models Deci DeciCoder 1b

Deci-DeciCoder-1b

Overview

The Model Card for DeciCoder 1B provides details about a 1 billion parameter decoder-only code completion model developed by Deci. The model was trained on Python, Java, and JavaScript subsets of Starcoder Training Dataset and uses Grouped Query Attention with a context window of 2048 tokens. It was trained using a Fill-in-the-Middle training objective and generated by Deci's proprietary Neural Architecture Search-based technology, AutoNAC. The model is intended for single/multiline code completion from a context window of up to 2048 tokens. The model has limitations as it has undergone training with source code from Python, Java, and JavaScript, and there is no assurance that the resulting code will function as expected. The Model Card provides details on how to use the model, training details, and evaluation results. The model's checkpoints are licensed under the Apache 2.0 license.

Model Evaluation Sample

Task	Use case	Dataset	Python sample (Notebook)	CLI with YAML
Text generation	Text generation	cnn_dailymail	evaluate-model-text-generation.ipynb	evaluate-model-text-generation.yml

Inference samples

Inference type	Python sample (Notebook)	CLI with YAML
Real time	text-generation-online-endpoint.ipynb	text-generation-online-endpoint.sh
Batch	text-generation-batch-endpoint.ipynb	coming soon

Sample inputs and outputs (for real-time inference)

Sample input

{
  "input_data": {
    "input_string": [
      "def print_hello_world():"
    ],
    "parameters": {
      "top_p": 0.95,
      "temperature": 0.1,
      "max_new_tokens": 10,
      "do_sample": true
    }
  }
}

Sample output

[
  {
    "0": "def print_hello_world():\n    print(\"Hello World!\")\n\n\ndef print"
  }
]

Version: 3

Tags

Featured Preview inference_compute_allow_list : ['Standard_NC12s_v3', 'Standard_NC24s_v3', 'Standard_ND40rs_v2', 'Standard_ND96asr_v4', 'Standard_ND96amsr_A100_v4'] evaluation_compute_allow_list : ['Standard_NC12s_v3', 'Standard_NC24s_v3', 'Standard_ND40rs_v2', 'Standard_ND96asr_v4', 'Standard_ND96amsr_A100_v4'] SharedComputeCapacityEnabled task : text-generation hiddenlayerscanned license : apache-2.0 author : deci-ai huggingface_model_id : Deci/DeciCoder-1b datasets : bigcode/starcoderdata

View in Studio: https://ml.azure.com/registries/azureml/models/Deci-DeciCoder-1b/version/3

License: apache-2.0

Properties

SharedComputeCapacityEnabled: True

SHA: 59cead352e3b213c9a77097d3d08e89bf467ef7b

inference-recommended-sku: Standard_NC12s_v3, Standard_NC24s_v3, Standard_ND40rs_v2, Standard_ND96asr_v4, Standard_ND96amsr_A100_v4

inference-min-sku-spec: 12|2|224|1474

evaluation-recommended-sku: Standard_NC12s_v3, Standard_NC24s_v3, Standard_ND40rs_v2, Standard_ND96asr_v4, Standard_ND96amsr_A100_v4

evaluation-min-sku-spec: 12|2|224|1474

languages: EN