Nous-Hermes-Llama2-70B-GGUF

Home/Models/TheBloke/Nous-Hermes-Llama2-70B-GGUF

Nous-Hermes-Llama2-70B-GGUF

TheBloke/Nous-Hermes-Llama2-70B-GGUF

kind: gguf
quant: gguf (2-bit)
family: llama
modality: —
root model: NousResearch/Nous-Hermes-Llama2-70b
provider: TheBloke
license: - mit
language: en
context: —
library: —
vRAM (GB): —
size on disk: —
downloads: 795
likes: 27
created: —
last modified: 2023-09-27T12:45:59+00:00 (2023)
huggingface: https://huggingface.co/TheBloke/Nous-Hermes-Llama2-70B-GGUF
tags: transformersggufllamallama-2self-instructdistillationsynthetic instructionenbase_model:NousResearch/Nous-Hermes-Llama2-70bbase_model:quantized:NousResearch/Nous-Hermes-Llama2-70blicense:mitregion:us

Benchmark scores (32)

benchmark	category	score	context	conf	evidence
AGIEval	reasoning	86.41	_sat_en	medium	`\| agieval_sat_en \| 0 \| acc \| 0.8641 \| ± \| 0.0239 \|`
BoolQ	knowledge	84.22		medium	`\| boolq \| 1 \| acc \| 0.8422 \| ± \| 0.0064 \|`
PIQA	knowledge	83.13		medium	`\| piqa \| 0 \| acc \| 0.8313 \| ± \| 0.0087 \|`
WinoGrande	knowledge	77.51		medium	`\| winogrande \| 0 \| acc \| 0.7751 \| ± \| 0.0117 \|`
BigBench	reasoning	73.94	_sports_understanding	medium	`\| bigbench_sports_understanding \| 0 \| multiple_choice_grade \| 0.7394 \| ± \| 0.0140 \|`
BigBench	reasoning	73.44	_date_understanding	medium	`\| bigbench_date_understanding \| 0 \| multiple_choice_grade \| 0.7344 \| ± \| 0.0230 \|`
AGIEval	reasoning	69.14	_lsat_rc	medium	`\| agieval_lsat_rc \| 0 \| acc \| 0.6914 \| ± \| 0.0282 \|`
BigBench	reasoning	66.3	_snarks	medium	`\| bigbench_snarks \| 0 \| multiple_choice_grade \| 0.6630 \| ± \| 0.0352 \|`
BigBench	reasoning	66.05	_reasoning_about_colored_objects	medium	`\| bigbench_reasoning_about_colored_objects \| 0 \| multiple_choice_grade \| 0.6605 \| ± \| 0.0106 \|`
BigBench	reasoning	65.79	_causal_judgement	medium	`\| bigbench_causal_judgement \| 0 \| multiple_choice_grade \| 0.6579 \| ± \| 0.0345 \|`
HellaSwag	knowledge	65.19		medium	`\| hellaswag \| 0 \| acc \| 0.6519 \| ± \| 0.0048 \|`
AGIEval	reasoning	57.65	_lsat_lr	medium	`\| agieval_lsat_lr \| 0 \| acc \| 0.5765 \| ± \| 0.0219 \|`
ARC-Challenge	knowledge	57.34	_challenge	medium	`\| arc_challenge \| 0 \| acc \| 0.5734 \| ± \| 0.0145 \|`
AGIEval	reasoning	52.91	_sat_en_without_passage	medium	`\| agieval_sat_en_without_passage \| 0 \| acc \| 0.5291 \| ± \| 0.0349 \|`
BigBench	reasoning	50.0	_navigate	medium	`\| bigbench_navigate \| 0 \| multiple_choice_grade \| 0.5000 \| ± \| 0.0158 \|`
BigBench	reasoning	45.98	_ruin_names	medium	`\| bigbench_ruin_names \| 0 \| multiple_choice_grade \| 0.4598 \| ± \| 0.0236 \|`
BigBench	reasoning	44.67	_logical_deduction_three_objects	medium	`\| bigbench_logical_deduction_three_objects \| 0 \| multiple_choice_grade \| 0.4467 \| ± \| 0.0288 \|`
BigBench	reasoning	44.67	_tracking_shuffled_objects_three_objects	medium	`\| bigbench_tracking_shuffled_objects_three_objects \| 0 \| multiple_choice_grade \| 0.4467 \| ± \| 0.0288 \|`
BigBench	reasoning	44.4	_temporal_sequences	medium	`\| bigbench_temporal_sequences \| 0 \| multiple_choice_grade \| 0.4440 \| ± \| 0.0157 \|`
AGIEval	reasoning	41.36	_sat_math	medium	`\| agieval_sat_math \| 0 \| acc \| 0.4136 \| ± \| 0.0333 \|`
AGIEval	reasoning	39.17	_logiqa_en	medium	`\| agieval_logiqa_en \| 0 \| acc \| 0.3917 \| ± \| 0.0191 \|`
OpenBookQA	knowledge	38.8		medium	`\| openbookqa \| 0 \| acc \| 0.3880 \| ± \| 0.0218 \|`
BigBench	reasoning	32.4	_movie_recommendation	medium	`\| bigbench_movie_recommendation \| 0 \| multiple_choice_grade \| 0.3240 \| ± \| 0.0210 \|`
BigBench	reasoning	30.23	_disambiguation_qa	medium	`\| bigbench_disambiguation_qa \| 0 \| multiple_choice_grade \| 0.3023 \| ± \| 0.0286 \|`
BigBench	reasoning	27.6	_logical_deduction_five_objects	medium	`\| bigbench_logical_deduction_five_objects \| 0 \| multiple_choice_grade \| 0.2760 \| ± \| 0.0200 \|`
BigBench	reasoning	25.85	_salient_translation_error_detection	medium	`\| bigbench_salient_translation_error_detection \| 0 \| multiple_choice_grade \| 0.2585 \| ± \| 0.0139 \|`
AGIEval	reasoning	24.8	_aqua_rat	medium	`\| agieval_aqua_rat \| 0 \| acc \| 0.2480 \| ± \| 0.0272 \|`
BigBench	reasoning	23.4	_geometric_shapes	medium	`\| bigbench_geometric_shapes \| 0 \| multiple_choice_grade \| 0.2340 \| ± \| 0.0224 \|`
AGIEval	reasoning	22.17	_lsat_ar	medium	`\| agieval_lsat_ar \| 0 \| acc \| 0.2217 \| ± \| 0.0275 \|`
BigBench	reasoning	21.68	_tracking_shuffled_objects_five_objects	medium	`\| bigbench_tracking_shuffled_objects_five_objects \| 0 \| multiple_choice_grade \| 0.2168 \| ± \| 0.0117 \|`
BigBench	reasoning	18.71	_logical_deduction_seven_objects	medium	`\| bigbench_logical_deduction_seven_objects \| 0 \| multiple_choice_grade \| 0.1871 \| ± \| 0.0148 \|`
BigBench	reasoning	15.31	_tracking_shuffled_objects_seven_objects	medium	`\| bigbench_tracking_shuffled_objects_seven_objects \| 0 \| multiple_choice_grade \| 0.1531 \| ± \| 0.0086 \|`

Discussions (0)

none scraped.