Marketplace · Text & chat

olmoe-7b-colibri

Call olmoe-7b-colibri through one OpenAI-compatible API. It's served by 1 host on the Inpherio grid, each at a price it sets — your request goes to the cheapest healthy one, and fails over to the next if it's down.

From
£0.65
per 1M output tokens
£1 buys about 1.5 million tokens (≈ 1.2 million words)
Hosts
1
Loaded now
1

At a glance.

  • Type: Text & chat
  • Hosts serving it now: 1 (1 with it loaded in memory)
  • Engines: vllm
  • Context window: up to 128 tokens
  • Rentable: a whole host from £0.04 an hour (rentals)
python · openai sdk
from openai import OpenAI
client = OpenAI(base_url="https://inpherio.co.uk/v1",
                api_key=INPHERIO_API_KEY)
reply = client.chat.completions.create(
    model="olmoe-7b-colibri",
    messages=[{"role": "user", "content": "Hello"}],
)

olmoe-7b-colibri in detail.

OLMoE-1B-7B-0125-Instruct January 2025 is post-trained variant of the [OLMoE-1B-7B January 2025](https://huggingface.co/allenai/OLMoE-1B-7B-0125) model, which has undergone supervised finetuning on an OLMo-specific variant of the [Tülu 3 dataset](allenai/tulu-3-sft-olmo-2-mixture) and further DPO training on [this dataset](https://huggingface.co/datasets/allenai/olmo-2-1124-13b-preference-mix), an

Published by
allenai
Parameters
6.9B
Format
transformers
Architecture
olmoe
Licence
Apache 2.0
Based on
allenai/OLMoE-1B-7B-0125-DPO
Task
text generation
Library
transformers
Languages
en
First published
27 Jan 2025
Last updated
4 Feb 2025
Downloads (30 days)
32,741 on Hugging Face
Likes
68

olmoe text-generation en

The model card

Published by the model's authors on Hugging Face — shown as they wrote it, unedited by Inpherio.

OLMoE-1B-7B-0125-Instruct

Release Documentation

OLMoE-1B-7B-0125-Instruct January 2025 is post-trained variant of the OLMoE-1B-7B January 2025 model, which has undergone supervised finetuning on an OLMo-specific variant of the Tülu 3 dataset and further DPO training on this dataset, and finally RLVR training using this data. 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 OLMoE paper or Tülu 3 paper for more details!

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:

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/OLMoE-1B-7B-0125-DPO

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: https://arxiv.org/abs/2409.02060
  • 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("OLMoE-1B-7B-0125-Instruct")

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.

Read the rest of the model card

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

Benchmark (eval)OLMoE-1B-7B-0125-InstructOLMoE-1B-7B-0924-InstructOLMoE-1B-7B-0125-DPOOLMoE-1B-7B-0125-SFTOLMoE-1B-7B-0924-SFT
Avg.45.6238.4445.0541.7637.05
MMLU (CoT)55.0854.5754.9355.2654.32
PopQA19.7520.5619.6520.1221.01
TruthfulQA50.5649.1449.9945.4844.66
BigBenchHard (CoT)38.6136.7837.3737.3136.55
DROP47.8734.4848.3848.5734.71
MATH (Flex)21.418.1620.3621.388.15
GSM8K72.4047.3864.5955.7242.46
HumanEval62.3063.0461.9262.5863.72
HumanEval+54.3758.9357.6155.6757.40
IFEval66.3645.2965.6256.5641.22
AlpacaEval17.997.5419.505.836.38
Safety (average)90.4051.4091.4094.5065.80

License and use

OLMoE is licensed under the Apache 2.0 license. OLMoE 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

@misc{muennighoff2024olmoeopenmixtureofexpertslanguage,
      title={OLMoE: Open Mixture-of-Experts Language Models}, 
      author={Niklas Muennighoff and Luca Soldaini and Dirk Groeneveld and Kyle Lo and Jacob Morrison and Sewon Min and Weijia Shi and Pete Walsh and Oyvind Tafjord and Nathan Lambert and Yuling Gu and Shane Arora and Akshita Bhagia and Dustin Schwenk and David Wadden and Alexander Wettig and Binyuan Hui and Tim Dettmers and Douwe Kiela and Ali Farhadi and Noah A. Smith and Pang Wei Koh and Amanpreet Singh and Hannaneh Hajishirzi},
      year={2024},
      eprint={2409.02060},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2409.02060}, 
}
@article{lambert2024tulu3,
  title = {Tülu 3: Pushing Frontiers in Open Language Model Post-Training},
  author = {
    Nathan Lambert and 
    Jacob Morrison and 
    Valentina Pyatkin and 
    Shengyi Huang and 
    Hamish Ivison and 
    Faeze Brahman and 
    Lester James V. Miranda and 
    Alisa Liu and 
    Nouha Dziri and 
    Shane Lyu and 
    Yuling Gu and 
    Saumya Malik and 
    Victoria Graf and 
    Jena D. Hwang and 
    Jiangjiang Yang and
    Ronan Le Bras and
    Oyvind Tafjord and
    Chris Wilhelm and
    Luca Soldaini and 
    Noah A. Smith and 
    Yizhong Wang and 
    Pradeep Dasigi and 
    Hannaneh Hajishirzi
  },
  year = {2024},
  email = {[email protected]}
}

Sources: allenai/OLMoE-1B-7B-0125-Instruct on Hugging Face. Collected from public sources on 8 Nov 2026; the host serving it may run a different build or quantisation — the marketplace shows each host's own measurements.

Who's serving it.

Every host benchmarked this model on its own hardware before serving it. Prices are set by each host; health is scored by the platform from what it observes.

Hosts serving olmoe-7b-colibri right now
HostTierPriceMeasured speedHealthStateRent
7B-A1B (5G)L1£0.17 in · £0.65 out7 tok/s · 3996 ms first token82loaded£0.04/h

Live data, refreshed on every visit. How billing works.

Room on the grid for your machine.

Right now one machine serves olmoe-7b-colibri. If it drops, so does every request for it — a second host is what turns it into failover, and the grid needs that more than another copy. The router weighs price, measured speed, health and whether the model is already loaded — so a host with a sharper price or quicker hardware wins the next call.

Hosts now
1
1 loaded in memory
Price to beat
£0.65
per 1M output tokens
Fastest measured
7 tok/s

Set your own price — you keep 85% of what it earns, and new hosts start with 12 months fee-free (up to £250 of earnings). A payout fee of £2 + 1% per payout to a UK bank account, £2 + 2% to any other country applies when you're paid. Install the connector, load olmoe-7b-colibri, and the platform benchmarks it on your hardware before your first request.