Olmo-3.1-32B-Instruct-GGUF

Note. Includes Unsloth chat template fixes!

For llama.cpp, use --jinja

Unsloth Dynamic 2.0 achieves superior accuracy & outperforms other leading quants.

https://github.com/unslothai/unsloth/ https://discord.gg/unsloth https://docs.unsloth.ai/

Model Details#

Image: Logo for Olmo 3.1 32B Instruct model

Model Card for Olmo-3.1-32B-Instruct#

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 Open language models 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:

Olmo-3.1-32B-Think | Olmo-3-7B-Instruct | Olmo-3.1-32B-Instruct |

Installation#

Olmo 3 is supported in transformers 4.57.0 or higher:

pip install transformers>=4.57.0

Inference#

You can use OLMo with the standard HuggingFace transformers library:

from transformers import AutoModelForCausalLM, AutoTokenizer
olmo = AutoModelForCausalLM.from_pretrained("allenai/Olmo-3.1-32B-Instruct")
tokenizer = AutoTokenizer.from_pretrained("allenai/Olmo-3.1-32B-Instruct")
message = ["Language modeling is "]
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])
>> 'Language modeling is  a key component of any text-based application, but its effectiveness...'

For faster performance, you can quantize the model using the following method:

AutoModelForCausalLM.from_pretrained("allenai/Olmo-3.1-32B-Instruct", 
    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:

inputs.input_ids.to('cuda')

We have released checkpoints for these models. For post-training, the naming convention is step_XXXX. NOTE: For this model, due to a checkpointing issue, we only are releasing the final few checkpoints. See our other RL jobs for more detailed intermediate checkpoint suite.

To load a specific model revision with HuggingFace, simply add the argument revision:

olmo = AutoModelForCausalLM.from_pretrained("allenai/Olmo-3.1-32B-Instruct", revision="step_1375")

Or, you can access all the revisions for the models via the following code snippet:

from huggingface_hub import list_repo_refs
out = list_repo_refs("allenai/Olmo-3.1-32B-Instruct")
branches = [b.name for b in out.branches]

Fine-tuning#

Model fine-tuning can be done from the final checkpoint (the main revision of this model) or many intermediate checkpoints. Two recipes for tuning are available.

1. Fine-tune with the OLMo-core repository:

torchrun --nproc-per-node=8 ./src/scripts/official/MODEL.py run01

You can override most configuration options from the command-line. For example, to override the learning rate you could launch the script like this:

torchrun --nproc-per-node=8 ./src/scripts/train/MODEL.py run01 --train_module.optim.lr=6e-3

For more documentation, see the GitHub readme.

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.
• 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:: https://allenai.org/papers/olmo3

Evaluation#

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, 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, Dolci-Instruct-DPO

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, Dolci-Instruct-RL

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.

Citation#

A technical manuscript is forthcoming!

Model Card Contact#

For errors in this model card, contact olmo@allenai.org.