upstage-llama-30b-instruct-2048-GPTQ

Home/Models/TheBloke/upstage-llama-30b-instruct-2048-GPTQ

TheBloke/upstage-llama-30b-instruct-2048-GPTQ

kind: gptq
quant: gptq
family: llama
modality: text-generation
root model: upstage/llama-30b-instruct-2048
provider: TheBloke
license: other
language: en
context: —
library: —
vRAM (GB): —
size on disk: —
downloads: 61
likes: 22
created: —
last modified: 2023-09-27T12:44:52+00:00 (2023)
huggingface: https://huggingface.co/TheBloke/upstage-llama-30b-instruct-2048-GPTQ
tags: transformerssafetensorsllamatext-generationupstageinstructinstructionendataset:sciqdataset:metaeval/ScienceQA_text_onlydataset:GAIR/limadataset:Open-Orca/OpenOrcadataset:openbookqabase_model:upstage/llama-30b-instruct-2048base_model:quantized:upstage/llama-30b-instruct-2048license:othertext-generation-inference4-bitgptqregion:us

benchmark	category	score	conf	evidence
HellaSwag	knowledge	87.9	low	`\| [Llama-2-70b-instruct-v2](https://huggingface.co/upstage/Llama-2-70b-instruct-v2)(Ours, Open LLM Leaderboard) \| 73 \| 71.1 \| 87.9 \| 70.6 \| 62.2 \| \| **7.44`
MMLU	knowledge	70.6	low	`\| [Llama-2-70b-instruct-v2](https://huggingface.co/upstage/Llama-2-70b-instruct-v2)(Ours, Open LLM Leaderboard) \| 73 \| 71.1 \| 87.9 \| 70.6 \| 62.2 \| \| **7.44`
TruthfulQA	safety	62.2	low	`\| [Llama-2-70b-instruct-v2](https://huggingface.co/upstage/Llama-2-70b-instruct-v2)(Ours, Open LLM Leaderboard) \| 73 \| 71.1 \| 87.9 \| 70.6 \| 62.2 \| \| **7.44`

none scraped.