Nous-Hermes-2-Yi-34B-GGUF

Home/Models/TheBloke/Nous-Hermes-2-Yi-34B-GGUF

Nous-Hermes-2-Yi-34B-GGUF

TheBloke/Nous-Hermes-2-Yi-34B-GGUF

kind: gguf
quant: gguf (2-bit)
family: yi
modality: —
root model: NousResearch/Nous-Hermes-2-Yi-34B
provider: TheBloke
license: apache-2.0
language: en
context: 4096,
library: —
vRAM (GB): —
size on disk: —
downloads: 1,356
likes: 40
created: —
last modified: 2023-12-26T08:16:32+00:00 (2023)
huggingface: https://huggingface.co/TheBloke/Nous-Hermes-2-Yi-34B-GGUF
tags: transformersggufyiinstructfinetunechatmlgpt4synthetic datadistillationenbase_model:NousResearch/Nous-Hermes-2-Yi-34Bbase_model:quantized:NousResearch/Nous-Hermes-2-Yi-34Blicense:apache-2.0region:usconversational

Benchmark scores (34)

benchmark	category	score	context	conf	evidence
BoolQ	knowledge	88.59		medium	`\| boolq \| 1 \| acc \| 0.8859 \| _ \| 0.0056 \|`
AGIEval	reasoning	86.89	_sat_en	medium	`\| agieval_sat_en \| 0 \| acc \| 0.8689 \| _ \| 0.0236 \|`
PIQA	knowledge	82.15		medium	`\| piqa \| 0 \| acc \| 0.8215 \| _ \| 0.0089 \|`
BigBench	reasoning	80.66	_snarks	medium	`\| bigbench_snarks \| 0 \| multiple_choice_grade \| 0.8066 \| _ \| 0.0294 \|`
WinoGrande	knowledge	79.08		medium	`\| winogrande \| 0 \| acc \| 0.7908 \| _ \| 0.0114 \|`
AGIEval	reasoning	78.07	_lsat_rc	medium	`\| agieval_lsat_rc \| 0 \| acc \| 0.7807 \| _ \| 0.0253 \|`
BigBench	reasoning	74.95	_reasoning_about_colored_objects	medium	`\| bigbench_reasoning_about_colored_objects \| 0 \| multiple_choice_grade \| 0.7495 \| _ \| 0.0097 \|`
BigBench	reasoning	72.63	_date_understanding	medium	`\| bigbench_date_understanding \| 0 \| multiple_choice_grade \| 0.7263 \| _ \| 0.0232 \|`
AGIEval	reasoning	70.78	_lsat_lr	medium	`\| agieval_lsat_lr \| 0 \| acc \| 0.7078 \| _ \| 0.0202 \|`
HellaSwag	knowledge	64.07		medium	`\| hellaswag \| 0 \| acc \| 0.6407 \| _ \| 0.0048 \|`
ARC-Challenge	knowledge	60.67	_challenge	medium	`\| arc_challenge \| 0 \| acc \| 0.6067 \| _ \| 0.0143 \|`
BigBench	reasoning	59.38	_ruin_names	medium	`\| bigbench_ruin_names \| 0 \| multiple_choice_grade \| 0.5938 \| _ \| 0.0232 \|`
BigBench	reasoning	57.37	_causal_judgement	medium	`\| bigbench_causal_judgement \| 0 \| multiple_choice_grade \| 0.5737 \| _ \| 0.0360 \|`
AGIEval	reasoning	54.38	_logiqa_en	medium	`\| agieval_logiqa_en \| 0 \| acc \| 0.5438 \| _ \| 0.0195 \|`
BigBench	reasoning	52.0	_movie_recommendation	medium	`\| bigbench_movie_recommendation \| 0 \| multiple_choice_grade \| 0.5200 \| _ \| 0.0224 \|`
AGIEval	reasoning	51.94	_sat_en_without_passage	medium	`\| agieval_sat_en_without_passage \| 0 \| acc \| 0.5194 \| _ \| 0.0349 \|`
BigBench	reasoning	51.01	_sports_understanding	medium	`\| bigbench_sports_understanding \| 0 \| multiple_choice_grade \| 0.5101 \| _ \| 0.0159 \|`
BigBench	reasoning	49.1	_navigate	medium	`\| bigbench_navigate \| 0 \| multiple_choice_grade \| 0.4910 \| _ \| 0.0158 \|`
BigBench	reasoning	47.33	_logical_deduction_three_objects	medium	`\| bigbench_logical_deduction_three_objects \| 0 \| multiple_choice_grade \| 0.4733 \| _ \| 0.0289 \|`
BigBench	reasoning	47.33	_tracking_shuffled_objects_three_objects	medium	`\| bigbench_tracking_shuffled_objects_three_objects \| 0 \| multiple_choice_grade \| 0.4733 \| _ \| 0.0289 \|`
BigBench	reasoning	44.57	_geometric_shapes	medium	`\| bigbench_geometric_shapes \| 0 \| multiple_choice_grade \| 0.4457 \| _ \| 0.0263 \|`
AGIEval	reasoning	44.09	_sat_math	medium	`\| agieval_sat_math \| 0 \| acc \| 0.4409 \| _ \| 0.0336 \|`
TruthfulQA	safety	43.33	_mc	medium	`\| truthfulqa_mc \| 1 \| mc1 \| 0.4333 \| _ \| 0.0173 \|`
AGIEval	reasoning	43.07	AGI Eval	medium	`\| AGI Eval \| 43.07 \| 50.27 \| +7.20 \|`
BigBench	reasoning	39.53	_disambiguation_qa	medium	`\| bigbench_disambiguation_qa \| 0 \| multiple_choice_grade \| 0.3953 \| _ \| 0.0305 \|`
BigBench	reasoning	38.5	_temporal_sequences	medium	`\| bigbench_temporal_sequences \| 0 \| multiple_choice_grade \| 0.3850 \| _ \| 0.0154 \|`
BigBench	reasoning	38.08	_salient_translation_error_detection	medium	`\| bigbench_salient_translation_error_detection \| 0 \| multiple_choice_grade \| 0.3808 \| _ \| 0.0154 \|`
OpenBookQA	knowledge	35.2		medium	`\| openbookqa \| 0 \| acc \| 0.3520 \| _ \| 0.0214 \|`
AGIEval	reasoning	31.89	_aqua_rat	medium	`\| agieval_aqua_rat \| 0 \| acc \| 0.3189 \| _ \| 0.0293 \|`
BigBench	reasoning	28.2	_logical_deduction_five_objects	medium	`\| bigbench_logical_deduction_five_objects \| 0 \| multiple_choice_grade \| 0.2820 \| _ \| 0.0201 \|`
AGIEval	reasoning	26.96	_lsat_ar	medium	`\| agieval_lsat_ar \| 0 \| acc \| 0.2696 \| _ \| 0.0293 \|`
BigBench	reasoning	21.86	_logical_deduction_seven_objects	medium	`\| bigbench_logical_deduction_seven_objects \| 0 \| multiple_choice_grade \| 0.2186 \| _ \| 0.0156 \|`
BigBench	reasoning	21.6	_tracking_shuffled_objects_five_objects	medium	`\| bigbench_tracking_shuffled_objects_five_objects \| 0 \| multiple_choice_grade \| 0.2160 \| _ \| 0.0116 \|`
BigBench	reasoning	16.34	_tracking_shuffled_objects_seven_objects	medium	`\| bigbench_tracking_shuffled_objects_seven_objects \| 0 \| multiple_choice_grade \| 0.1634 \| _ \| 0.0088 \|`

Discussions (0)

none scraped.