Llama 3.1 Tulu3 405B
ResearchOpen weightsText405B parameters
OLMo/Tulu (Ai2) family model by Allen Institute for AI.
About the OLMo/Tulu (Ai2) family
The Allen Institute's Tulu — a fully open post-training recipe (SFT+DPO+RLVR) applied to Llama 3.1 405B, matching closed-lab finetunes with published data and code.
All OLMo/Tulu (Ai2) modelsHow this one is configured
This configuration ~405B parameters.
Who makes it
Allen Institute for AI — United States. Not listed as a provider in this directory.