It now supports fine-tuning, and the inference cost is the same as the base model! <coughs LORA adopters> 🤭🤖
So the base model must be expensive? 💸
For the base model, the input price is reduced by 78% to $0.075/1 million tokens and the output price by 71% to $0.3/1 million tokens. 📉💵
But is it any good? 🤷♂️
On the LLM Hallucination Index, Gemini 1.5 Flash achieved great context adherence scores of 0.94, 1, and 0.92 across short, medium, and long contexts. 📊🎯
Google has finally given a model that is free to tune and offers an excellent balance between performance and cost. ⚖️👌
Happy tuning... 🎶🔧
Gemini 1.5 Flash: https://developers.googleblog.com/en/gemini-15-flash-updates-google-ai-studio-gemini-api/ 🔗
LLM Hallucination Index: https://www.rungalileo.io/hallucinationindex 🔗
- 1 reply
liked
a
dataset
10 months ago
reacted to
chiphuyen's
post with ❤️
12 months ago
Post
It feels awkward having my first post sharing my stuff, but this is a weekend project that I really enjoyed working on. I'd love to meet more people interested in random ideas like this.
A hard part of building AI applications is choosing which model to use. What if we don’t have to? What if we can predict the best model for any prompt?
Predictive human preference aims to predict which model users might prefer for a specific query.
https://huyenchip.com/2024/02/28/predictive-human-preference.html
One use case is model routing. If we know in advance that for a prompt, users will prefer Claude Instant’s response over GPT-4, and Claude Instant is cheaper/faster than GPT-4, we can route this prompt to Claude Instant. Model routing has the potential to increase response quality while reducing costs and latency.
One pattern is that for simple prompts, weak models can do (nearly) as well as strong models. For more challenging prompts, however, users are more likely to prefer stronger models. Here’s a visualization of predicted human preference for an easy prompt (“hello, how are you?”) and a challenging prompt (“Explain why Planc length …”).
Preference predictors make it possible to create leaderboards unique to any prompt and domain.
A hard part of building AI applications is choosing which model to use. What if we don’t have to? What if we can predict the best model for any prompt?
Predictive human preference aims to predict which model users might prefer for a specific query.
https://huyenchip.com/2024/02/28/predictive-human-preference.html
One use case is model routing. If we know in advance that for a prompt, users will prefer Claude Instant’s response over GPT-4, and Claude Instant is cheaper/faster than GPT-4, we can route this prompt to Claude Instant. Model routing has the potential to increase response quality while reducing costs and latency.
One pattern is that for simple prompts, weak models can do (nearly) as well as strong models. For more challenging prompts, however, users are more likely to prefer stronger models. Here’s a visualization of predicted human preference for an easy prompt (“hello, how are you?”) and a challenging prompt (“Explain why Planc length …”).
Preference predictors make it possible to create leaderboards unique to any prompt and domain.
- 3 replies
updated
a
collection
12 months ago
reacted to
DmitryRyumin's
post with ❤️
12 months ago
Post
🎉✨ Exciting Research Alert! YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information 🚀
YOLOv9 is the latest breakthrough in object detection!
📄 Title: YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information
👥 Authors: Chien-Yao Wang et al.
📅 Published: ArXiv, February 2024
🔗 Paper: YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information (2402.13616)
🔗 Model 🤖: adonaivera/yolov9
🔗 Repo: https://github.com/WongKinYiu/yolov9
🚀 Don't miss out on this cutting-edge research! Explore YOLOv9 today and stay ahead of the curve in the dynamic world of computer vision. 🌟
🔍 Keywords: #YOLOv9 #ObjectDetection #DeepLearning #ComputerVision #Innovation #Research #ArtificialIntelligence
YOLOv9 is the latest breakthrough in object detection!
📄 Title: YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information
👥 Authors: Chien-Yao Wang et al.
📅 Published: ArXiv, February 2024
🔗 Paper: YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information (2402.13616)
🔗 Model 🤖: adonaivera/yolov9
🔗 Repo: https://github.com/WongKinYiu/yolov9
🚀 Don't miss out on this cutting-edge research! Explore YOLOv9 today and stay ahead of the curve in the dynamic world of computer vision. 🌟
🔍 Keywords: #YOLOv9 #ObjectDetection #DeepLearning #ComputerVision #Innovation #Research #ArtificialIntelligence
- 1 reply
liked
2
models
12 months ago
upvoted
2
papers
about 1 year ago
liked
2
models
about 1 year ago
liked
a
dataset
about 1 year ago
updated
a
collection
about 1 year ago
liked
a
model
about 1 year ago