bigcode/starcoder2-15b

`bigcode/starcoder2-15b` powered by Text Generation Inference (TGI) - [Example Notebook](https://aka.ms/hugging-face-text-generation-streaming-online-endpoint) - [Original Model Card](https://hugging…

azureFoundry/HuggingFace/bigcode-starcoder2-15b@1

bigcode/starcoder2-15b 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
starcoder2-15b

Evaluations

1–20 / 34

BigCode Models Leaderboard

23.64%

source id
bigCode
leaderboard name
d
dimension
coding
metric
d
rank
3
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
BigCode
evaluation_sequence_length
16384
metric_kind
d
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
bigcode/bigcode-models-leaderboard/data/code_eval_board.csv
published_at
2024-11-11T20:36:38Z
source_revision
e9d7f58791a40b01c9477337f81d5d77602db07768042d96cbbb42e11a50ee09
metric_population
29
benchmark_evaluation
true
source model id
StarCoder2-15B
Original result ↗

BigCode Models Leaderboard

43.75%

source id
bigCode
leaderboard name
lua
dimension
coding
metric
lua
rank
8
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
BigCode
evaluation_sequence_length
16384
metric_kind
lua
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
bigcode/bigcode-models-leaderboard/data/code_eval_board.csv
published_at
2024-11-11T20:36:38Z
source_revision
e9d7f58791a40b01c9477337f81d5d77602db07768042d96cbbb42e11a50ee09
metric_population
29
benchmark_evaluation
true
source model id
StarCoder2-15B
Original result ↗

BigCode Models Leaderboard

22.41%

source id
bigCode
leaderboard name
racket
dimension
coding
metric
racket
rank
9
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
BigCode
evaluation_sequence_length
16384
metric_kind
racket
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
bigcode/bigcode-models-leaderboard/data/code_eval_board.csv
published_at
2024-11-11T20:36:38Z
source_revision
e9d7f58791a40b01c9477337f81d5d77602db07768042d96cbbb42e11a50ee09
metric_population
29
benchmark_evaluation
true
source model id
StarCoder2-15B
Original result ↗

BigCode Models Leaderboard

39.92%

source id
bigCode
leaderboard name
Win Rate
dimension
coding
metric
Win Rate
rank
13
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
BigCode
evaluation_sequence_length
16384
metric_kind
Win Rate
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
bigcode/bigcode-models-leaderboard/data/code_eval_board.csv
published_at
2024-11-11T20:36:38Z
source_revision
e9d7f58791a40b01c9477337f81d5d77602db07768042d96cbbb42e11a50ee09
metric_population
29
benchmark_evaluation
true
source model id
StarCoder2-15B
Original result ↗

BigCode Models Leaderboard

33.19%

source id
bigCode
leaderboard name
julia
dimension
coding
metric
julia
rank
13
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
BigCode
evaluation_sequence_length
16384
metric_kind
julia
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
bigcode/bigcode-models-leaderboard/data/code_eval_board.csv
published_at
2024-11-11T20:36:38Z
source_revision
e9d7f58791a40b01c9477337f81d5d77602db07768042d96cbbb42e11a50ee09
metric_population
29
benchmark_evaluation
true
source model id
StarCoder2-15B
Original result ↗

BigCode Models Leaderboard

34.85%

source id
bigCode
leaderboard name
Average score
dimension
coding
metric
Average score
rank
15
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
BigCode
evaluation_sequence_length
16384
metric_kind
Average score
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
bigcode/bigcode-models-leaderboard/data/code_eval_board.csv
published_at
2024-11-11T20:36:38Z
source_revision
e9d7f58791a40b01c9477337f81d5d77602db07768042d96cbbb42e11a50ee09
metric_population
29
benchmark_evaluation
true
source model id
StarCoder2-15B
Original result ↗

BigCode Models Leaderboard

41.44%

source id
bigCode
leaderboard name
cpp
dimension
coding
metric
cpp
rank
16
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
BigCode
evaluation_sequence_length
16384
metric_kind
cpp
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
bigcode/bigcode-models-leaderboard/data/code_eval_board.csv
published_at
2024-11-11T20:36:38Z
source_revision
e9d7f58791a40b01c9477337f81d5d77602db07768042d96cbbb42e11a50ee09
metric_population
29
benchmark_evaluation
true
source model id
StarCoder2-15B
Original result ↗

BigCode Models Leaderboard

39.48%

source id
bigCode
leaderboard name
php
dimension
coding
metric
php
rank
16
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
BigCode
evaluation_sequence_length
16384
metric_kind
php
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
bigcode/bigcode-models-leaderboard/data/code_eval_board.csv
published_at
2024-11-11T20:36:38Z
source_revision
e9d7f58791a40b01c9477337f81d5d77602db07768042d96cbbb42e11a50ee09
metric_population
29
benchmark_evaluation
true
source model id
StarCoder2-15B
Original result ↗

BigCode Models Leaderboard

38.03%

source id
bigCode
leaderboard name
rust
dimension
coding
metric
rust
rank
16
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
BigCode
evaluation_sequence_length
16384
metric_kind
rust
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
bigcode/bigcode-models-leaderboard/data/code_eval_board.csv
published_at
2024-11-11T20:36:38Z
source_revision
e9d7f58791a40b01c9477337f81d5d77602db07768042d96cbbb42e11a50ee09
metric_population
29
benchmark_evaluation
true
source model id
StarCoder2-15B
Original result ↗

BigCode Models Leaderboard

34.18%

source id
bigCode
leaderboard name
swift
dimension
coding
metric
swift
rank
16
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
BigCode
evaluation_sequence_length
16384
metric_kind
swift
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
bigcode/bigcode-models-leaderboard/data/code_eval_board.csv
published_at
2024-11-11T20:36:38Z
source_revision
e9d7f58791a40b01c9477337f81d5d77602db07768042d96cbbb42e11a50ee09
metric_population
29
benchmark_evaluation
true
source model id
StarCoder2-15B
Original result ↗

BigCode Models Leaderboard

44.24%

source id
bigCode
leaderboard name
javascript
dimension
coding
metric
javascript
rank
17
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
BigCode
evaluation_sequence_length
16384
metric_kind
javascript
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
bigcode/bigcode-models-leaderboard/data/code_eval_board.csv
published_at
2024-11-11T20:36:38Z
source_revision
e9d7f58791a40b01c9477337f81d5d77602db07768042d96cbbb42e11a50ee09
metric_population
29
benchmark_evaluation
true
source model id
StarCoder2-15B
Original result ↗

BigCode Models Leaderboard

33.86%

source id
bigCode
leaderboard name
java
dimension
coding
metric
java
rank
19
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
BigCode
evaluation_sequence_length
16384
metric_kind
java
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
bigcode/bigcode-models-leaderboard/data/code_eval_board.csv
published_at
2024-11-11T20:36:38Z
source_revision
e9d7f58791a40b01c9477337f81d5d77602db07768042d96cbbb42e11a50ee09
metric_population
29
benchmark_evaluation
true
source model id
StarCoder2-15B
Original result ↗

BigCode Models Leaderboard

19.81%

source id
bigCode
leaderboard name
r
dimension
coding
metric
r
rank
19
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
BigCode
evaluation_sequence_length
16384
metric_kind
r
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
bigcode/bigcode-models-leaderboard/data/code_eval_board.csv
published_at
2024-11-11T20:36:38Z
source_revision
e9d7f58791a40b01c9477337f81d5d77602db07768042d96cbbb42e11a50ee09
metric_population
29
benchmark_evaluation
true
source model id
StarCoder2-15B
Original result ↗

BigCode Models Leaderboard

44.15%

source id
bigCode
leaderboard name
humaneval-python
dimension
coding
metric
humaneval-python
rank
20
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
BigCode
evaluation_sequence_length
16384
metric_kind
humaneval-python
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
bigcode/bigcode-models-leaderboard/data/code_eval_board.csv
published_at
2024-11-11T20:36:38Z
source_revision
e9d7f58791a40b01c9477337f81d5d77602db07768042d96cbbb42e11a50ee09
metric_population
29
benchmark_evaluation
true
source model id
StarCoder2-15B
Original result ↗

Open LLM Leaderboard v1

52.237%

source id
openLLMLeaderboardV1
leaderboard name
Open LLM v1 GSM8K
dimension
math
metric
Accuracy
rank
2602
aggregation scope
suite
Open LLM v1
status
archived
precision
float16
task_count
6
metric_kind
Accuracy
rank_method
Derived competition rank over published evaluations with reported scores, including variants and source flags
weight_type
Original
published_at
2024-06-25T14:11:42Z
chat_template
false
suite_version
1
model_revision
995200dd02e1e5080004d1967664933b28d5e577
source_flagged
true
missing_metrics
    dataset_revision
    791ca1c841030008c6c266562c2b88c9b7196550
    metric_population
    7260
    ranking_population
    7260
    source_flag_anomaly
    true
    evaluated at
    2024-04-01T21:38:02.000Z
    source model id
    bigcode/starcoder2-15b
    Original result ↗

    Open LLM Leaderboard v2

    5.967%

    source id
    openLLMLeaderboardV2
    leaderboard name
    Open LLM v2 MATH Lvl 5 · Raw
    dimension
    math
    metric
    Raw accuracy
    rank
    3059
    aggregation scope
    suite
    Open LLM v2
    co2_kg
    67.68626903353528
    status
    archived
    precision
    bfloat16
    task_count
    6
    metric_kind
    Raw accuracy
    rank_method
    Derived competition rank over published evaluations with reported scores, including variants and source flags
    weight_type
    Original
    published_at
    2025-03-20T12:17:27Z
    chat_template
    false
    suite_version
    2
    model_revision
    46d44742909c03ac8cee08eb03fdebce02e193ec
    source_flagged
    false
    missing_metrics
      dataset_revision
      9c09a7cae43334062a82cb164f2ef255013dafa2
      metric_population
      4576
      ranking_population
      4576
      source_flag_anomaly
      false
      source model id
      bigcode/starcoder2-15b
      Original result ↗

      Open LLM Leaderboard v2

      5.967%

      source id
      openLLMLeaderboardV2
      leaderboard name
      Open LLM v2 MATH Lvl 5 · Normalized
      dimension
      math
      metric
      Normalized score
      rank
      3059
      aggregation scope
      suite
      Open LLM v2
      co2_kg
      67.68626903353528
      status
      archived
      precision
      bfloat16
      task_count
      6
      metric_kind
      Normalized score
      rank_method
      Derived competition rank over published evaluations with reported scores, including variants and source flags
      weight_type
      Original
      published_at
      2025-03-20T12:17:27Z
      chat_template
      false
      suite_version
      2
      model_revision
      46d44742909c03ac8cee08eb03fdebce02e193ec
      source_flagged
      false
      missing_metrics
        dataset_revision
        9c09a7cae43334062a82cb164f2ef255013dafa2
        metric_population
        4576
        ranking_population
        4576
        source_flag_anomaly
        false
        source model id
        bigcode/starcoder2-15b
        Original result ↗

        Open LLM Leaderboard v2

        44.48%

        source id
        openLLMLeaderboardV2
        leaderboard name
        Open LLM v2 BBH · Raw
        dimension
        reasoning
        metric
        Raw accuracy
        rank
        3075
        aggregation scope
        suite
        Open LLM v2
        co2_kg
        67.68626903353528
        status
        archived
        precision
        bfloat16
        task_count
        6
        metric_kind
        Raw accuracy
        rank_method
        Derived competition rank over published evaluations with reported scores, including variants and source flags
        weight_type
        Original
        published_at
        2025-03-20T12:17:27Z
        chat_template
        false
        suite_version
        2
        model_revision
        46d44742909c03ac8cee08eb03fdebce02e193ec
        source_flagged
        false
        missing_metrics
          dataset_revision
          9c09a7cae43334062a82cb164f2ef255013dafa2
          metric_population
          4576
          ranking_population
          4576
          source_flag_anomaly
          false
          source model id
          bigcode/starcoder2-15b
          Original result ↗

          Open LLM Leaderboard v2

          20.374%

          source id
          openLLMLeaderboardV2
          leaderboard name
          Open LLM v2 BBH · Normalized
          dimension
          reasoning
          metric
          Normalized score
          rank
          3179
          aggregation scope
          suite
          Open LLM v2
          co2_kg
          67.68626903353528
          status
          archived
          precision
          bfloat16
          task_count
          6
          metric_kind
          Normalized score
          rank_method
          Derived competition rank over published evaluations with reported scores, including variants and source flags
          weight_type
          Original
          published_at
          2025-03-20T12:17:27Z
          chat_template
          false
          suite_version
          2
          model_revision
          46d44742909c03ac8cee08eb03fdebce02e193ec
          source_flagged
          false
          missing_metrics
            dataset_revision
            9c09a7cae43334062a82cb164f2ef255013dafa2
            metric_population
            4576
            ranking_population
            4576
            source_flag_anomaly
            false
            source model id
            bigcode/starcoder2-15b
            Original result ↗

            Open LLM Leaderboard v2

            27.349%

            source id
            openLLMLeaderboardV2
            leaderboard name
            Open LLM v2 GPQA · Raw
            dimension
            knowledge
            metric
            Raw accuracy
            rank
            3246
            aggregation scope
            suite
            Open LLM v2
            co2_kg
            67.68626903353528
            status
            archived
            precision
            bfloat16
            task_count
            6
            metric_kind
            Raw accuracy
            rank_method
            Derived competition rank over published evaluations with reported scores, including variants and source flags
            weight_type
            Original
            published_at
            2025-03-20T12:17:27Z
            chat_template
            false
            suite_version
            2
            model_revision
            46d44742909c03ac8cee08eb03fdebce02e193ec
            source_flagged
            false
            missing_metrics
              dataset_revision
              9c09a7cae43334062a82cb164f2ef255013dafa2
              metric_population
              4576
              ranking_population
              4576
              source_flag_anomaly
              false
              source model id
              bigcode/starcoder2-15b
              Original result ↗

              Provider specifications & access

              1–2 / 2

              bigcode/starcoder2-15b ↗

              source model id
              bigcode/starcoder2-15b
              hosting
              nvidia-inference-listed
              platforms
              • NVIDIA inference catalog
              architecture
              input_modalities
                output_modalities
                  capabilities
                    availability
                    Listed by inference API; runtime availability unverified

                    bigcode/starcoder2-15b ↗

                    source model id
                    HuggingFace/bigcode-starcoder2-15b@1
                    hosting
                    foundry-managed-compute
                    platforms
                    • Microsoft Foundry
                    license
                    bigcode-openrail-m
                    architecture
                    input_modalities
                    • text
                    output_modalities
                    • text
                    capabilities

                      Original sources

                      1–8 / 8

                      Hugging Face · Model repository ↗

                      Microsoft Foundry · Model page ↗

                      Microsoft Foundry · Model documentation ↗

                      NVIDIA · Catalog ↗

                      Hugging Face · Catalog ↗

                      Hugging Face · Catalog ↗

                      Hugging Face · Catalog ↗

                      Microsoft Foundry · Catalog ↗

                      Source links

                      1–5 / 5

                      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