Origional Model HuggingFaceH4/mistral-7b-grok

This model is not fully trained jet, this is only to play around with it.

Prompt Format:

<s><|system|>
{system}</s>
<s><|user|>
{user}</s>
<s><|assistant|>
{assistant}</s>

GGUF

Model size

7B params

Architecture

llama

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support