Hugging Face's logo

MaziyarPanahi
/
Meta-Llama-3-8B-Instruct-GGUF

Text Generation
Transformers
GGUF
PyTorch
English
mistral
facebook
meta
llama
llama-3
quantized
2-bit
3-bit
4-bit precision
5-bit
6-bit
8-bit precision
16-bit
GGUF
conversational
Model card Files Community
20
New discussion

OK llama 3 8b model is INSANE. Is almost as good as wizard 2 8x22b!

52
#5 opened 7 months ago by mirek190

Impressive.

1
#19 opened 7 months ago by Ecstasio

Llama-3: Syntax of the prompt and conversation with 3 or more participants

5
#16 opened 7 months ago by tsalvoch

template for llamacpp

1
#4 opened 7 months ago by mirek190