Llama3.1-8B-Chinese-Chat-GGUF

Original Model

shenzhi-wang/Llama3.1-8B-Chinese-Chat

Run with LlamaEdge

Run with Gaianet

Prompt template:

prompt template: llama-3-chat

Context size:

chat_ctx_size: 128000

Run with GaiaNet:

Quantized with llama.cpp b3463

Downloads last month
71
GGUF
Model size
8.03B params
Architecture
llama

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.

Model tree for gaianet/Llama3.1-8B-Chinese-Chat-GGUF