This is a Base quantized base model. As it might not be appropriate and may generate awkward responses. for instructions follow this format. Instructions:

[INST]Your Instruction Here[/INST]

Responses:

[RESPONSE]Your Message here[/RESPONSE]

Correctness:

[CORRECTNESS]Your Statement Here[/CORRECTNESS]
Downloads last month
2
GGUF
Model size
7B params
Architecture
llama
Hardware compatibility
Log In to add your hardware

4-bit

5-bit

6-bit

8-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support