snowflake-arctic-base · azureml v1

# Model Overview Arctic is a dense-MoE Hybrid transformer architecture pre-trained from scratch by the Snowflake AI Research Team. We are releasing model checkpoints for both the base and instruct-tu…

azureFoundry/azureml/snowflake-arctic-base@1

Model Overview

Arctic is a dense-MoE Hybrid transformer architecture pre-trained from scratch by the Snowflake AI Research Team. We are releasing model checkpoints for both the base and instruct-tuned versions of Arctic under an Apache-2.0 license. This means you can use them freely in your own research, prototypes, and products. Please see our blog Snowflake Arctic: The Best LLM for Enterprise AI — Efficiently Intelligent, Truly Open for more information on Arctic and links to other relevant resources such as our series of cookbooks covering topics around training your own custom MoE models, how to produce high-quality training data, and much more.

  • Inputs: Models input text only.
  • Output: Models generate text and code only.
  • Model Architecture: Arctic combines a 10B dense transformer model with a residual 128x3.66B MoE MLP resulting in 480B total and 17B active parameters chosen using a top-2 gating. For more details about Arctic's model Architecture, training process, data, etc. see our series of cookbooks.
  • License: Apache-2.0.
  • Model developers: Snowflake AI Research Team.

Training Data

Snowflake Arctic was pretrained on 3.5 trillion tokens of data from publicly available sources. The fine-tuning data includes publicly available datasets.

Evaluation Results

MetricValue
MMLU67.3
GSM8k74.2
Spider78.9
IFEval52.4
Coding - HumanEval+ & MBPP+ -64.3

Inference samples

Inference typePython sample (Notebook)CLI with YAML
Real timetext-generation-online-endpoint.ipynbtext-generation-online-endpoint.sh
Batchtext-generation-batch-endpoint.ipynbcoming soon

Sample Inputs and Outputs (for real-time inference)

Sample input

{
  "input_data": {
      "input_string": ["I believe the meaning of life is"],
      "parameters":{   
              "top_p": 0.9,
              "temperature": 0.6,
              "max_new_tokens": 96,
              "do_sample": true
      }
  }
}

Sample output

[
    {
        "0": "I believe the meaning of life is to learn to love.\\nI believe in a world of compassion, a world where love rules.\\nI believe in a world where people care for one another.\\nI believe in a world where people help each other.\\nI believe in a world where people are kind to each other.\\nI believe in a world where people are happy.\\nI believe in a world where people are peaceful.\\nI believe in a world where people are loving."
    }
]

Specifications & capabilities

Input
text
Output
text

Provider specifications & access

1–1 / 1

snowflake-arctic-base · azureml v1 ↗

source model id
azureml/snowflake-arctic-base@1
hosting
foundry-managed-compute
platforms
  • Microsoft Foundry
license
apache2.0
architecture
input_modalities
  • text
output_modalities
  • text
capabilities

    Original sources

    1–3 / 3

    Microsoft Foundry · Model page ↗

    Microsoft Foundry · Model documentation ↗

    Microsoft Foundry · Catalog ↗

    Source links

    1–1 / 1

    Explore more models

    Models

    Loading
    EVIDENCE / COMPARISON

    Benchmarks

    Explore every benchmark

    Loading

    These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

    Install TensorTrace