8 2 2

kyle PRO

kaikaidai

kaikaidai

AI & ML interests

None yet

Recent Activity

new activity 3 days ago

AtlaAI/judge-arena:Which models do you want to see on here?

new activity 3 days ago

AtlaAI/judge-arena:What are Meta-Llama-3.1-Instruct "Turbo" models?

updated a Space 4 days ago

AtlaAI/judge-arena

View all activity

Articles

Judge Arena: Benchmarking LLMs as Evaluators

Nov 19, 2024

• 54

Experimenting with different training objectives for an AI evaluator

Oct 31, 2024

• 2

Organizations

kaikaidai's activity

New activity in AtlaAI/judge-arena 3 days ago

Which models do you want to see on here?

#2 opened about 2 months ago by

kaikaidai

What are Meta-Llama-3.1-Instruct "Turbo" models?

#4 opened about 2 months ago by

m-ric

updated a Space 4 days ago

Running

💻

Judge Arena

New activity in AtlaAI/judge-arena 4 days ago

fix/update-flow-judge-model

#9 opened 4 days ago by

bergr7f

New activity in AtlaAI/judge-arena 5 days ago

add-Flow-Judge-v0.1

#8 opened 8 days ago by

bergr7f

New activity in AtlaAI/judge-arena about 1 month ago

Promotion to get more voters

#7 opened about 1 month ago by

softclone

posted an update about 1 month ago

Post

1037

📈 Early results on the 8B evaluation model we've been training...

@NinaCalvi wrote about the progress we've made this quarter towards training the best 'LLM-as-a-judge' evaluator. We've significantly improved against the baseline and are approaching state-of-the-art evaluation performance with an 8B model.

Next up: training Llama-3.1-70B 👀

Here's the full article: https://www.atla-ai.com/post/evaluating-the-evaluator