HF Model & Benchmark Matrix

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

internlm2_5-20b-chat

internlm/internlm2_5-20b-chat

kind
original
quant
bf16 (16-bit)
family
internlm
modality
text-generation
root model
internlm/internlm2_5-20b-chat
provider
internlm
license
other
language
—
context
—
library
—
vRAM (GB)
—
size on disk
—
downloads
8,231
likes
96
created
—
last modified
2025-03-13T07:04:47+00:00 (2025)
huggingface
https://huggingface.co/internlm/internlm2_5-20b-chat
tags
transformerssafetensorsinternlm2feature-extractiontext-generationconversationalcustom_codearxiv:2403.17297license:otherregion:us

Benchmark scores (5)

benchmarkcategoryscorecontextconfevidence
CMMLUknowledge79.7CMMLU (5-shot)medium| CMMLU (5-shot) | **79.7** | 63.3 |
BBHreasoning76.3BBH (3-shot CoT)medium| BBH (3-shot CoT) | **76.3** | 71.5 |
MMLUknowledge73.5MMLU (5-shot)medium| MMLU (5-shot) | 73.5 | 75.0 |
MATHmath64.7MATH (0-shot CoT)medium| MATH (0-shot CoT) | **64.7** | 50.1 |
GPQAreasoning33.3GPQA (0-shot)medium| GPQA (0-shot) | **33.3** | 29.3 |

Discussions (0)

none scraped.

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