Azure
@realazure.bsky.social
An experiment analyzing the thinking traces of reasoning LLM.
By tracking first-word statistics in reasoning traces, I found commonalities across models using pivotal tokens like "wait".
A lot of models are similar to R1, but others like sonnet and gemini come from their own school of thought.
By tracking first-word statistics in reasoning traces, I found commonalities across models using pivotal tokens like "wait".
A lot of models are similar to R1, but others like sonnet and gemini come from their own school of thought.
April 5, 2025 at 8:12 AM
An experiment analyzing the thinking traces of reasoning LLM.
By tracking first-word statistics in reasoning traces, I found commonalities across models using pivotal tokens like "wait".
A lot of models are similar to R1, but others like sonnet and gemini come from their own school of thought.
By tracking first-word statistics in reasoning traces, I found commonalities across models using pivotal tokens like "wait".
A lot of models are similar to R1, but others like sonnet and gemini come from their own school of thought.
Reposted by Azure
Meet Helium-1 preview, our 2B multi-lingual LLM, targeting edge and mobile devices, released under a CC-BY license. Start building with it today!
huggingface.co/kyutai/heliu...
huggingface.co/kyutai/heliu...
kyutai/helium-1-preview-2b · Hugging Face
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
huggingface.co
January 13, 2025 at 5:50 PM
Meet Helium-1 preview, our 2B multi-lingual LLM, targeting edge and mobile devices, released under a CC-BY license. Start building with it today!
huggingface.co/kyutai/heliu...
huggingface.co/kyutai/heliu...