Total runs:
5.6M
Run Growth:
2.7M
Growth Rate:
47.46%
allenai / OLMo-2-1124-13B-DPO
Model's Last Updated: January 24 2025
text-generation
Introduction of OLMo-2-1124-13B-DPO
Model Details of OLMo-2-1124-13B-DPO
OLMo-2-1124-13B-DPO
OLMo-2 13B DPO November 2024 is post-trained variant of the OLMo-2 13B November 2024 model, which has undergone supervised finetuning on an OLMo-specific variant of the Tülu 3 dataset and further DPO training on this dataset . Tülu 3 is designed for state-of-the-art performance on a diversity of tasks in addition to chat, such as MATH, GSM8K, and IFEval. Check out OLMo 2 paper (forthcoming) or Tülu 3 paper for more details!
OLMo is a series of O pen L anguage Mo dels designed to enable the science of language models. These models are trained on the Dolma dataset. 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 2 7B | OLMo 2 13B |
|---|---|---|
| Base Model | allenai/OLMo2-7B-1124 | allenai/OLMo-2-13B-1124 |
| SFT | allenai/OLMo-2-1124-7B-SFT | allenai/OLMo-2-1124-13B-SFT |
| DPO | allenai/OLMo-2-1124-7B-DPO | allenai/OLMo-2-1124-13B-DPO |
| Final Models (RLVR) | allenai/OLMo-2-1124-7B-Instruct | allenai/OLMo-2-1124-13B-Instruct |
| Reward Model (RM) | allenai/OLMo-2-1124-7B-RM | (Same as 7B) |
Model description
- Model type: A model trained on a mix of publicly available, synthetic and human-created datasets.
- Language(s) (NLP): Primarily English
- License: Apache 2.0
- Finetuned from model: allenai/OLMo-2-13B-1124-SFT
Model Sources
- Project Page: https://allenai.org/olmo
-
Repositories:
- Core repo (training, inference, fine-tuning etc.): https://github.com/allenai/OLMo
- Evaluation code: https://github.com/allenai/olmes
- Further fine-tuning code: https://github.com/allenai/open-instruct
- Paper: Coming soon!
- Demo: https://playground.allenai.org/
Installation
OLMo 2 will be supported in the next version of Transformers, and you need to install it from the main branch using:
pip install --upgrade git+https://github.com/huggingface/transformers.git
Using the model
Loading with HuggingFace
To load the model with HuggingFace, use the following snippet:
from transformers import AutoModelForCausalLM
olmo_model = AutoModelForCausalLM.from_pretrained("allenai/OLMo-2-1124-13B-DPO")
Chat template
The chat template for our models is formatted as:
<|endoftext|><|user|>\nHow are you doing?\n<|assistant|>\nI'm just a computer program, so I don't have feelings, but I'm functioning as expected. How can I assist you today?<|endoftext|>
Or with new lines expanded:
<|endoftext|><|user|>
How are you doing?
<|assistant|>
I'm just a computer program, so I don't have feelings, but I'm functioning as expected. How can I assist you today?<|endoftext|>
It is embedded within the tokenizer as well, for
tokenizer.apply_chat_template
.
System prompt
In Ai2 demos, we use this system prompt by default:
You are OLMo 2, a helpful and harmless AI Assistant built by the Allen Institute for AI.
The model has not been trained with a specific system prompt in mind.
Bias, Risks, and Limitations
The OLMo 2 models have limited safety training, but are not deployed automatically with in-the-loop filtering of responses like ChatGPT, so the model can produce problematic outputs (especially when prompted to do so). See the Falcon 180B model card for an example of this.
Performance
| Model | Average | AlpacaEval | BBH | DROP | GSM8k | IFEval | MATH | MMLU | Safety | PopQA | TruthQA |
|---|---|---|---|---|---|---|---|---|---|---|---|
| Open weights models | |||||||||||
| Gemma-2-9B-it | 51.9 | 43.7 | 2.5 | 58.8 | 79.7 | 69.9 | 29.8 | 69.1 | 75.5 | 28.3 | 61.4 |
| Ministral-8B-Instruct | 52.1 | 31.4 | 56.2 | 56.2 | 80.0 | 56.4 | 40.0 | 68.5 | 56.2 | 20.2 | 55.5 |
| Mistral-Nemo-Instruct-2407 | 50.9 | 45.8 | 54.6 | 23.6 | 81.4 | 64.5 | 31.9 | 70.0 | 52.7 | 26.9 | 57.7 |
| Qwen-2.5-7B-Instruct | 57.1 | 29.7 | 25.3 | 54.4 | 83.8 | 74.7 | 69.9 | 76.6 | 75.0 | 18.1 | 63.1 |
| Llama-3.1-8B-Instruct | 58.9 | 25.8 | 69.7 | 61.7 | 83.4 | 80.6 | 42.5 | 71.3 | 70.2 | 28.4 | 55.1 |
| Tülu 3 8B | 60.4 | 34.0 | 66.0 | 62.6 | 87.6 | 82.4 | 43.7 | 68.2 | 75.4 | 29.1 | 55.0 |
| Qwen-2.5-14B-Instruct | 60.8 | 34.6 | 34.0 | 50.5 | 83.9 | 82.4 | 70.6 | 81.1 | 79.3 | 21.1 | 70.8 |
| Fully open models | |||||||||||
| OLMo-7B-Instruct | 28.2 | 5.2 | 35.3 | 30.7 | 14.3 | 32.2 | 2.1 | 46.3 | 54.0 | 17.1 | 44.5 |
| OLMo-7B-0424-Instruct | 33.1 | 8.5 | 34.4 | 47.9 | 23.2 | 39.2 | 5.2 | 48.9 | 49.3 | 18.9 | 55.2 |
| OLMoE-1B-7B-0924-Instruct | 35.5 | 8.5 | 37.2 | 34.3 | 47.2 | 46.2 | 8.4 | 51.6 | 51.6 | 20.6 | 49.1 |
| MAP-Neo-7B-Instruct | 42.9 | 17.6 | 26.4 | 48.2 | 69.4 | 35.9 | 31.5 | 56.5 | 73.7 | 18.4 | 51.6 |
| OLMo-2-7B-DPO | 55.0 | 29.9 | 47.0 | 58.8 | 82.4 | 74.5 | 31.2 | 63.4 | 81.5 | 24.5 | 57.2 |
| OLMo-2-7B-SFT | 50.0 | 9.3 | 50.7 | 58.2 | 71.2 | 68.0 | 25.1 | 62.0 | 82.4 | 25.0 | 47.8 |
| OLMo-2-13B-DPO | 61.0 | 38.3 | 58.5 | 71.9 | 84.2 | 80.6 | 35.0 | 68.5 | 80.6 | 28.9 | 63.9 |
| OLMo-2-13B-SFT | 55.7 | 12.0 | 58.8 | 71.8 | 75.7 | 71.5 | 31.1 | 67.3 | 82.8 | 29.3 | 56.2 |
| OLMo-2-7B-1124–Instruct | 55.7 | 31.0 | 48.5 | 58.9 | 85.2 | 75.6 | 31.3 | 63.9 | 81.2 | 24.6 | 56.3 |
| OLMo-2-13B-1124-Instruct | 61.4 | 37.5 | 58.4 | 72.1 | 87.4 | 80.4 | 39.7 | 68.6 | 77.5 | 28.8 | 63.9 |
Hyperparameters
Note we use a length-normalized variant of DPO for training.
DPO:
- Learning Rate : 8E-7 (7B, 13B)
- Beta : 5
- Effective Batch Size: 128 (7B, 13B)
- Max. Sequence Length: 2048
- Learning Rate Schedule: Linear
- LR Warmup Ratio: 0.1
- Num. Epochs: 1
License and use
OLMo 2 is licensed under the Apache 2.0 license. OLMo 2 is intended for research and educational use. For more information, please see our Responsible Use Guidelines . This model has been fine-tuned using a dataset mix with outputs generated from third party models and are subject to additional terms: Gemma Terms of Use .
Citation
A technical manuscript is forthcoming!
Runs of allenai OLMo-2-1124-13B-DPO on huggingface.co
189
Total runs
0
24-hour runs
23
3-day runs
-145
7-day runs
-216
30-day runs
More Information About OLMo-2-1124-13B-DPO huggingface.co Model
Url of OLMo-2-1124-13B-DPO
OLMo-2-1124-13B-DPO huggingface.co Url
Provider of OLMo-2-1124-13B-DPO huggingface.co
Other API from allenai
Updated: April 05 2023
Total runs:
804.0K
Run Growth:
118.1K
Growth Rate:
14.70%
Total runs:
173.9K
Run Growth:
-113.8K
Growth Rate:
-65.44%
Total runs:
134.2K
Run Growth:
110.4K
Growth Rate:
82.06%
Total runs:
94.4K
Run Growth:
-2.1K
Growth Rate:
-2.24%
Total runs:
91.3K
Run Growth:
63.3K
Growth Rate:
69.57%
Total runs:
77.3K
Run Growth:
-517.1K
Growth Rate:
-669.13%
Total runs:
75.6K
Run Growth:
4.4K
Growth Rate:
5.77%
Total runs:
63.3K
Run Growth:
51.7K
Growth Rate:
81.63%
Total runs:
61.6K
Run Growth:
-50.5K
Growth Rate:
-81.96%
Total runs:
49.7K
Run Growth:
-640
Growth Rate:
-1.29%
Total runs:
41.2K
Run Growth:
41.2K
Growth Rate:
99.97%
Total runs:
35.6K
Run Growth:
26.6K
Growth Rate:
98.51%
Total runs:
31.2K
Run Growth:
-19.4K
Growth Rate:
-62.31%
Total runs:
27.7K
Run Growth:
24.5K
Growth Rate:
88.59%
Total runs:
23.4K
Run Growth:
1.4K
Growth Rate:
5.61%
Total runs:
22.6K
Run Growth:
-54
Growth Rate:
-0.24%
Total runs:
21.2K
Run Growth:
-18.4K
Growth Rate:
-87.09%
Total runs:
17.9K
Run Growth:
-22.8K
Growth Rate:
-127.30%
Total runs:
16.3K
Run Growth:
5.4K
Growth Rate:
27.42%
Total runs:
12.4K
Run Growth:
8.0K
Growth Rate:
69.22%
Total runs:
11.5K
Run Growth:
4.9K
Growth Rate:
42.53%
Total runs:
11.3K
Run Growth:
977
Growth Rate:
8.66%
Total runs:
11.0K
Run Growth:
2.7K
Growth Rate:
25.33%
Total runs:
10.5K
Run Growth:
43
Growth Rate:
0.41%
Total runs:
7.6K
Run Growth:
7.9K
Growth Rate:
65.67%
Total runs:
7.1K
Run Growth:
-19.8K
Growth Rate:
-277.09%
Total runs:
6.9K
Run Growth:
880
Growth Rate:
12.71%
Total runs:
6.5K
Run Growth:
-2.3K
Growth Rate:
-34.31%
Total runs:
6.4K
Run Growth:
3.3K
Growth Rate:
51.01%
Total runs:
4.9K
Run Growth:
2.1K
Growth Rate:
45.30%
Total runs:
4.7K
Run Growth:
2.7K
Growth Rate:
56.97%
Total runs:
4.5K
Run Growth:
4.4K
Growth Rate:
97.96%
Total runs:
4.3K
Run Growth:
3.2K
Growth Rate:
74.66%
Total runs:
4.1K
Run Growth:
-888
Growth Rate:
-21.90%
Total runs:
3.7K
Run Growth:
1.6K
Growth Rate:
42.74%
Total runs:
3.3K
Run Growth:
3.1K
Growth Rate:
93.97%
Total runs:
2.4K
Run Growth:
-2.0K
Growth Rate:
-77.45%
Total runs:
2.3K
Run Growth:
1.6K
Growth Rate:
69.43%
Total runs:
2.3K
Run Growth:
2.2K
Growth Rate:
98.27%
Total runs:
2.1K
Run Growth:
2.2K
Growth Rate:
33.30%
Total runs:
2.1K
Run Growth:
578
Growth Rate:
34.24%
Total runs:
2.0K
Run Growth:
-2.5K
Growth Rate:
-123.46%
Total runs:
1.9K
Run Growth:
854
Growth Rate:
44.90%
Total runs:
1.9K
Run Growth:
1.9K
Growth Rate:
99.26%
Total runs:
1.9K
Run Growth:
862
Growth Rate:
45.37%
Total runs:
1.9K
Run Growth:
1.5K
Growth Rate:
82.01%
Total runs:
1.9K
Run Growth:
1.8K
Growth Rate:
97.27%
Total runs:
1.8K
Run Growth:
162
Growth Rate:
9.02%
Total runs:
1.7K
Run Growth:
-160
Growth Rate:
-9.16%
Total runs:
1.7K
Run Growth:
943
Growth Rate:
72.21%
Total runs:
1.6K
Run Growth:
461
Growth Rate:
28.09%
Total runs:
1.6K
Run Growth:
885
Growth Rate:
47.40%
Total runs:
1.5K
Run Growth:
824
Growth Rate:
53.93%
Total runs:
1.4K
Run Growth:
841
Growth Rate:
57.17%
Total runs:
1.0K
Run Growth:
-34
Growth Rate:
-3.30%
Total runs:
946
Run Growth:
-3.2K
Growth Rate:
-239.15%
Total runs:
936
Run Growth:
513
Growth Rate:
54.81%
Total runs:
920
Run Growth:
854
Growth Rate:
92.83%
Total runs:
873
Run Growth:
-148
Growth Rate:
-16.95%
Total runs:
842
Run Growth:
839
Growth Rate:
99.64%
Total runs:
819
Run Growth:
795
Growth Rate:
97.07%
Total runs:
669
Run Growth:
392
Growth Rate:
58.59%
Total runs:
667
Run Growth:
237
Growth Rate:
35.53%
Total runs:
655
Run Growth:
323
Growth Rate:
43.01%
Total runs:
542
Run Growth:
-250
Growth Rate:
-46.13%
Total runs:
522
Run Growth:
-340
Growth Rate:
-65.13%
Total runs:
469
Run Growth:
134
Growth Rate:
29.00%
Total runs:
406
Run Growth:
383
Growth Rate:
94.33%
Total runs:
382
Run Growth:
333
Growth Rate:
87.17%
Total runs:
360
Run Growth:
13
Growth Rate:
4.30%
Total runs:
339
Run Growth:
26
Growth Rate:
7.67%
Total runs:
329
Run Growth:
242
Growth Rate:
73.11%
Total runs:
326
Run Growth:
-125
Growth Rate:
-38.34%
Total runs:
317
Run Growth:
-5.8K
Growth Rate:
-1837.22%
Total runs:
299
Run Growth:
36
Growth Rate:
12.08%
Total runs:
284
Run Growth:
190
Growth Rate:
64.41%
Total runs:
262
Run Growth:
135
Growth Rate:
51.53%
Total runs:
254
Run Growth:
176
Growth Rate:
69.29%
Total runs:
218
Run Growth:
204
Growth Rate:
93.58%
Total runs:
210
Run Growth:
82
Growth Rate:
39.23%
Total runs:
194
Run Growth:
22
Growth Rate:
11.46%
Total runs:
179
Run Growth:
-41
Growth Rate:
-22.91%
Total runs:
177
Run Growth:
162
Growth Rate:
91.53%
Total runs:
176
Run Growth:
-178
Growth Rate:
-101.14%