openchat_v3.2_super-GGUF

Home/Models/TheBloke/openchat_v3.2_super-GGUF

TheBloke/openchat_v3.2_super-GGUF

kind: gguf
quant: gguf (2-bit)
family: misc
modality: —
root model: openchat/openchat_v3.2_super
provider: TheBloke
license: llama2
language: —
context: —
library: —
vRAM (GB): —
size on disk: —
downloads: 420
likes: 10
created: —
last modified: 2023-09-27T12:47:15+00:00 (2023)
huggingface: https://huggingface.co/TheBloke/openchat_v3.2_super-GGUF
tags: transformersggufllamabase_model:openchat/openchat_v3.2_superbase_model:quantized:openchat/openchat_v3.2_superlicense:llama2region:us

benchmark	category	score	context	conf	evidence
AlpacaEval	chat	95.3		low	`\| GPT-4 \| 1.8T* \| 8K \| \| ❌ \| 95.3 \| 82.5 \| 8.99 \|`
MT-Bench	chat	82.5		low	`\| GPT-4 \| 1.8T* \| 8K \| \| ❌ \| 95.3 \| 82.5 \| 8.99 \|`

none scraped.