NovaSky-AI/Sky-T1-32B-Preview

`NovaSky-AI/Sky-T1-32B-Preview` powered by Text Generation Inference (TGI) - [Example Notebook](https://aka.ms/hugging-face-text-generation-streaming-online-endpoint) - [Original Model Card](https://…

azureFoundry/HuggingFace/novasky-ai-sky-t1-32b-preview@1

NovaSky-AI/Sky-T1-32B-Preview powered by Text Generation Inference (TGI)

Send Request

You can use cURL or any REST Client to send a request to the AzureML endpoint with your AzureML token.

curl <AZUREML_ENDPOINT_URL> \
    -X POST \
    -d '{"inputs":"What is Deep Learning?"}' \
    -H "Authorization: Bearer <AZUREML_TOKEN>" \
    -H "Content-Type: application/json"

Supported Parameters

  • inputs (string): Input prompt.
  • parameters (object):
    • best_of (integer): Generate best_of sequences and return the one if the highest token logprobs.
    • decoder_input_details (boolean): Whether to return decoder input token logprobs and ids.
    • details (boolean): Whether to return generation details.
    • do_sample (boolean): Activate logits sampling.
    • frequency_penalty (float): The parameter for frequency penalty. 1.0 means no penalty Penalize new tokens based on their existing frequency in the text so far, decreasing the model’s likelihood to repeat the same line verbatim.
    • grammar (object): One of the following
      • #1 (object):
        • type (enum): Possible values: json.
        • value (string): A string that represents a JSON Schema. JSON Schema is a declarative language that allows to annotate JSON documents with types and descriptions.
      • #2 (object):
        • type (enum): Possible values: regex.
        • value (string): The regular expression.
      • #3 (object):
        • type (enum): Possible values: json_schema.
        • value (object):
          • name (string): Optional name identifier for the schema
          • schema (object): The actual JSON schema definition
    • max_new_tokens (integer): Maximum number of tokens to generate.
    • repetition_penalty (float): The parameter for repetition penalty. 1.0 means no penalty. See this paper for more details.
    • return_full_text (boolean): Whether to prepend the prompt to the generated text
    • seed (integer): Random sampling seed.
    • stop (string[]): Stop generating tokens if a member of stop is generated.
    • temperature (float): The value used to module the logits distribution.
    • top_k (integer): The number of highest probability vocabulary tokens to keep for top-k-filtering.
    • top_n_tokens (integer): The number of highest probability vocabulary tokens to keep for top-n-filtering.
    • top_p (float): Top-p value for nucleus sampling.
    • truncate (integer): Truncate inputs tokens to the given size.
    • typical_p (float): Typical Decoding mass See Typical Decoding for Natural Language Generation for more information.
    • watermark (boolean): Watermarking with A Watermark for Large Language Models.
    • stream (boolean): Whether to stream the output tokens or not. Defaults to false.

Example payload

{
  "inputs": "What is Deep Learning?",
  "parameters": {
    "do_sample": true,
    "top_p": 0.95,
    "temperature": 0.2,
    "top_k": 50,
    "max_new_tokens": 256,
    "repetition_penalty": 1.03,
    "stop": ["\nUser:", "<|endoftext|>", "</s>"]
  }
}

OpenAI Chat Completion API compatibility

Additionally, Text Generation Inference (TGI) offers an OpenAI Chat Completion API compatible layer under the endpoint /v1/chat/completions, check the full specification in the OpenAI Chat Completion Create Documentation.

Specifications & capabilities

Input
text
Output
text
Published model ID
Sky-T1-32B-Preview

Evaluations

1–4 / 4

LiveBench

54.688%

source id
liveBench
leaderboard name
LiveBench Coding
dimension
coding
metric
Average score
rank
34
sample size
128
evaluated at
2025-02-06T18:31:23.006Z
source model id
sky-t1-32b-preview
Original result ↗

LiveBench

39.289%

source id
liveBench
leaderboard name
LiveBench Overall
dimension
general
metric
Average score
rank
85
sample size
318
evaluated at
2025-02-06T18:31:23.006Z
source model id
sky-t1-32b-preview
Original result ↗

LiveBench

20.481%

source id
liveBench
leaderboard name
LiveBench Language
dimension
intelligence
metric
Average score
rank
118
sample size
140
evaluated at
2025-01-20T00:11:16.285Z
source model id
sky-t1-32b-preview
Original result ↗

LiveBench

52.533%

source id
liveBench
leaderboard name
LiveBench Instruction Following
dimension
general
metric
Average score
rank
133
sample size
50
evaluated at
2025-01-20T00:13:02.680Z
source model id
sky-t1-32b-preview
Original result ↗

Published prices

1–2 / 2

Provider specifications & access

1–1 / 1

NovaSky-AI/Sky-T1-32B-Preview ↗

source model id
HuggingFace/novasky-ai-sky-t1-32b-preview@1
hosting
foundry-managed-compute
platforms
  • Microsoft Foundry
license
apache-2.0
architecture
input_modalities
  • text
output_modalities
  • text
capabilities

    Safety assessments

    1–1 / 1

    Foundation Model Transparency Index 2025 ↗

    39 / 100

    source id
    stanfordFMTI
    canonical model id
    azureFoundry/HuggingFace/novasky-ai-sky-t1-32b-preview@1
    taxonomy
    transparency
    hazard category
    transparency
    hazard name
    Organization transparency
    policy area
    Amazon
    assessment type
    organization-level disclosure
    metric
    disclosure_score
    result label
    39 / 100
    sample size
    100
    updated at
    2026-11-09T18:08:05.227Z

    Original sources

    1–8 / 8

    Hugging Face · NovaSky-AI/Sky-T1-32B-Preview ↗

    DeepInfra · Model page ↗

    Microsoft Foundry · Model page ↗

    Microsoft Foundry · Model documentation ↗

    DeepInfra · Catalog ↗

    GitHub · Catalog ↗

    Microsoft Foundry · Catalog ↗

    livebench.ai · Catalog ↗

    Source links

    1–4 / 4

    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