Xwin-LM-7B-V0.2-GGUF

Home/Models/TheBloke/Xwin-LM-7B-V0.2-GGUF

TheBloke/Xwin-LM-7B-V0.2-GGUF

kind: gguf
quant: gguf (2-bit)
family: misc
modality: —
root model: Xwin-LM/Xwin-LM-7B-V0.2
provider: TheBloke
license: llama2
language: —
context: —
library: —
vRAM (GB): —
size on disk: —
downloads: 388
likes: 4
created: —
last modified: 2023-10-18T13:12:09+00:00 (2023)
huggingface: https://huggingface.co/TheBloke/Xwin-LM-7B-V0.2-GGUF
tags: transformersggufllamabase_model:Xwin-LM/Xwin-LM-7B-V0.2base_model:quantized:Xwin-LM/Xwin-LM-7B-V0.2license:llama2region:us

benchmark	category	score	conf	evidence
AlpacaEval	chat	95.57	low	`\| Xwin-LM-70B-V0.1 \| 95.57 \| 87.50 \| 60.61 \|`
TruthfulQA	safety	59.3	low	`\| Text-davinci-003 \| 56.9 \| 85.2 \| 59.3 \| 82.2 \| 70.9 \|`
MMLU	knowledge	56.9	low	`\| Text-davinci-003 \| 56.9 \| 85.2 \| 59.3 \| 82.2 \| 70.9 \|`
HellaSwag	knowledge	10.0	medium	`HellaSwag 10`

none scraped.