HF Model & Benchmark Matrix

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

internlm2_5-7b

internlm/internlm2_5-7b

kind
original
quant
bf16 (16-bit)
family
internlm
modality
text-generation
root model
internlm/internlm2_5-7b
provider
internlm
license
—
language
—
context
—
library
—
vRAM (GB)
—
size on disk
—
downloads
3,696
likes
18
created
—
last modified
2025-03-13T07:04:49+00:00 (2025)
huggingface
https://huggingface.co/internlm/internlm2_5-7b
tags
transformerssafetensorsinternlm2text-generationconversationalcustom_codearxiv:2403.17297region:us

Benchmark scores (6)

benchmarkcategoryscorecontextconfevidence
CMMLUknowledge79.1CMMLUmedium| CMMLU | 79.1 | 66.2 | 51.0 | 74.1 |
GSM8Kmath74.8GSM8Kmedium| GSM8K | 74.8 | 70.8 | 54.3 | 74.5 |
MMLUknowledge71.6MMLUmedium| MMLU | 71.6 | 65.8 | 66.4 | 71.6 |
BBHreasoning70.1BBHmedium| BBH | 70.1 | 65.0 | 59.7 | 71.1 |
MATHmath34.0MATHmedium| MATH | 34.0 | 20.2 | 16.4 | 31.9 |
GPQAreasoning31.3GPQAmedium| GPQA | 31.3 | 28.3 | 31.3 | 27.8 |

Discussions (0)

none scraped.

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