open-llama-3b-v2-wizard-evol-instuct-v2-196k-GGUF

Home/Models/TheBloke/open-llama-3b-v2-wizard-evol-instuct-v2-196k-GGUF

TheBloke/open-llama-3b-v2-wizard-evol-instuct-v2-196k-GGUF

kind: gguf
quant: gguf (2-bit)
family: llama
modality: —
root model: harborwater/open-llama-3b-v2-wizard-evol-instuct-v2-196k
provider: TheBloke
license: apache-2.0
language: en
context: 2048,
library: transformers
vRAM (GB): —
size on disk: —
downloads: 1,078
likes: 12
created: —
last modified: 2023-11-30T00:07:02+00:00 (2023)
huggingface: https://huggingface.co/TheBloke/open-llama-3b-v2-wizard-evol-instuct-v2-196k-GGUF
tags: transformersggufllamaendataset:WizardLM/WizardLM_evol_instruct_V2_196kbase_model:harborwater/open-llama-3b-v2-wizard-evol-instuct-v2-196kbase_model:quantized:harborwater/open-llama-3b-v2-wizard-evol-instuct-v2-196klicense:apache-2.0region:us

benchmark	category	score	context	conf	evidence
HellaSwag	knowledge	73.01	HellaSwag (10-shot)	medium	`\| HellaSwag (10-shot) \| 73.01 \|`
WinoGrande	knowledge	66.69	Winogrande (5-shot)	medium	`\| Winogrande (5-shot) \| 66.69 \|`
TruthfulQA	safety	38.99	TruthfulQA (0-shot)	medium	`\| TruthfulQA (0-shot) \| 38.99 \|`
MMLU	knowledge	26.36	MMLU (5-shot)	medium	`\| MMLU (5-shot) \| 26.36 \|`
DROP	reasoning	5.57	DROP (3-shot)	medium	`\| DROP (3-shot) \| 5.57 \|`
GSM8K	math	1.9	GSM8K (5-shot)	medium	`\| GSM8K (5-shot) \| 1.9 \|`

none scraped.