Swallow-7B-Instruct-GGUF

Home/Models/TheBloke/Swallow-7B-Instruct-GGUF

TheBloke/Swallow-7B-Instruct-GGUF

kind: gguf
quant: gguf (2-bit)
family: misc
modality: text-generation
root model: tokyotech-llm/Swallow-7b-instruct-hf
provider: TheBloke
license: llama2
language: en, ja
context: 4096,
library: transformers
vRAM (GB): —
size on disk: —
downloads: 637
likes: 9
created: —
last modified: 2023-12-19T23:33:54+00:00 (2023)
huggingface: https://huggingface.co/TheBloke/Swallow-7B-Instruct-GGUF
tags: transformersggufllamatext-generationenjabase_model:tokyotech-llm/Swallow-7b-instruct-hfbase_model:quantized:tokyotech-llm/Swallow-7b-instruct-hflicense:llama2region:us

benchmark	category	score	context	conf	evidence
CommonsenseQA	knowledge	48.08		high	`\| Swallow \| 7B \| 0.4808 \| 0.5078 \| 0.5968 \| 0.8573 \| 0.1830 \| 0.1240 \| 0.2510 \| 0.1511 \|`
MGSM	math	12.4		high	`\| Swallow \| 7B \| 0.4808 \| 0.5078 \| 0.5968 \| 0.8573 \| 0.1830 \| 0.1240 \| 0.2510 \| 0.1511 \|`

none scraped.