OLMo-2-1124-7B-RM

OLMo 2 7B RM November 2024 is reward model trained on top of the OLMo 2 7B SFT November 2024 model. It has been trained using an OLMo-specific variant of the Tülu 3 dataset and this preference 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 the OLMo 2 paper (forthcoming) or Tülu 3 paper for more details!

This reward model was used to initialize value models during RLVR training for both 7B and 13B RLVR training. Note we used a slightly different mix to the final mixture used for DPO training for this RM.

OLMo is a series of Open Language Models 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/OLMo2-7B-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/

Using the model

Loading with HuggingFace

To load the model with HuggingFace, use the following snippet:

# please install from our custom branch
# pip install git+https://github.com/vwxyzjn/transformers.git@olmo1124_classification
from transformers.models.olmo_1124.modeling_olmo_1124 import Olmo1124ForSequenceClassification, Olmo1124Config
AutoModelForSequenceClassification.register(Olmo1124Config, Olmo1124ForSequenceClassification)
from transformers import AutoModelForSequenceClassification

olmo_model = AutoModelForSequenceClassification.from_pretrained("allenai/OLMo-2-1124-7B-RM")

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

Note we did not benchmark the RM since it is just used for initialization during RLVR training. We provide the results of the OLMo-2 models below:

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-SFT	50.0	9.3	50.7	58.2	71.2	68.0	25.1	62.0	82.4	25.0	47.8
OLMo-2-7B-DPO	55.0	29.9	47.0	58.8	82.4	74.5	31.2	63.4	81.5	24.5	57.2
OLMo-2-13B-SFT	55.7	12.0	58.8	71.8	75.7	71.5	31.1	67.3	82.8	29.3	56.2
OLMo-2-13B-DPO	61.0	38.3	58.5	71.9	84.2	80.6	35.0	68.5	80.6	28.9	63.9
OLMo-2-7B-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

RM training:

Learning Rate: 3E-6
Effective Batch Size: 256
Max. Sequence Length: 4096
Learning Rate Schedule: None
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.

Citation

A technical manuscript is forthcoming!

allenai
/

OLMo-2-1124-7B-RM