--- license: apache-2.0 base_model: allenai/Olmo-3-1025-7B language: - en library_name: transformers datasets: - allenai/Dolci-Instruct-SFT - allenai/Dolci-Instruct-SFT-Tool-Use-SA --- ## Model Details Logo for Olmo 3 7B Instruct model # Model Card for Olmo 3 7B Instruct SFT We introduce Olmo 3, a new family of 7B and 32B models both Instruct and Think variants. Long chain-of-thought thinking improves reasoning tasks like math and coding. Olmo is a series of **O**pen **l**anguage **mo**dels designed to enable the science of language models. These models are pre-trained on the Dolma 3 dataset and post-trained on the Dolci datasets. We are releasing all code, checkpoints, logs (coming soon), and associated training details. The core models released in this batch include the following: | **Stage** | **Olmo 3 7B Think** | **Olmo 3 32B Think** | **Olmo 3 7B Instruct** | |--------------------------|-----------------------|------------------------|---------------------------| | **Base Model** | [Olmo-3-7B](https://huggingface.co/allenai/Olmo-3-1025-7B) | [Olmo-3-32B](https://huggingface.co/allenai/Olmo-3-1125-32B) | [Olmo-3-7B](https://huggingface.co/allenai/Olmo-3-1025-7B) | | **SFT** | [Olmo-3-7B-Think-SFT](https://huggingface.co/allenai/Olmo-3-7B-Think-SFT) | [Olmo-3-32B-Think-SFT](https://huggingface.co/allenai/Olmo-3-32B-Think-SFT) | [Olmo-3-7B-Instruct-SFT](https://huggingface.co/allenai/Olmo-3-7B-Instruct-SFT) | | **DPO** | [Olmo-3-7B-Think-DPO](https://huggingface.co/allenai/Olmo-3-7B-Think-DPO) | [Olmo-3-32B-Think-DPO](https://huggingface.co/allenai/Olmo-3-32B-Think-DPO) | [Olmo-3-7B-Instruct-DPO](https://huggingface.co/allenai/Olmo-3-7B-Instruct-DPO) | | **Final Models (RLVR)** | [Olmo-3-7B-Think](https://huggingface.co/allenai/Olmo-3-7B-Think) | [Olmo-3-32B-Think](https://huggingface.co/allenai/Olmo-3-32B-Think) | [Olmo-3-7B-Instruct](https://huggingface.co/allenai/Olmo-3-7B-Instruct) | ## Installation Olmo 3 is supported in transformers 4.57.0 or higher: ```bash pip install transformers>=4.57.0 ``` ## Inference You can use OLMo with the standard HuggingFace transformers library: ```python from transformers import AutoModelForCausalLM, AutoTokenizer olmo = AutoModelForCausalLM.from_pretrained("allenai/Olmo-3-7B-Instruct-SFT") tokenizer = AutoTokenizer.from_pretrained("allenai/Olmo-3-7B-Instruct-SFT") message = ["Who would win in a fight - a dinosaur or a cow named Moo Moo?"] inputs = tokenizer(message, return_tensors='pt', return_token_type_ids=False) # optional verifying cuda # inputs = {k: v.to('cuda') for k,v in inputs.items()} # olmo = olmo.to('cuda') response = olmo.generate(**inputs, max_new_tokens=100, do_sample=True, top_k=50, top_p=0.95) print(tokenizer.batch_decode(response, skip_special_tokens=True)[0]) >> 'This is a fun and imaginative question! Let’s break it down...' ``` For faster performance, you can quantize the model using the following method: ```python AutoModelForCausalLM.from_pretrained("allenai/Olmo-3-7B-Instruct-SFT", torch_dtype=torch.float16, load_in_8bit=True) # Requires bitsandbytes ``` The quantized model is more sensitive to data types and CUDA operations. To avoid potential issues, it's recommended to pass the inputs directly to CUDA using: ```python inputs.input_ids.to('cuda') ``` ## Chat template ## Default System Message The default system prompt for this model is: ``` <|im_start|>system You are a helpful function-calling AI assistant. You do not currently have access to any functions. <|im_end|> ``` ## Chat Format The chat template for this model is formatted as: ``` <|im_start|>system You are a helpful function-calling AI assistant. You do not currently have access to any functions. <|im_end|> <|im_start|>user Who would win in a fight - a dinosaur or a cow named Moo Moo?<|im_end|> <|im_start|>assistant This is a fun and imaginative question! Let’s break it down... Moo Moo the cow would certinaly win. <|endoftext|> ``` ### Model Description - **Developed by:** Allen Institute for AI (Ai2) - **Model type:** a Transformer style autoregressive language model. - **Language(s) (NLP):** English - **License:** This model is licensed under Apache 2.0. It is intended for research and educational use in accordance with Ai2's [Responsible Use Guidelines](https://allenai.org/responsible-use). - **Contact:** Technical inquiries: `olmo@allenai.org`. Press: `press@allenai.org` - **Date cutoff:** Dec. 2024. ### Model Sources - **Project Page:** https://allenai.org/olmo - **Repositories:** - Open-Instruct for DPO and RLVR: https://github.com/allenai/open-instruct - OLMo-Core for pre-training and SFT: https://github.com/allenai/OLMo-core - OLMo-Eval for evaluation: https://github.com/allenai/OLMo-Eval - **Paper:** [TBD] ## Evaluation | **Skill** | **Benchmark** | **Olmo 3 Instruct 7B SFT** | **Olmo 3 Instruct 7B DPO** | **Olmo3 Instruct 7B** | **Qwen 3 8B (no reasoning)** | **Qwen 3 VL 8B Instruct** | **Qwen 2.5 7B** | **Olmo 2 7B Instruct** | **Apertus 8B Instruct** | **Granite 3.3 8B Instruct** | |-----------|--------------|---------------------------|---------------------------|------------------------|------------------------------|----------------------------|-------------------|--------------------------|----------------------------|-------------------------------| | **Math** | MATH | 65.1 | 79.6 | 87.3 | 82.3 | 91.6 | 71.0 | 30.1 | 21.9 | 67.3 | | | AIME 2024 | 6.7 | 23.5 | 44.3 | 26.2 | 55.1 | 11.3 | 1.3 | 0.5 | 7.3 | | | AIME 2025 | 7.2 | 20.4 | 32.5 | 21.7 | 43.3 | 6.3 | 0.4 | 0.2 | 6.3 | | | OMEGA | 14.4 | 22.8 | 28.9 | 20.5 | 32.3 | 13.7 | 5.2 | 5.0 | 10.7 | | **Reasoning** | BigBenchHard | 51.0 | 69.3 | 71.2 | 73.7 | 85.6 | 68.8 | 43.8 | 42.2 | 61.2 | | | ZebraLogic | 18.0 | 28.4 | 32.9 | 25.4 | 64.3 | 10.7 | 5.3 | 5.3 | 17.6 | | | AGI Eval English | 59.2 | 64.0 | 64.4 | 76.0 | 84.5 | 69.8 | 56.1 | 50.8 | 64.0 | | **Coding** | HumanEvalPlus | 69.8 | 72.9 | 77.2 | 79.8 | 82.9 | 74.9 | 25.8 | 34.4 | 64.0 | | | MBPP+ | 56.5 | 55.9 | 60.2 | 64.4 | 66.3 | 62.6 | 40.7 | 42.1 | 54.0 | | | LiveCodeBench v3 | 20.0 | 18.8 | 29.5 | 53.2 | 55.9 | 34.5 | 7.2 | 7.8 | 11.5 | | **IF** | IFEval | 81.7 | 82.0 | 85.6 | 86.3 | 87.8 | 73.4 | 72.2 | 71.4 | 77.5 | | | IFBench | 27.4 | 29.3 | 32.3 | 29.3 | 34.0 | 28.4 | 26.7 | 22.1 | 22.3 | | **Knowledge** | MMLU | 67.1 | 69.1 | 69.1 | 80.4 | 83.6 | 77.2 | 61.6 | 62.7 | 63.5 | | **QA** | PopQA | 16.5 | 20.7 | 14.1 | 20.4 | 26.5 | 21.5 | 25.5 | 25.5 | 28.9 | | | GPQA | 30.0 | 37.9 | 40.4 | 44.6 | 51.1 | 35.6 | 31.3 | 28.8 | 33.0 | | **Chat** | AlpacaEval 2 LC | 21.8 | 43.3 | 40.9 | 49.8 | 73.5 | 23.0 | 18.3 | 8.1 | 28.6 | | **Tool Use** | SimpleQA | 74.2 | 79.8 | 79.3 | 79.0 | 90.3 | 78.0 | – | – | – | | | LitQA2 | 38.0 | 43.3 | 38.2 | 39.6 | 30.7 | 29.8 | – | – | – | | | BFCL | 48.9 | 49.6 | 49.8 | 60.2 | 66.2 | 55.8 | – | – | – | | **Safety** | Safety | 89.2 | 90.2 | 87.3 | 78.0 | 80.2 | 73.4 | 93.1 | 72.2 | 73.7 | ## Model Details #### Stage 1: SFT - supervised fine-tuning on the Dolci-Think-SFT-7B dataset. This dataset consits of math, code, chat, and general knowledge queries. - Datasets: [Dolci-Think-SFT-7B](https://huggingface.co/datasets/allenai/dolci-thinking-sft), [Dolci-Instruct-SFT-7B](https://huggingface.co/datasets/allenai/dolci-instruct-sft) #### Stage 2:DPO - direct preference optimization on the Dolci-Think-DPO-7B dataset. This dataset consits of math, code, chat, and general knowledge queries. - Datasets: [Dolci-Think-DPO-7B](https://huggingface.co/datasets/allenai/dolci-thinking-dpo), [Dolci-Instruct-DPO-7B](https://huggingface.co/datasets/allenai/dolci-3-instruct-dpo-with-metadata) #### Stage 3: RLVR - reinforcement learning from verifiable rewards on the Dolci-Think-RL-7B dataset. This dataset consits of math, code, instruction-following, and general chat queries. - Datasets: [Dolci-Think-RL-7B](https://huggingface.co/datasets/allenai/Dolci-Think-RL-7B), [Dolci-Instruct-RL-7B](https://huggingface.co/datasets/allenai/Dolci-Instruct-RL-7B) ## Inference & Recommended Settings We evaluated our models on the following settings. We also recommend using them for generation: - **temperature:** `0.6` - **top_p:** `0.95` - **max_tokens:** `32768` ### transformers Example ```python from transformers import AutoModelForCausalLM, AutoTokenizer model_id = "allenai/Olmo-3-7B-Instruct-SFT" tokenizer = AutoTokenizer.from_pretrained(model_id) model = AutoModelForCausalLM.from_pretrained( model_id, device_map="auto", ) prompt = "Who would win in a fight - a dinosaur or a cow named MooMoo?" inputs = tokenizer(prompt, return_tensors="pt").to(model.device) outputs = model.generate( **inputs, temperature=0.6, top_p=0.95, max_new_tokens=32768, ) print(tokenizer.decode(outputs[0], skip_special_tokens=True)) ``` ### vllm Example ```python from vllm import LLM, SamplingParams model_id = "allenai/Olmo-3-7B-Instruct-SFT" llm = LLM(model=model_id) sampling_params = SamplingParams( temperature=0.6, top_p=0.95, max_tokens=32768, ) prompt = "Who would win in a fight - a dinosaur or a cow named MooMoo?" outputs = llm.generate(prompt, sampling_params) print(outputs[0].outputs[0].text) ``` ## Bias, Risks, and Limitations Like any base language model or fine-tuned model without safety filtering, these models can easily be prompted by users to generate harmful and sensitive content. Such content may also be produced unintentionally, especially in cases involving bias, so we recommend that users consider the risks when applying this technology. Additionally, many statements from OLMo or any LLM are often inaccurate, so facts should be verified. ## License This model is licensed under Apache 2.0. It is intended for research and educational use in accordance with [Ai2's Responsible Use Guidelines](https://allenai.org/responsible-use). ## Citation A technical manuscript is forthcoming! ## Model Card Contact For errors in this model card, contact `olmo@allenai.org`.