Llama3-70B-Chinese-Chat-GGUF-4bit

Home/Models/shenzhi-wang/Llama3-70B-Chinese-Chat-GGUF-4bit

shenzhi-wang/Llama3-70B-Chinese-Chat-GGUF-4bit

kind: gguf
quant: gguf (4-bit)
family: llama
modality: text-generation
root model: meta-llama/Meta-Llama-3-70B-Instruct
provider: shenzhi-wang
license: llama3
language: en, zh
context: 8K
library: transformers
vRAM (GB): —
size on disk: —
downloads: 189
likes: 18
created: —
last modified: 2024-07-04T10:16:17+00:00 (2024)
huggingface: https://huggingface.co/shenzhi-wang/Llama3-70B-Chinese-Chat-GGUF-4bit
tags: transformersggufllamatext-generationllama-factoryorpoenzharxiv:2403.07691arxiv:2306.09212base_model:meta-llama/Meta-Llama-3-70B-Instructbase_model:quantized:meta-llama/Meta-Llama-3-70B-Instructlicense:llama3endpoints_compatibleregion:usconversational

benchmark	category	score	context	conf	evidence
CMMLU	knowledge	55.51		low	`\| ChatGPT \| 54.4 \| 41.4 \| 55.51 \|`
C-Eval	knowledge	54.4		low	`\| ChatGPT \| 54.4 \| 41.4 \| 55.51 \|`

none scraped.