Toby Drane

tobydrane

AI & ML interests

None yet

Recent Activity

replied to kaikaidai's post 20 days ago

📈 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

liked a Space about 1 month ago

AtlaAI/judge-arena

updated a Space about 2 months ago

AtlaAI/judge-arena

View all activity

Articles

Judge Arena: Benchmarking LLMs as Evaluators

Nov 19

• 53

Organizations

tobydrane's activity

replied to kaikaidai's post 20 days ago

Hi @Taylor658 , the base model does natively support function calling. We have been running some internal tests of our models capability for function calling as this is something we might look to expose via our API in the near future.

liked a Space about 1 month ago

Running

💻

Judge Arena

updated a Space about 2 months ago

Running

💻