Qwen/Qwen1.5-14B-Chat

`Qwen/Qwen1.5-14B-Chat` powered by Text Generation Inference (TGI) - [Example Notebook](https://aka.ms/hugging-face-text-generation-streaming-online-endpoint) - [Original Model Card](https://huggingf…

azureFoundry/HuggingFace/qwen-qwen1.5-14b-chat@1

Qwen/Qwen1.5-14B-Chat 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
Qwen1.5-14B-Chat

Evaluations

1–20 / 95

Open Ko-LLM Leaderboard

42.873

source id
openKoLLM
leaderboard name
ko_eqbench · eqbench,none
dimension
general
metric
ko_eqbench · eqbench,none
rank
40
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
Open Ko-LLM
language
ko
execution
model_dtype
torch.float16
num_fewshot_seeds
1
override_batch_size
1
num_few_shot_default
0
task_versions
all
2
ko_gsm8k
2
ko_ifeval
2
ko_eqbench
2
ko_winogrande
2
kornat_common
2
kornat_social
2
kornat_helpful
2
kornat_harmless
2
ko_gpqa_diamond_zeroshot
2
metric_kind
ko_eqbench · eqbench,none
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
open-ko-llm-leaderboard/results/Qwen/Qwen1.5-14B-Chat/result_2024-05-13 18:15:27.json
published_at
2025-01-12T22:16:32Z
model_revision
9492b22871f43e975435455f5c616c77fe7a50ec
source_revision
79263b00db68621dc9765e72ec588deada54cd531a2fd26b8a849eda14e14574
metric_population
994
benchmark_evaluation
true
source model id
Qwen/Qwen1.5-14B-Chat
Original result ↗

Open Ko-LLM Leaderboard

52.725%

source id
openKoLLM
leaderboard name
kornat_helpful · acc_norm,none
dimension
general
metric
kornat_helpful · acc_norm,none
rank
54
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
Open Ko-LLM
language
ko
execution
model_dtype
torch.float16
num_fewshot_seeds
1
override_batch_size
1
num_few_shot_default
0
task_versions
all
2
ko_gsm8k
2
ko_ifeval
2
ko_eqbench
2
ko_winogrande
2
kornat_common
2
kornat_social
2
kornat_helpful
2
kornat_harmless
2
ko_gpqa_diamond_zeroshot
2
metric_kind
kornat_helpful · acc_norm,none
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
open-ko-llm-leaderboard/results/Qwen/Qwen1.5-14B-Chat/result_2024-05-13 18:15:27.json
published_at
2025-01-12T22:16:32Z
model_revision
9492b22871f43e975435455f5c616c77fe7a50ec
source_revision
79263b00db68621dc9765e72ec588deada54cd531a2fd26b8a849eda14e14574
metric_population
994
benchmark_evaluation
true
source model id
Qwen/Qwen1.5-14B-Chat
Original result ↗

Open Ko-LLM Leaderboard

53.904%

source id
openKoLLM
leaderboard name
ko_gsm8k · exact_match,flexible-extract
dimension
general
metric
ko_gsm8k · exact_match,flexible-extract
rank
61
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
Open Ko-LLM
language
ko
execution
model_dtype
torch.float16
num_fewshot_seeds
1
override_batch_size
1
num_few_shot_default
0
task_versions
all
2
ko_gsm8k
2
ko_ifeval
2
ko_eqbench
2
ko_winogrande
2
kornat_common
2
kornat_social
2
kornat_helpful
2
kornat_harmless
2
ko_gpqa_diamond_zeroshot
2
metric_kind
ko_gsm8k · exact_match,flexible-extract
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
open-ko-llm-leaderboard/results/Qwen/Qwen1.5-14B-Chat/result_2024-05-13 18:15:27.json
published_at
2025-01-12T22:16:32Z
model_revision
9492b22871f43e975435455f5c616c77fe7a50ec
source_revision
79263b00db68621dc9765e72ec588deada54cd531a2fd26b8a849eda14e14574
metric_population
994
benchmark_evaluation
true
source model id
Qwen/Qwen1.5-14B-Chat
Original result ↗

Open Ko-LLM Leaderboard

70.057%

source id
openKoLLM
leaderboard name
kornat_harmless · acc_norm,none
dimension
general
metric
kornat_harmless · acc_norm,none
rank
69
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
Open Ko-LLM
language
ko
execution
model_dtype
torch.float16
num_fewshot_seeds
1
override_batch_size
1
num_few_shot_default
0
task_versions
all
2
ko_gsm8k
2
ko_ifeval
2
ko_eqbench
2
ko_winogrande
2
kornat_common
2
kornat_social
2
kornat_helpful
2
kornat_harmless
2
ko_gpqa_diamond_zeroshot
2
metric_kind
kornat_harmless · acc_norm,none
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
open-ko-llm-leaderboard/results/Qwen/Qwen1.5-14B-Chat/result_2024-05-13 18:15:27.json
published_at
2025-01-12T22:16:32Z
model_revision
9492b22871f43e975435455f5c616c77fe7a50ec
source_revision
79263b00db68621dc9765e72ec588deada54cd531a2fd26b8a849eda14e14574
metric_population
994
benchmark_evaluation
true
source model id
Qwen/Qwen1.5-14B-Chat
Original result ↗

Open Ko-LLM Leaderboard

44.807%

source id
openKoLLM
leaderboard name
ko_ifeval · inst_level_strict_acc,none
dimension
general
metric
ko_ifeval · inst_level_strict_acc,none
rank
103
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
Open Ko-LLM
language
ko
execution
model_dtype
torch.float16
num_fewshot_seeds
1
override_batch_size
1
num_few_shot_default
0
task_versions
all
2
ko_gsm8k
2
ko_ifeval
2
ko_eqbench
2
ko_winogrande
2
kornat_common
2
kornat_social
2
kornat_helpful
2
kornat_harmless
2
ko_gpqa_diamond_zeroshot
2
metric_kind
ko_ifeval · inst_level_strict_acc,none
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
open-ko-llm-leaderboard/results/Qwen/Qwen1.5-14B-Chat/result_2024-05-13 18:15:27.json
published_at
2025-01-12T22:16:32Z
model_revision
9492b22871f43e975435455f5c616c77fe7a50ec
source_revision
79263b00db68621dc9765e72ec588deada54cd531a2fd26b8a849eda14e14574
metric_population
994
benchmark_evaluation
true
source model id
Qwen/Qwen1.5-14B-Chat
Original result ↗

Open Ko-LLM Leaderboard

48.813%

source id
openKoLLM
leaderboard name
ko_ifeval · inst_level_loose_acc,none
dimension
general
metric
ko_ifeval · inst_level_loose_acc,none
rank
108
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
Open Ko-LLM
language
ko
execution
model_dtype
torch.float16
num_fewshot_seeds
1
override_batch_size
1
num_few_shot_default
0
task_versions
all
2
ko_gsm8k
2
ko_ifeval
2
ko_eqbench
2
ko_winogrande
2
kornat_common
2
kornat_social
2
kornat_helpful
2
kornat_harmless
2
ko_gpqa_diamond_zeroshot
2
metric_kind
ko_ifeval · inst_level_loose_acc,none
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
open-ko-llm-leaderboard/results/Qwen/Qwen1.5-14B-Chat/result_2024-05-13 18:15:27.json
published_at
2025-01-12T22:16:32Z
model_revision
9492b22871f43e975435455f5c616c77fe7a50ec
source_revision
79263b00db68621dc9765e72ec588deada54cd531a2fd26b8a849eda14e14574
metric_population
994
benchmark_evaluation
true
source model id
Qwen/Qwen1.5-14B-Chat
Original result ↗

Open Ko-LLM Leaderboard

39.474%

source id
openKoLLM
leaderboard name
ko_ifeval · prompt_level_loose_acc,none
dimension
general
metric
ko_ifeval · prompt_level_loose_acc,none
rank
113
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
Open Ko-LLM
language
ko
execution
model_dtype
torch.float16
num_fewshot_seeds
1
override_batch_size
1
num_few_shot_default
0
task_versions
all
2
ko_gsm8k
2
ko_ifeval
2
ko_eqbench
2
ko_winogrande
2
kornat_common
2
kornat_social
2
kornat_helpful
2
kornat_harmless
2
ko_gpqa_diamond_zeroshot
2
metric_kind
ko_ifeval · prompt_level_loose_acc,none
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
open-ko-llm-leaderboard/results/Qwen/Qwen1.5-14B-Chat/result_2024-05-13 18:15:27.json
published_at
2025-01-12T22:16:32Z
model_revision
9492b22871f43e975435455f5c616c77fe7a50ec
source_revision
79263b00db68621dc9765e72ec588deada54cd531a2fd26b8a849eda14e14574
metric_population
994
benchmark_evaluation
true
source model id
Qwen/Qwen1.5-14B-Chat
Original result ↗

Open Ko-LLM Leaderboard

35.425%

source id
openKoLLM
leaderboard name
ko_ifeval · prompt_level_strict_acc,none
dimension
general
metric
ko_ifeval · prompt_level_strict_acc,none
rank
124
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
Open Ko-LLM
language
ko
execution
model_dtype
torch.float16
num_fewshot_seeds
1
override_batch_size
1
num_few_shot_default
0
task_versions
all
2
ko_gsm8k
2
ko_ifeval
2
ko_eqbench
2
ko_winogrande
2
kornat_common
2
kornat_social
2
kornat_helpful
2
kornat_harmless
2
ko_gpqa_diamond_zeroshot
2
metric_kind
ko_ifeval · prompt_level_strict_acc,none
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
open-ko-llm-leaderboard/results/Qwen/Qwen1.5-14B-Chat/result_2024-05-13 18:15:27.json
published_at
2025-01-12T22:16:32Z
model_revision
9492b22871f43e975435455f5c616c77fe7a50ec
source_revision
79263b00db68621dc9765e72ec588deada54cd531a2fd26b8a849eda14e14574
metric_population
994
benchmark_evaluation
true
source model id
Qwen/Qwen1.5-14B-Chat
Original result ↗

Open Ko-LLM Leaderboard

87.135%

source id
openKoLLM
leaderboard name
ko_eqbench · percent_parseable,none
dimension
general
metric
ko_eqbench · percent_parseable,none
rank
157
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
Open Ko-LLM
language
ko
execution
model_dtype
torch.float16
num_fewshot_seeds
1
override_batch_size
1
num_few_shot_default
0
task_versions
all
2
ko_gsm8k
2
ko_ifeval
2
ko_eqbench
2
ko_winogrande
2
kornat_common
2
kornat_social
2
kornat_helpful
2
kornat_harmless
2
ko_gpqa_diamond_zeroshot
2
metric_kind
ko_eqbench · percent_parseable,none
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
open-ko-llm-leaderboard/results/Qwen/Qwen1.5-14B-Chat/result_2024-05-13 18:15:27.json
published_at
2025-01-12T22:16:32Z
model_revision
9492b22871f43e975435455f5c616c77fe7a50ec
source_revision
79263b00db68621dc9765e72ec588deada54cd531a2fd26b8a849eda14e14574
metric_population
994
benchmark_evaluation
true
source model id
Qwen/Qwen1.5-14B-Chat
Original result ↗

Open Ko-LLM Leaderboard

25.253%

source id
openKoLLM
leaderboard name
ko_gpqa_diamond_zeroshot · acc_norm,none
dimension
general
metric
ko_gpqa_diamond_zeroshot · acc_norm,none
rank
196
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
Open Ko-LLM
language
ko
execution
model_dtype
torch.float16
num_fewshot_seeds
1
override_batch_size
1
num_few_shot_default
0
task_versions
all
2
ko_gsm8k
2
ko_ifeval
2
ko_eqbench
2
ko_winogrande
2
kornat_common
2
kornat_social
2
kornat_helpful
2
kornat_harmless
2
ko_gpqa_diamond_zeroshot
2
metric_kind
ko_gpqa_diamond_zeroshot · acc_norm,none
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
open-ko-llm-leaderboard/results/Qwen/Qwen1.5-14B-Chat/result_2024-05-13 18:15:27.json
published_at
2025-01-12T22:16:32Z
model_revision
9492b22871f43e975435455f5c616c77fe7a50ec
source_revision
79263b00db68621dc9765e72ec588deada54cd531a2fd26b8a849eda14e14574
metric_population
994
benchmark_evaluation
true
source model id
Qwen/Qwen1.5-14B-Chat
Original result ↗

LMArena

1,082.929

source id
lmarena
leaderboard name
LMArena Text Style Control Japanese
dimension
style
metric
Arena rating
rank
268
sample size
217
evaluated at
2026-11-09T00:00:00.000Z
source model id
Qwen1.5-14B-Chat
confidence lower
1041.8316438765885
confidence upper
1124.0261345463782
Original result ↗

LMArena

1,019.552

source id
lmarena
leaderboard name
LMArena Text Japanese
dimension
general
metric
Arena rating
rank
268
sample size
217
evaluated at
2026-11-09T00:00:00.000Z
source model id
Qwen1.5-14B-Chat
confidence lower
979.4135495991561
confidence upper
1059.6913461097206
Original result ↗

LMArena

1,190.809

source id
lmarena
leaderboard name
LMArena Text Style Control French
dimension
style
metric
Arena rating
rank
280
sample size
279
evaluated at
2026-11-09T00:00:00.000Z
source model id
Qwen1.5-14B-Chat
confidence lower
1151.6790849836898
confidence upper
1229.9398477649117
Original result ↗

LMArena

1,115.61

source id
lmarena
leaderboard name
LMArena Text French
dimension
general
metric
Arena rating
rank
281
sample size
279
evaluated at
2026-11-09T00:00:00.000Z
source model id
Qwen1.5-14B-Chat
confidence lower
1076.7134267832298
confidence upper
1154.506575887792
Original result ↗

LMArena

1,156.477

source id
lmarena
leaderboard name
LMArena Text Style Control Spanish
dimension
style
metric
Arena rating
rank
293
sample size
293
evaluated at
2026-11-09T00:00:00.000Z
source model id
Qwen1.5-14B-Chat
confidence lower
1120.4915923282028
confidence upper
1192.463069727501
Original result ↗

LMArena

1,085.091

source id
lmarena
leaderboard name
LMArena Text Spanish
dimension
general
metric
Arena rating
rank
293
sample size
293
evaluated at
2026-11-09T00:00:00.000Z
source model id
Qwen1.5-14B-Chat
confidence lower
1049.394664195166
confidence upper
1120.786948385049
Original result ↗

Open Ko-LLM Leaderboard

16.376%

source id
openKoLLM
leaderboard name
ko_gsm8k · exact_match,strict-match
dimension
general
metric
ko_gsm8k · exact_match,strict-match
rank
301
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
Open Ko-LLM
language
ko
execution
model_dtype
torch.float16
num_fewshot_seeds
1
override_batch_size
1
num_few_shot_default
0
task_versions
all
2
ko_gsm8k
2
ko_ifeval
2
ko_eqbench
2
ko_winogrande
2
kornat_common
2
kornat_social
2
kornat_helpful
2
kornat_harmless
2
ko_gpqa_diamond_zeroshot
2
metric_kind
ko_gsm8k · exact_match,strict-match
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
open-ko-llm-leaderboard/results/Qwen/Qwen1.5-14B-Chat/result_2024-05-13 18:15:27.json
published_at
2025-01-12T22:16:32Z
model_revision
9492b22871f43e975435455f5c616c77fe7a50ec
source_revision
79263b00db68621dc9765e72ec588deada54cd531a2fd26b8a849eda14e14574
metric_population
994
benchmark_evaluation
true
source model id
Qwen/Qwen1.5-14B-Chat
Original result ↗

LMArena

1,107.466

source id
lmarena
leaderboard name
LMArena Text Style Control German
dimension
style
metric
Arena rating
rank
304
sample size
540
evaluated at
2026-11-09T00:00:00.000Z
source model id
Qwen1.5-14B-Chat
confidence lower
1081.1536866151541
confidence upper
1133.777431664662
Original result ↗

LMArena

1,042.38

source id
lmarena
leaderboard name
LMArena Text German
dimension
general
metric
Arena rating
rank
306
sample size
540
evaluated at
2026-11-09T00:00:00.000Z
source model id
Qwen1.5-14B-Chat
confidence lower
1016.3153029810344
confidence upper
1068.4445825158857
Original result ↗

LMArena

1,242.002

source id
lmarena
leaderboard name
LMArena Text Style Control Chinese
dimension
style
metric
Arena rating
rank
324
sample size
3152
evaluated at
2026-11-09T00:00:00.000Z
source model id
Qwen1.5-14B-Chat
confidence lower
1227.9356802204845
confidence upper
1256.0684133371992
Original result ↗

Provider specifications & access

1–1 / 1

Qwen/Qwen1.5-14B-Chat ↗

source model id
HuggingFace/qwen-qwen1.5-14b-chat@1
hosting
foundry-managed-compute
platforms
  • Microsoft Foundry
license
other
architecture
input_modalities
  • text
output_modalities
  • text
capabilities

    Safety assessments

    1–1 / 1

    Foundation Model Transparency Index 2025 ↗

    26 / 100

    source id
    stanfordFMTI
    canonical model id
    azureFoundry/HuggingFace/qwen-qwen1.5-14b-chat@1
    taxonomy
    transparency
    hazard category
    transparency
    hazard name
    Organization transparency
    policy area
    Alibaba
    assessment type
    organization-level disclosure
    metric
    disclosure_score
    result label
    26 / 100
    sample size
    100
    updated at
    2026-11-09T18:08:05.227Z

    Original sources

    1–10 / 10

    Hugging Face · Model repository ↗

    Microsoft Foundry · Model page ↗

    Microsoft Foundry · Model documentation ↗

    GitHub · Catalog ↗

    Hugging Face · Catalog ↗

    Hugging Face · Catalog ↗

    Hugging Face · Catalog ↗

    Hugging Face · Catalog ↗

    LMArena · Catalog ↗

    Microsoft Foundry · Catalog ↗

    Source links

    1–7 / 7

    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