Qwen2-7B-Instruct

Home/Models/Qwen/Qwen2-7B-Instruct

Qwen/Qwen2-7B-Instruct

kind: original
quant: bf16 (16-bit)
family: qwen
modality: text-generation
root model: Qwen/Qwen2-7B
provider: Qwen
license: apache-2.0
language: en
context: 32768,
library: —
vRAM (GB): —
size on disk: —
downloads: 629,607
likes: 687
created: —
last modified: 2024-08-21T10:29:04+00:00 (2024)
huggingface: https://huggingface.co/Qwen/Qwen2-7B-Instruct
tags: transformerssafetensorsqwen2text-generationchatconversationalenarxiv:2309.00071base_model:Qwen/Qwen2-7Bbase_model:finetune:Qwen/Qwen2-7Blicense:apache-2.0eval-resultstext-generation-inferenceendpoints_compatibleregion:usdeploy:sagemaker

benchmark	category	score	context	conf	evidence
GSM8K	math	79.6	GSM8K	medium	`\| GSM8K \| 79.6 \| 84.8 \| 79.6 \| 60.3 \| 82.3 \|`
MMLU	knowledge	68.4	MMLU	medium	`\| MMLU \| 68.4 \| 69.5 \| 72.4 \| 59.5 \| 70.5 \|`
MBPP	coding	67.9	MBPP	medium	`\| MBPP \| 67.9 \| - \| - \| 48.9 \| 67.2 \|`
HumanEval	coding	62.2	Humaneval	medium	`\| Humaneval \| 62.2 \| 66.5 \| 71.8 \| 46.3 \| 79.9 \|`
EvalPlus	coding	60.9	Evalplus	medium	`\| Evalplus \| 60.9 \| - \| - \| 44.8 \| 70.3 \|`
C-Eval	knowledge	45.9	C-Eval	medium	`\| C-Eval \| 45.9 \| - \| 75.6 \| 67.3 \| 77.2 \|`
MMLU-Pro	knowledge	41.0	MMLU-Pro	medium	`\| MMLU-Pro \| 41.0 \| - \| - \| 29.1 \| 44.1 \|`
GPQA	reasoning	34.2	GPQA	medium	`\| GPQA \| 34.2 \| - \| - \| 27.8 \| 25.3 \|`
MATH	math	30.0	MATH	medium	`\| MATH \| 30.0 \| 47.7 \| 50.6 \| 23.2 \| 49.6 \|`
LiveCodeBench	coding	17.3	LiveCodeBench	medium	`\| LiveCodeBench \| 17.3 \| - \| - \| 6.0 \| 26.6 \|`
MT-Bench	chat	8.05	MT-Bench	medium	`\| MT-Bench \| 8.05 \| 8.20 \| 8.35 \| 7.60 \| 8.41 \|`

none scraped.