falcon-mamba-7b-instruct

Home/Models/tiiuae/falcon-mamba-7b-instruct

tiiuae/falcon-mamba-7b-instruct

kind: original
quant: bf16 (16-bit)
family: falcon
modality: text-generation
root model: tiiuae/falcon-mamba-7b
provider: tiiuae
license: other
language: en
context: 2,048
library: —
vRAM (GB): —
size on disk: —
downloads: 17,209
likes: 73
created: —
last modified: 2024-12-17T11:11:40+00:00 (2024)
huggingface: https://huggingface.co/tiiuae/falcon-mamba-7b-instruct
tags: transformerssafetensorsfalcon_mambatext-generationconversationalendataset:tiiuae/falcon-refinedwebdataset:HuggingFaceFW/fineweb-eduarxiv:2312.00752arxiv:2410.05355base_model:tiiuae/falcon-mamba-7bbase_model:finetune:tiiuae/falcon-mamba-7blicense:otherendpoints_compatibleregion:us

benchmark	category	score	conf	evidence
HellaSwag	knowledge	80.82	low	\| `FalconMamba-7B`<sup></sup> \| 62.03 \| 80.82 \| 62.11 \| 73.64 \| 53.42 \| 52.54 \| 64.09* \|
WinoGrande	knowledge	73.64	low	\| `FalconMamba-7B`<sup></sup> \| 62.03 \| 80.82 \| 62.11 \| 73.64 \| 53.42 \| 52.54 \| 64.09* \|
MMLU	knowledge	62.11	low	\| `FalconMamba-7B`<sup></sup> \| 62.03 \| 80.82 \| 62.11 \| 73.64 \| 53.42 \| 52.54 \| 64.09* \|
TruthfulQA	safety	53.42	low	\| `FalconMamba-7B`<sup></sup> \| 62.03 \| 80.82 \| 62.11 \| 73.64 \| 53.42 \| 52.54 \| 64.09* \|
GSM8K	math	52.54	low	\| `FalconMamba-7B`<sup></sup> \| 62.03 \| 80.82 \| 62.11 \| 73.64 \| 53.42 \| 52.54 \| 64.09* \|
IFEval	instruction-following	33.36	low	\| `FalconMamba-7B` \| 33.36 \| 19.88 \| 3.63 \| 8.05 \| 10.86 \| 14.47 \| 15.04 \|
BBH	reasoning	19.88	low	\| `FalconMamba-7B` \| 33.36 \| 19.88 \| 3.63 \| 8.05 \| 10.86 \| 14.47 \| 15.04 \|
MMLU-Pro	knowledge	14.47	low	\| `FalconMamba-7B` \| 33.36 \| 19.88 \| 3.63 \| 8.05 \| 10.86 \| 14.47 \| 15.04 \|
MUSR	reasoning	10.86	low	\| `FalconMamba-7B` \| 33.36 \| 19.88 \| 3.63 \| 8.05 \| 10.86 \| 14.47 \| 15.04 \|
GPQA	reasoning	8.05	low	\| `FalconMamba-7B` \| 33.36 \| 19.88 \| 3.63 \| 8.05 \| 10.86 \| 14.47 \| 15.04 \|
MATH	math	3.63	low	\| `FalconMamba-7B` \| 33.36 \| 19.88 \| 3.63 \| 8.05 \| 10.86 \| 14.47 \| 15.04 \|

none scraped.