Sponsored by
APIMart
tencent / Hunyuan-7B-Instruct
Model's Last Updated: September 02 2025
text-generation
Introduction of Hunyuan-7B-Instruct
Model Details of Hunyuan-7B-Instruct
Model Introduction
The 7B models released by Hunyuan this time: Hunyuan-7B-Pretrain and Hunyuan-7B-Instruct , use better data allocation and training, have strong performance, and have achieved a good balance between computing and performance. It stands out from many large-scale language models and is currently one of the strongest Chinese 7B Dense models.
Introduction to Technical Advantages
Model
- Extended long text capability to 256K and utilizes Grouped Query Attention (GQA)
Inference Framework
- This open-source release offers two inference backend options tailored for the Hunyuan-7B model: the popular vLLM-backend and the TensorRT-LLM Backend. In this release, we are initially open-sourcing the vLLM solution, with plans to release the TRT-LLM solution in the near future.
Training Framework
- The Hunyuan-7B open-source model is fully compatible with the Hugging Face format, enabling researchers and developers to perform model fine-tuning using the hf-deepspeed framework. Learn more : Tencent-Hunyuan-Large 。
Related News
-
2025.1.24 We have open-sourced
Hunyuan-7B-Pretrain
,
Hunyuan-7B-Instruct
on Hugging Face.
Benchmark
Note: The following benchmarks are evaluated by TRT-LLM-backend
Hunyuan-7B-Pretrain
| Qwen2.5-7B | Llama3-8B | OLMO2-7B | HunYuan-7B-V2 | |
|---|---|---|---|---|
| MMLU | 74.26 | 66.95 | 63.7 | 75.37 |
| MMLU-Pro | 46.17 | 34.04 | 31 | 47.54 |
| MMLU-CF | 61.01 | 55.21 | 52.94 | 59.62 |
| MMLU-Redux | 73.47 | 66.44 | 63.74 | 74.54 |
| BBH | 70.4 | 62.16 | 38.01 | 70.77 |
| HellaSwag | 75.82 | 78.24 | 61.97 | 80.77 |
| WinoGrande | 69.69 | 73.64 | 74.43 | 71.51 |
| PIQA | 79.33 | 80.52 | 80.63 | 81.45 |
| SIQA | 77.48 | 61.05 | 65.2 | 79.73 |
| NaturalQuestions | 31.77 | 35.43 | 36.9 | 33.52 |
| DROP | 68.2 | 60.13 | 60.8 | 68.63 |
| ARC-C | 91.64 | 77.59 | 74.92 | 91.97 |
| TriviaQA | 69.31 | 78.61 | 78 | 74.31 |
| Chinese-SimpleQA | 30.37 | 19.4 | 7.35 | 30.51 |
| SimpleQA | 4.98 | 7.68 | 4.51 | 3.73 |
| CMMLU | 81.39 | 50.25 | 38.79 | 82.19 |
| C-Eval | 81.11 | 50.4 | 38.53 | 82.12 |
| C3 | 71.77 | 61.5 | 54 | 79.07 |
| GSM8K | 82.71 | 57.54 | 67.5 | 93.33 |
| MATH | 49.6 | 18.45 | 19 | 62.15 |
| CMATH | 84.33 | 52.83 | 44 | 88.5 |
| HumanEval | 57.93 | 35.98 | 15.24 | 59.15 |
Hunyuan-7B-Instruct
| Model | Qwen2.5-7B-Instruct | Llama-3-8B-Instruct | OLMo-2-1124-7B-DPO | Hunyuan-7B-Instruct |
|---|---|---|---|---|
| ARC-C | 89.83 | 82.4 | - | 88.81 |
| BBH | 66.24 | - | 46.6 | 76.47 |
| CEval | 76.82 | - | - | 81.8 |
| CMMLU | 78.55 | - | - | 82.29 |
| DROP_F1 | 80.63 | - | 60.5 | 82.96 |
| GPQA | 36.87 | 34.6 | - | 47.98 |
| Gsm8k | 80.14 | 80.6 | 85.1 | 90.14 |
| HellaSwag | 83.34 | - | - | 86.57 |
| HumanEval | 84.8 | 60.4 | - | 84.0 |
| MATH | 72.86 | - | 32.5 | 70.64 |
| MMLU | 72.36 | 68.5 | 61.3 | 79.18 |
Quick Start
You can refer to the content in Tencent-Hunyuan-Large to get started quickly. The training and inference code can use the version provided in this github repository.
Inference Framework
- This open-source release offers two inference backend options tailored for the Hunyuan-7B model: the popular vLLM-backend and the TensorRT-LLM Backend. In this release, we are initially open-sourcing the vLLM solution, with plans to release the TRT-LLM solution in the near future.
Inference Performance
This section presents the efficiency test results of deploying various models using vLLM, including inference speed (tokens/s) under different batch sizes.
| Inference Framework | Model | Number of GPUs (GPU productA) | input_length | batch=1 | batch=4 |
|---|---|---|---|---|---|
| vLLM | hunyuan-7B | 1 | 2048 | 78.9 | 279.5 |
Contact Us
If you would like to leave a message for our R&D and product teams, Welcome to contact our open-source team . You can also contact us via email ( [email protected] ).
Runs of tencent Hunyuan-7B-Instruct on huggingface.co
51.3K
Total runs
0
24-hour runs
55
3-day runs
-63
7-day runs
34.5K
30-day runs
More Information About Hunyuan-7B-Instruct huggingface.co Model
Url of Hunyuan-7B-Instruct
Hunyuan-7B-Instruct huggingface.co Url
Provider of Hunyuan-7B-Instruct huggingface.co
Other API from tencent
Total runs:
337.1K
Run Growth:
127.1K
Growth Rate:
37.30%
Total runs:
254.9K
Run Growth:
193.9K
Growth Rate:
86.72%
Total runs:
113.2K
Run Growth:
11.7K
Growth Rate:
10.47%
Total runs:
90.7K
Run Growth:
-582.4K
Growth Rate:
-642.43%
Total runs:
65.1K
Run Growth:
15.8K
Growth Rate:
24.76%
Total runs:
56.3K
Run Growth:
-5.3K
Growth Rate:
-9.56%
Total runs:
43.0K
Run Growth:
42.6K
Growth Rate:
99.07%
Total runs:
34.9K
Run Growth:
6.5K
Growth Rate:
18.85%
Total runs:
22.1K
Run Growth:
3.2K
Growth Rate:
18.96%
Total runs:
22.0K
Run Growth:
17.6K
Growth Rate:
79.99%
Total runs:
18.4K
Run Growth:
15.8K
Growth Rate:
86.24%
Total runs:
16.6K
Run Growth:
-1.3K
Growth Rate:
-8.02%
Total runs:
16.5K
Run Growth:
-299
Growth Rate:
-1.73%
Total runs:
15.4K
Run Growth:
6.3K
Growth Rate:
42.50%
Total runs:
12.2K
Run Growth:
-10.5K
Growth Rate:
-86.41%
Total runs:
11.4K
Run Growth:
3.7K
Growth Rate:
32.55%
Total runs:
6.3K
Run Growth:
4.2K
Growth Rate:
66.60%
Total runs:
6.1K
Run Growth:
6.1K
Growth Rate:
100.00%
Total runs:
4.4K
Run Growth:
-1.0K
Growth Rate:
-24.15%
Total runs:
3.9K
Run Growth:
3.8K
Growth Rate:
97.48%
Total runs:
3.5K
Run Growth:
-5.4K
Growth Rate:
-157.16%
Total runs:
3.4K
Run Growth:
-207
Growth Rate:
-6.41%
Total runs:
3.2K
Run Growth:
2.6K
Growth Rate:
82.74%
Total runs:
2.6K
Run Growth:
-2.3K
Growth Rate:
-87.99%
Total runs:
2.4K
Run Growth:
-1.6K
Growth Rate:
-66.58%
Total runs:
2.2K
Run Growth:
-1.3K
Growth Rate:
-59.31%
Total runs:
1.8K
Run Growth:
327
Growth Rate:
17.71%
Total runs:
1.7K
Run Growth:
125
Growth Rate:
7.29%
Total runs:
1.7K
Run Growth:
-873
Growth Rate:
-51.17%
Total runs:
1.5K
Run Growth:
56
Growth Rate:
3.44%
Total runs:
1.4K
Run Growth:
1.2K
Growth Rate:
82.02%
Total runs:
1.4K
Run Growth:
954
Growth Rate:
70.10%
Total runs:
1.2K
Run Growth:
-857
Growth Rate:
-68.02%
Total runs:
1.1K
Run Growth:
747
Growth Rate:
66.52%
Total runs:
1.1K
Run Growth:
-799
Growth Rate:
-70.83%
Total runs:
1.1K
Run Growth:
684
Growth Rate:
64.71%
Total runs:
699
Run Growth:
532
Growth Rate:
77.33%
Total runs:
695
Run Growth:
218
Growth Rate:
32.68%
Total runs:
693
Run Growth:
-114
Growth Rate:
-16.45%
Total runs:
656
Run Growth:
250
Growth Rate:
43.55%
Total runs:
554
Run Growth:
163
Growth Rate:
29.64%
Total runs:
529
Run Growth:
166
Growth Rate:
32.30%
Total runs:
528
Run Growth:
275
Growth Rate:
57.29%
Total runs:
494
Run Growth:
-153
Growth Rate:
-32.42%
Total runs:
480
Run Growth:
79
Growth Rate:
16.46%
Total runs:
468
Run Growth:
138
Growth Rate:
29.36%
Total runs:
451
Run Growth:
-1.7K
Growth Rate:
-381.96%
Total runs:
418
Run Growth:
418
Growth Rate:
100.00%
Total runs:
408
Run Growth:
252
Growth Rate:
63.64%
Total runs:
401
Run Growth:
139
Growth Rate:
35.64%
Total runs:
390
Run Growth:
220
Growth Rate:
59.62%
Total runs:
329
Run Growth:
37
Growth Rate:
11.64%
Total runs:
317
Run Growth:
-81
Growth Rate:
-25.55%
Total runs:
315
Run Growth:
153
Growth Rate:
48.57%
Total runs:
297
Run Growth:
193
Growth Rate:
68.93%
Total runs:
297
Run Growth:
-416
Growth Rate:
-140.07%
Total runs:
290
Run Growth:
-86
Growth Rate:
-29.66%
Total runs:
280
Run Growth:
-137
Growth Rate:
-48.93%
Total runs:
277
Run Growth:
-69
Growth Rate:
-24.91%
Total runs:
270
Run Growth:
102
Growth Rate:
39.53%
Total runs:
262
Run Growth:
111
Growth Rate:
43.87%
Total runs:
258
Run Growth:
-283
Growth Rate:
-111.86%
Total runs:
246
Run Growth:
62
Growth Rate:
26.16%
Total runs:
237
Run Growth:
-27
Growth Rate:
-12.22%
Total runs:
233
Run Growth:
91
Growth Rate:
38.56%
Total runs:
213
Run Growth:
54
Growth Rate:
26.60%
Total runs:
213
Run Growth:
85
Growth Rate:
43.59%