HF Model & Benchmark Matrix

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

internlm2_5-20b

internlm/internlm2_5-20b

kind
original
quant
bf16 (16-bit)
family
internlm
modality
text-generation
root model
internlm/internlm2_5-20b
provider
internlm
license
apache-2.0
language
—
context
—
library
—
vRAM (GB)
—
size on disk
—
downloads
148
likes
17
created
—
last modified
2025-03-13T07:04:49+00:00 (2025)
huggingface
https://huggingface.co/internlm/internlm2_5-20b
tags
transformerssafetensorsinternlm2text-generationconversationalcustom_codearxiv:2403.17297license:apache-2.0region:us

Benchmark scores (6)

benchmarkcategoryscorecontextconfevidence
CMMLUknowledge82.22CMMLUmedium| CMMLU | 82.22 | 68.29 |
BBHreasoning77.82BBHmedium| BBH | 77.82 | 71.36 |
MMLUknowledge74.25MMLUmedium| MMLU | 74.25 | 67.58 |
HumanEvalcoding71.95HUMANEVALmedium| HUMANEVAL | 71.95 | 51.22 |
MATHmath48.0MATHmedium| MATH | 48 | 32.66 |
GPQAreasoning37.88GPQAmedium| GPQA | 37.88 | 31.31 |

Discussions (0)

none scraped.

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