LLM EXPLORER 59,766 MODELS INDEXED

Olmo 3 7B Instruct DPO by allenai

By allenai · 9041 downloads
HF Repo ↗ Copy URL

Olmo 3 7B Instruct DPO is an open-source language model by allenai. Features: 7b LLM, VRAM: 14.6GB, Context: 64K, License: apache-2.0, Instruction-Based, LLM Explorer Score: 0.26.

  Arxiv:2512.13961 Base model:allenai/olmo-3-7b-i... Base model:finetune:allenai/ol...   Conversational Dataset:allenai/dolci-think-dp...   En   Endpoints compatible   Instruct   Olmo3   Pytorch   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/allenai/Olmo-3-7B-Instruct-DPO 

Olmo 3 7B Instruct DPO Parameters and Internals

LLM NameOlmo 3 7B Instruct DPO
Repository 🤗https://huggingface.co/allenai/Olmo-3-7B-Instruct-DPO 
Base Model(s)  Olmo 3 7B Instruct SFT   allenai/Olmo-3-7B-Instruct-SFT
Model Size7b
Required VRAM14.6 GB
Updated2026-08-08
Maintainerallenai
Model Typeolmo3
Instruction-BasedYes
Model Files  5.0 GB: 1-of-3   5.0 GB: 2-of-3   4.6 GB: 3-of-3   5.0 GB: 1-of-3   5.0 GB: 2-of-3   4.6 GB: 3-of-3
Supported Languagesen
Model ArchitectureOlmo3ForCausalLM
Licenseapache-2.0
Context Length65536
Model Max Length65536
Transformers Version4.57.1
Tokenizer ClassGPT2Tokenizer
Padding Token<|pad|>
Vocabulary Size100278

Best Alternatives to Olmo 3 7B Instruct DPO

Best Alternatives
Context / RAM
Downloads
Likes
Olmo 3 7B Instruct64K / 14.6 GB431172142
Olmo 3 7B Instruct SFT64K / 14.6 GB2993576
Olmo 3 7B Instruct64K / 14.6 GB7940
...o 3 7B Instruct Abliterated V164K / 14.6 GB112
Olmo 3 7B Instruct 4bit64K / 4.1 GB391
Olmo 3 7B Instruct 8bit64K / 7.7 GB92
Note: green Score (e.g. "73.2") means that the model is better than allenai/Olmo-3-7B-Instruct-DPO.