HF Model & Benchmark Matrix

24,078 variants · 14,984 scores · 120 benchmarks

DeepSeek-V2-Lite-Chat

deepseek-ai/DeepSeek-V2-Lite-Chat

kind
original
quant
bf16 (16-bit)
family
deepseek
modality
text-generation
root model
deepseek-ai/DeepSeek-V2-Lite-Chat
provider
deepseek-ai
license
other
language
—
context
—
library
—
vRAM (GB)
—
size on disk
—
downloads
1,211,911
likes
144
created
—
last modified
2024-06-25T08:36:27+00:00 (2024)
huggingface
https://huggingface.co/deepseek-ai/DeepSeek-V2-Lite-Chat
tags
transformerssafetensorsdeepseek_v2text-generationconversationalcustom_codearxiv:2405.04434license:othertext-generation-inferenceendpoints_compatibleregion:us

Benchmark scores (8)

benchmarkcategoryscorecontextconfevidence
MMLUknowledge48.2**MMLU**medium| **MMLU** | English | 48.2 | 45.0 | 58.3 |
CMMLUknowledge47.2**CMMLU**medium| **CMMLU** | Chinese | 47.2 | 42.5 | 64.3 |
C-Evalknowledge45.0**C-Eval**medium| **C-Eval** | Chinese | 45.0 | 40.6 | 60.3 |
BBHreasoning39.5**BBH**medium| **BBH** | English | 39.5 | 38.9 | 44.1 |
MBPPcoding39.0**MBPP**medium| **MBPP** | Code | 39.0 | 39.2 | 43.2 |
HumanEvalcoding26.2**HumanEval**medium| **HumanEval** | Code | 26.2 | 26.8 | 29.9 |
GSM8Kmath17.4**GSM8K**medium| **GSM8K** | Math | 17.4 | 18.8 | 41.1 |
MATHmath3.3**Math**medium| **Math** | Math | 3.3 | 4.3 | 17.1 |

Discussions (0)

none scraped.

Hugging Face model & benchmark data scraped & matrix-ified. 24,078 variants · 14,984 scores · 120 benchmarks.