HF Model & Benchmark Matrix

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

tulu-2-dpo-70b

allenai/tulu-2-dpo-70b

kind
original
quant
bf16 (16-bit)
family
misc
modality
text-generation
root model
meta-llama/Llama-2-70b-hf
provider
allenai
license
other
language
en
context
—
library
—
vRAM (GB)
—
size on disk
—
downloads
248
likes
157
created
—
last modified
2024-01-31T18:54:37+00:00 (2024)
huggingface
https://huggingface.co/allenai/tulu-2-dpo-70b
tags
transformerspytorchsafetensorsllamatext-generationconversationalendataset:HuggingFaceH4/ultrafeedback_binarizeddataset:allenai/tulu-v2-sft-mixturearxiv:2305.18290arxiv:2311.10702base_model:meta-llama/Llama-2-70b-hfbase_model:finetune:meta-llama/Llama-2-70b-hflicense:othertext-generation-inferenceendpoints_compatibleregion:usdeploy:azure

Benchmark scores (2)

benchmarkcategoryscorecontextconfevidence
AlpacaEvalchat73.9low| **Tulu-v2-7b** 🐪 | **7B** | **SFT** | **6.30** | **73.9** |
MT-Benchchat6.3low| **Tulu-v2-7b** 🐪 | **7B** | **SFT** | **6.30** | **73.9** |

Discussions (0)

none scraped.

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