OLMo-2-0425-1B-RLVR1

Home/Models/allenai/OLMo-2-0425-1B-RLVR1

allenai/OLMo-2-0425-1B-RLVR1

kind: original
quant: bf16 (16-bit)
family: olmo
modality: text-generation
root model: allenai/OLMo-2-0425-1B-DPO
provider: allenai
license: apache-2.0
language: en
context: —
library: transformers
vRAM (GB): —
size on disk: —
downloads: 320
likes: 2
created: —
last modified: 2025-04-30T22:33:02+00:00 (2025)
huggingface: https://huggingface.co/allenai/OLMo-2-0425-1B-RLVR1
tags: transformerssafetensorsolmo2text-generationconversationalendataset:allenai/RLVR-GSM-MATH-IF-Mixed-Constraintsarxiv:2501.00656arxiv:2411.15124base_model:allenai/OLMo-2-0425-1B-DPObase_model:finetune:allenai/OLMo-2-0425-1B-DPOlicense:apache-2.0endpoints_compatibleregion:us

benchmark	category	score	conf	evidence
MMLU	knowledge	36.6	low	`\| OLMo 1B 0724 \| 24.4 \| 2.4 \| 29.9 \| 27.9 \| 10.8 \| 25.3 \| 2.2 \| 36.6 \| 52.0 \| 12.1 \| 44.3 \|`
BBH	reasoning	29.9	low	`\| OLMo 1B 0724 \| 24.4 \| 2.4 \| 29.9 \| 27.9 \| 10.8 \| 25.3 \| 2.2 \| 36.6 \| 52.0 \| 12.1 \| 44.3 \|`
DROP	reasoning	27.9	low	`\| OLMo 1B 0724 \| 24.4 \| 2.4 \| 29.9 \| 27.9 \| 10.8 \| 25.3 \| 2.2 \| 36.6 \| 52.0 \| 12.1 \| 44.3 \|`
IFEval	instruction-following	25.3	low	`\| OLMo 1B 0724 \| 24.4 \| 2.4 \| 29.9 \| 27.9 \| 10.8 \| 25.3 \| 2.2 \| 36.6 \| 52.0 \| 12.1 \| 44.3 \|`
PopQA	knowledge	12.1	low	`\| OLMo 1B 0724 \| 24.4 \| 2.4 \| 29.9 \| 27.9 \| 10.8 \| 25.3 \| 2.2 \| 36.6 \| 52.0 \| 12.1 \| 44.3 \|`
GSM8K	math	10.8	low	`\| OLMo 1B 0724 \| 24.4 \| 2.4 \| 29.9 \| 27.9 \| 10.8 \| 25.3 \| 2.2 \| 36.6 \| 52.0 \| 12.1 \| 44.3 \|`
AlpacaEval	chat	2.4	low	`\| OLMo 1B 0724 \| 24.4 \| 2.4 \| 29.9 \| 27.9 \| 10.8 \| 25.3 \| 2.2 \| 36.6 \| 52.0 \| 12.1 \| 44.3 \|`
MATH	math	2.2	low	`\| OLMo 1B 0724 \| 24.4 \| 2.4 \| 29.9 \| 27.9 \| 10.8 \| 25.3 \| 2.2 \| 36.6 \| 52.0 \| 12.1 \| 44.3 \|`

none scraped.