Model Details
Model Card for Olmo 3 32B
We introduce Olmo 3, a new family of 7B and 32B models featuring a [TODO: insert gain in performance], among other evaluation improvements, compared to the most recent Olmo 2 7B model. These gains come from training on dolma3-mix-1025] and dolma3-dolmino-mix-1025 datasets and staged training approach.
Olmo is a series of Open language models designed to enable the science of language models. These models are trained on the Dolma 3 dataset. We are releasing all code, checkpoints, logs (coming soon), and associated training details.
| Size | Training Tokens | Layers | Hidden Size | Attention Heads | Context Length |
|---|---|---|---|---|---|
| Olmo 3 7B | 5.93T | 32 | 4096 | 32 | 8192 |
| Olmo 3 32B |
The core models released in this batch include the following:
| Stage | [Olmo 3 7B] | [Olmo 3 32B] |
|---|---|---|
| Base Model | ||
| SFT | ||
| DPO | ||
| Final Models (RLVR) | ||
| Reward Model (RM) |
Installation
Olmo 3 is supported in transformers [TODO] vX.XX or higher:
pip install transformers>=X.XX [TODO]
Inference
You can use OLMo with the standard HuggingFace transformers library:
from transformers import AutoModelForCausalLM, AutoTokenizer
olmo = AutoModelForCausalLM.from_pretrained("allenai/Olmo-3-1125-32B")
tokenizer = AutoTokenizer.from_pretrained("allenai/Olmo-3-1125-32B")
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-3-1125-32B",
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 pretraining, the naming convention is stage1-stepXXX.
To load a specific model revision with HuggingFace, simply add the argument revision:
olmo = AutoModelForCausalLM.from_pretrained("allenai/Olmo-3-1125-32B", revision="stage1-step10000")
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-3-1125-32B")
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.
- 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: The code and model are released under Apache 2.0.
- Contact: Technical inquiries:
olmo@allenai.org. Press:press@allenai.org - Date cutoff: Dec. 2023.
Model Sources
- Project Page: https://allenai.org/olmo
- Repositories:
- Core repo (training, inference, fine-tuning etc.): https://github.com/allenai/OLMo-core
- Evaluation code: https://github.com/allenai/OLMo-Eval
- Further fine-tuning code: https://github.com/allenai/open-instruct
- Paper: [TBD]
Evaluation
Core model results for MODELS are found below.
| Model | Training FLOPs | Average | ARC/C | HSwag | WinoG | MMLU | DROP | NQ | AGIEval | GSM8k | MMLUPro | TriviaQA |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Open weights models | ||||||||||||
| Llama-2-13B | 1.6 路 10^23 | 54.1 | 67.3 | 83.9 | 74.9 | 55.7 | 45.6 | 38.4 | 41.5 | 28.1 | 23.9 | 81.3 |
| Mistral-7B-v0.3 | n/a | 58.8 | 78.3 | 83.1 | 77.7 | 63.5 | 51.8 | 37.2 | 47.3 | 40.1 | 30 | 79.3 |
| Llama-3.1-8B | 7.2 路 10^23 | 61.8 | 79.5 | 81.6 | 76.6 | 66.9 | 56.4 | 33.9 | 51.3 | 56.5 | 34.7 | 80.3 |
| Mistral-Nemo-12B | n/a | 66.9 | 85.2 | 85.6 | 81.5 | 69.5 | 69.2 | 39.7 | 54.7 | 62.1 | 36.7 | 84.6 |
| Qwen-2.5-7B | 8.2 路 10^23 | 67.4 | 89.5 | 89.7 | 74.2 | 74.4 | 55.8 | 29.9 | 63.7 | 81.5 | 45.8 | 69.4 |
| Gemma-2-9B | 4.4 路 10^23 | 67.8 | 89.5 | 87.3 | 78.8 | 70.6 | 63 | 38 | 57.3 | 70.1 | 42 | 81.8 |
| Mistral-Small-24B | n/a | 75.2 | 93.3 | 91.3 | 77.8 | 80.7 | 74.4 | 42.3 | 69.1 | 79.7 | 54.2 | 88.8 |
| Gemma-2-27B | 2.1 路 10^24 | 71.3 | 90.7 | 88.4 | 74.5 | 75.7 | 70.1 | 44.7 | 61.5 | 75.7 | 44.7 | 87.4 |
| Qwen-2.5-14B | 1.6 路 10^24 | 72.2 | 94.0 | 94.0 | 80.0 | 79.3 | 51.5 | 37.3 | 71.0 | 83.4 | 52.8 | 79.1 |
| Qwen-2.5-32B | 3.5 路 10^24 | 74.9 | 95.6 | 96.0 | 84.0 | 83.1 | 53.1 | 37.0 | 78.0 | 83.3 | 59.0 | 79.9 |
| Partially open models | ||||||||||||
| StableLM-2-12B | 2.9 路 10^23 | 62.2 | 81.9 | 84.5 | 77.7 | 62.4 | 55.5 | 37.6 | 50.9 | 62 | 29.3 | 79.9 |
| Zamba-2-7B | n/c | 65.2 | 92.2 | 89.4 | 79.6 | 68.5 | 51.7 | 36.5 | 55.5 | 67.2 | 32.8 | 78.8 |
| Fully open models | ||||||||||||
| Amber-7B | 0.5 路 10^23 | 35.2 | 44.9 | 74.5 | 65.5 | 24.7 | 26.1 | 18.7 | 21.8 | 4.8 | 11.7 | 59.3 |
| OLMo-7B | 1.0 路 10^23 | 38.3 | 46.4 | 78.1 | 68.5 | 28.3 | 27.3 | 24.8 | 23.7 | 9.2 | 12.1 | 64.1 |
| MAP-Neo-7B | 2.1 路 10^23 | 49.6 | 78.4 | 72.8 | 69.2 | 58 | 39.4 | 28.9 | 45.8 | 12.5 | 25.9 | 65.1 |
| OLMo-0424-7B | 0.9 路 10^23 | 50.7 | 66.9 | 80.1 | 73.6 | 54.3 | 50 | 29.6 | 43.9 | 27.7 | 22.1 | 58.8 |
| DCLM-7B | 1.0 路 10^23 | 56.9 | 79.8 | 82.3 | 77.3 | 64.4 | 39.3 | 28.8 | 47.5 | 46.1 | 31.3 | 72.1 |
| OLMo-2-1124-7B | 1.8 路 10^23 | 62.9 | 79.8 | 83.8 | 77.2 | 63.7 | 60.8 | 36.9 | 50.4 | 67.5 | 31.0 | 78 |
| OLMo-2-1124-13B | 4.6 路 10^23 | 68.3 | 83.5 | 86.4 | 81.5 | 67.5 | 70.7 | 46.7 | 54.2 | 75.1 | 35.1 | 81.9 |
| OLMo-2-0325-32B | 1.3 路 10^24 | 72.9 | 90.4 | 89.7 | 78.7 | 74.9 | 74.3 | 50.2 | 61.0 | 78.8 | 43.3 | 88.0 |
| Olmo-3-1025-7B | ||||||||||||
| Olmo-3-1025-32B |
Model Details
Stage 1: Initial Pretraining
- Dataset: dolma3-mix-1025 (6T tokens)
- Coverage: X%+ of total pretraining budget
- MODEL: ~X epoch
Stage 2: Mid-training
- Dataset: dolma3-dolmino-mix-1025 (100B tokens)
- Mix composition: XYZ
Stage 3: Long Context
- Dataset: dolma3-longmino-mix-1025 (XX tokens)
- Mix composition: XYZ
Model Merging
- MODEL:
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.
Citation
A technical manuscript is forthcoming!
Model Card Contact
For errors in this model card, contact olmo@allenai.org.
- Downloads last month
- 3