firefly-llama2-13B-chat-GGUF

Home/Models/TheBloke/firefly-llama2-13B-chat-GGUF

TheBloke/firefly-llama2-13B-chat-GGUF

kind: gguf
quant: gguf (2-bit)
family: llama
modality: —
root model: YeungNLP/firefly-llama2-13b-chat
provider: TheBloke
license: llama2
language: —
context: —
library: —
vRAM (GB): —
size on disk: —
downloads: 456
likes: 3
created: —
last modified: 2023-11-17T13:42:37+00:00 (2023)
huggingface: https://huggingface.co/TheBloke/firefly-llama2-13B-chat-GGUF
tags: transformersggufllamabase_model:YeungNLP/firefly-llama2-13b-chatbase_model:quantized:YeungNLP/firefly-llama2-13b-chatlicense:llama2region:us

benchmark	category	score	conf	evidence
HellaSwag	knowledge	79.74	low	`\| chinese-alpaca-2-13b \| 60.94 \| 58.7 \| 79.74 \| 55.1 \| 50.22 \|`
CMMLU	knowledge	56.83	low	`\| firefly-baichuan2-13b \| 56.83 \| 4\*V100，QLoRA，指令微调 \|`
MMLU	knowledge	55.1	low	`\| chinese-alpaca-2-13b \| 60.94 \| 58.7 \| 79.74 \| 55.1 \| 50.22 \|`
TruthfulQA	safety	50.22	low	`\| chinese-alpaca-2-13b \| 60.94 \| 58.7 \| 79.74 \| 55.1 \| 50.22 \|`

none scraped.