allenai/OLMo-2-0325-32B-Instruct

Text Generation • Updated 1 day ago • 3.27k • 69

Note ✨ New! ✨ Our best OLMo 2 model yet. 💬 Instruct models are best used for chat applications.

allenai/OLMo-2-0325-32B

Text Generation • Updated 2 days ago • 90.1k • 23

Note ✨ New! ✨ Our best OLMo 2 model yet. 🧱Base models are used as foundation for post-training.

allenai/OLMo-2-1124-13B-Instruct

Text Generation • Updated Jan 6 • 5.16k • 36

Note 💬 Instruct version of OLMo 2 13B. This model is best used for chat applications.

allenai/OLMo-2-1124-13B-Instruct-GGUF

Updated Jan 6 • 902 • 5

Note 💻 Quantized version of OLMo 2 13B Instruct. Great for running locally on device.

allenai/OLMo-2-1124-13B

Updated Jan 6 • 10.6k • 53

Note 🧱Base version of OLMo 2 13B. Use as foundation for post-training.

allenai/OLMo-2-1124-7B-Instruct

Text Generation • Updated Jan 6 • 13k • 30

Note 💬 Instruct version of OLMo 2 7B. This model is best used for chat applications.

allenai/OLMo-2-1124-7B-Instruct-GGUF

Updated Jan 6 • 751 • 5

Note 💻 Quantized version of OLMo 2 7B Instruct. Great for running locally on device.

allenai/OLMo-2-1124-7B

Updated Jan 6 • 159k • 47

Note 🧱Base version of OLMo 2 7B. Use as foundation for post-training.

Note 📚1️⃣ Pretrain data mix for OLMo 2 7B, 13B, and 32B.

Note 📚2️⃣ Midtrain data mix for OLMo 2 7B, 13B, and 32B.

Note 📚3️⃣ Post-train SFT data mix for OLMo 2 7B and 13B.

Note 📚3️⃣ Post-train SFT data mix for OLMo 2 32B.

Note 📚4️⃣ Post-train preference data mix (DPO) for OLMo 2 7B.

Note 📚4️⃣ Post-train preference data mix (DPO) for OLMo 2 13B.

Note 📚4️⃣ Post-train preference data mix (DPO) for OLMo 2 32B.

Note 📚5️⃣ Post-train dataset used for RLVR training on OLMo 2 7B, 13B, and 32B.

allenai/OLMo-2-1124-7B-SFT

Text Generation • Updated Jan 6 • 8.65k

Note SFT only version of OLMo 2 7B. Use allenai/OLMo-2-1124-7B-Instruct instead.

allenai/OLMo-2-1124-13B-SFT

Text Generation • Updated Jan 6 • 187

Note SFT only version of OLMo 2 13B. Use allenai/OLMo-2-1124-13B-Instruct instead.

allenai/OLMo-2-0325-32B-SFT

Text Generation • Updated 1 day ago • 57 • 4

Note SFT only version of OLMo 2 32B. Use allenai/OLMo-2-0325-32B-Instruct instead.

allenai/OLMo-2-1124-7B-DPO

Text Generation • Updated Jan 6 • 461 • 1

Note SFT+DPO version of OLMo 2 7B. Use allenai/OLMo-2-1124-7B-Instruct instead.

allenai/OLMo-2-1124-13B-DPO

Text Generation • Updated Jan 24 • 245

Note SFT+DPO version of OLMo 2 13B. Use allenai/OLMo-2-1124-13B-Instruct instead.

allenai/OLMo-2-0325-32B-DPO

Text Generation • Updated 1 day ago • 54 • 3

Note SFT+DPO version of OLMo 2 32B. Use allenai/OLMo-2-0325-32B-Instruct instead.

allenai/OLMo-2-1124-7B-RM

Text Generation • Updated Jan 6 • 124 • 2

Note Reward model for OLMo 2 7B. Use allenai/OLMo-2-1124-7B-Instruct instead.

allenai/OLMo-2-1124-13B-RM

Text Generation • Updated Jan 6 • 111 • 2

Note Reward model for OLMo 2 13B. Use allenai/OLMo-2-1124-13B-Instruct instead.

allenai/OLMo-2-1124-13B-Instruct-RLVR1

Text Generation • Updated Jan 6 • 43 • 2

Note Preliminary version of OLMo 2 13B Instruct. Use allenai/OLMo-2-1124-13B-Instruct instead.

allenai/OLMo-2-1124-13B-Instruct-RLVR2

Text Generation • Updated Jan 6 • 40

Note Preliminary version of OLMo 2 13B Instruct. Use allenai/OLMo-2-1124-13B-Instruct instead.