SynthIA-7B-v1.3-dare-0.85-GGUF

Home/Models/TheBloke/SynthIA-7B-v1.3-dare-0.85-GGUF

TheBloke/SynthIA-7B-v1.3-dare-0.85-GGUF

kind: gguf
quant: gguf (2-bit)
family: misc
modality: —
root model: uukuguy/SynthIA-7B-v1.3-dare-0.85
provider: TheBloke
license: llama2
language: —
context: —
library: —
vRAM (GB): —
size on disk: —
downloads: 163
likes: 3
created: —
last modified: 2023-11-23T02:18:07+00:00 (2023)
huggingface: https://huggingface.co/TheBloke/SynthIA-7B-v1.3-dare-0.85-GGUF
tags: transformersggufmistralbase_model:uukuguy/SynthIA-7B-v1.3-dare-0.85base_model:quantized:uukuguy/SynthIA-7B-v1.3-dare-0.85license:llama2region:us

benchmark	category	score	conf	evidence
HellaSwag	knowledge	83.64	low	`\| Intel/neural-chat-7b-v3-1 \| 59.06 \| 66.21 \| 83.64 \| 62.37 \| 59.65 \| 78.14 \| 19.56 \| 43.84 \|`
WinoGrande	knowledge	78.14	low	`\| Intel/neural-chat-7b-v3-1 \| 59.06 \| 66.21 \| 83.64 \| 62.37 \| 59.65 \| 78.14 \| 19.56 \| 43.84 \|`
MMLU	knowledge	62.37	low	`\| Intel/neural-chat-7b-v3-1 \| 59.06 \| 66.21 \| 83.64 \| 62.37 \| 59.65 \| 78.14 \| 19.56 \| 43.84 \|`
TruthfulQA	safety	59.65	low	`\| Intel/neural-chat-7b-v3-1 \| 59.06 \| 66.21 \| 83.64 \| 62.37 \| 59.65 \| 78.14 \| 19.56 \| 43.84 \|`
DROP	reasoning	43.84	low	`\| Intel/neural-chat-7b-v3-1 \| 59.06 \| 66.21 \| 83.64 \| 62.37 \| 59.65 \| 78.14 \| 19.56 \| 43.84 \|`
GSM8K	math	19.56	low	`\| Intel/neural-chat-7b-v3-1 \| 59.06 \| 66.21 \| 83.64 \| 62.37 \| 59.65 \| 78.14 \| 19.56 \| 43.84 \|`

none scraped.