HF Model & Benchmark Matrix

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

Llama-3.1-Tulu-3-8B-SFT-RM-RB2

allenai/Llama-3.1-Tulu-3-8B-SFT-RM-RB2

kind
original
quant
bf16 (16-bit)
family
llama
modality
text-classification
root model
allenai/Llama-3.1-Tulu-3-8B-SFT
provider
allenai
license
llama3.1
language
en
context
—
library
transformers
vRAM (GB)
—
size on disk
—
downloads
51
likes
0
created
—
last modified
2025-06-04T08:54:30+00:00 (2025)
huggingface
https://huggingface.co/allenai/Llama-3.1-Tulu-3-8B-SFT-RM-RB2
tags
transformerspytorchllamatext-classificationendataset:allenai/llama-3.1-tulu-3-8b-preference-mixturedataset:Skywork/Skywork-Reward-Preference-80K-v0.2arxiv:2506.01937base_model:allenai/Llama-3.1-Tulu-3-8B-SFTbase_model:finetune:allenai/Llama-3.1-Tulu-3-8B-SFTlicense:llama3.1text-embeddings-inferenceendpoints_compatibleregion:us

Benchmark scores (1)

benchmarkcategoryscorecontextconfevidence
MATHmath62.8high| 1 | Combined | 3e-6 | 1 | 67.9 | 75.6 | 40.6 | 62.8 | 83.1 | 80.6 | 64.8 |

Discussions (0)

none scraped.

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