DeepSeek-V2-Chat

Home/Models/deepseek-ai/DeepSeek-V2-Chat

deepseek-ai/DeepSeek-V2-Chat

kind: original
quant: bf16 (16-bit)
family: deepseek
modality: text-generation
root model: deepseek-ai/DeepSeek-V2-Chat
provider: deepseek-ai
license: other
language: —
context: —
library: —
vRAM (GB): —
size on disk: —
downloads: 10,482
likes: 462
created: —
last modified: 2024-06-08T09:14:11+00:00 (2024)
huggingface: https://huggingface.co/deepseek-ai/DeepSeek-V2-Chat
tags: transformerssafetensorsdeepseek_v2text-generationconversationalcustom_codearxiv:2405.04434arxiv:2311.18743license:othereval-resultstext-generation-inferenceendpoints_compatibleregion:us

benchmark	category	score	context	conf	evidence
GSM8K	math	83.0	GSM8K	medium	`\| GSM8K \| Math \| 83.0 \| 80.3 \| 63.4 \| 79.2 \|`
BBH	reasoning	81.0	BBH	medium	`\| BBH \| English \| 81.0 \| 78.9 \| 68.7 \| 78.9 \|`
MMLU	knowledge	78.9	MMLU	medium	`\| MMLU \| English \| 78.9 \| 77.6 \| 71.3 \| 78.5 \|`
CMMLU	knowledge	69.3	CMMLU	medium	`\| CMMLU \| Chinese \| 69.3 \| 60.0 \| 70.8 \| 84.0 \|`
MBPP	coding	68.6	MBPP	medium	`\| MBPP \| Code \| 68.6 \| 64.2 \| 57.4 \| 66.6 \|`
C-Eval	knowledge	67.5	C-Eval	medium	`\| C-Eval \| Chinese \| 67.5 \| 58.6 \| 66.1 \| 81.7 \|`
HumanEval	coding	48.2	HumanEval	medium	`\| HumanEval \| Code \| 48.2 \| 53.1 \| 45.1 \| 48.8 \|`
MATH	math	42.2	Math	medium	`\| Math \| Math \| 42.2 \| 42.5 \| 18.7 \| 43.6 \|`
LiveCodeBench	coding	18.8	LiveCodeBench (0901-0401)	medium	`\| LiveCodeBench (0901-0401) \| Code \| 18.8 \| 25.0 \| 30.5 \| 18.3 \| 28.7 \| 32.5 \|`
AlpacaEval	chat	2.0		medium	`AlpacaEval 2.0`

none scraped.