allenai/OLMoE-1B-7B-0125

Text Generation • Updated 20 days ago • 24 • 4

Note 🧱Base version of OLMoE. Use as foundation for post-training or Fine Tuning.

allenai/OLMoE-1B-7B-0125-Instruct

Text Generation • Updated 7 days ago • 91 • 9

Note 🤖 Instruct variant of OLMoE. Use it in chat models

allenai/OLMoE-1B-7B-0125-Instruct-GGUF

Updated 14 days ago • 39 • 3

Note 📲 Quantized version of OLMoE. Great for running locally on device.

Note 📚1️⃣ Pretrain data mix.

Note 📚2️⃣ Mid-train data mix.

Note 📚3️⃣ Post-train SFT data mix.

Note 📚4️⃣ Post-train preference data mix (DPO).

allenai/OLMoE-1B-7B-0125-SFT

Text Generation • Updated 7 days ago • 87

Note SFT only verision of OLMoE. Use allenai/OLMoE-1B-7B-0125-Instruct instead.

allenai/OLMoE-1B-7B-0125-DPO

Text Generation • Updated 7 days ago • 83

Note SFT + DPO only verision of OLMoE. Use allenai/OLMoE-1B-7B-0125-Instruct instead.

allenai/OLMoE-1B-7B-0125-GGUF

Updated 20 days ago • 3 • 1

Note Quantized version of base model. Use allenai/OLMoE-1B-7B-0125-Instruct-GGUF instead.