HF Model & Benchmark Matrix

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

meditron-70B-GPTQ

TheBloke/meditron-70B-GPTQ

kind
gptq
quant
gptq
family
misc
modality
text-generation
root model
epfl-llm/meditron-70b
provider
TheBloke
license
llama2
language
en
context
4K
library
—
vRAM (GB)
—
size on disk
—
downloads
548
likes
5
created
—
last modified
2023-11-30T21:24:40+00:00 (2023)
huggingface
https://huggingface.co/TheBloke/meditron-70B-GPTQ
tags
transformerssafetensorsllamatext-generationmedicalhealthllama2endataset:bigbio/med_qadataset:medmcqadataset:bigbio/pubmed_qadataset:epfl-llm/guidelinesarxiv:2311.16079base_model:epfl-llm/meditron-70bbase_model:quantized:epfl-llm/meditron-70blicense:llama2text-generation-inference4-bitgptqregion:us

Benchmark scores (3)

benchmarkcategoryscorecontextconfevidence
MMLUknowledge77.6MMLU-Medicalmedium| MMLU-Medical | 77.6 | 77.9 | 74.5 | 65.7 |
MedQAdomain70.2MedQA-4-Optionmedium| MedQA-4-Option | 70.2 | 63.8 | 63.9 | 56.8 |
MedQAdomain64.4MedQAmedium| MedQA | 64.4 | 61.5 | 59.1 | 50.8 |

Discussions (0)

none scraped.

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