tulu-30B-GPTQ

Home/Models/TheBloke/tulu-30B-GPTQ

TheBloke/tulu-30B-GPTQ

kind: gptq
quant: gptq
family: misc
modality: text-generation
root model: allenai/tulu-30b
provider: TheBloke
license: other
language: en
context: —
library: —
vRAM (GB): —
size on disk: —
downloads: 70
likes: 10
created: —
last modified: 2023-09-27T12:44:34+00:00 (2023)
huggingface: https://huggingface.co/TheBloke/tulu-30B-GPTQ
tags: transformerssafetensorsllamatext-generationendataset:databricks/databricks-dolly-15kdataset:OpenAssistant/oasst1dataset:sahil2801/CodeAlpaca-20karxiv:2306.04751arxiv:2302.13971arxiv:2301.13688arxiv:2304.07327arxiv:2304.03277base_model:allenai/tulu-30bbase_model:quantized:allenai/tulu-30blicense:othertext-generation-inference4-bitgptqregion:us

benchmark	category	score	context	conf	evidence
TydiQA	knowledge	58.2	GSM CoT \| BBH CoT \| TydiQA Closed-book	low	`\| 57.7 \| 58.4 \| 6.0 \| 51.0 \| 45.8 \| 48.7 \| 58.2 \| 12.3 \| 25.4 \| 46.0 \| 63.5 \| 44.7 \|`
MMLU	knowledge	57.7	GSM CoT \| BBH CoT \| TydiQA Closed-book	low	`\| 57.7 \| 58.4 \| 6.0 \| 51.0 \| 45.8 \| 48.7 \| 58.2 \| 12.3 \| 25.4 \| 46.0 \| 63.5 \| 44.7 \|`
BBH	reasoning	45.8	GSM CoT \| BBH CoT \| TydiQA Closed-book	low	`\| 57.7 \| 58.4 \| 6.0 \| 51.0 \| 45.8 \| 48.7 \| 58.2 \| 12.3 \| 25.4 \| 46.0 \| 63.5 \| 44.7 \|`
Codex-Eval	coding	25.4	GSM CoT \| BBH CoT \| TydiQA Closed-book	low	`\| 57.7 \| 58.4 \| 6.0 \| 51.0 \| 45.8 \| 48.7 \| 58.2 \| 12.3 \| 25.4 \| 46.0 \| 63.5 \| 44.7 \|`

none scraped.