This is a math fine-tuning of the LLaMA-3 70B model.

Prompt template

Llama3

<|begin_of_text|><|start_header_id|>system<|end_header_id|>

{{ system_prompt }}<|eot_id|><|start_header_id|>user<|end_header_id|>

{{ user_message_1 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|>

{{ model_answer_1 }}<|eot_id|><|start_header_id|>user<|end_header_id|>

{{ user_message_2 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|>

Run this model

You can run this model using Jan Desktop on Mac, Windows, or Linux.

Jan is an open source, ChatGPT alternative that is:

💻 100% offline on your machine: Your conversations remain confidential, and visible only to you.
🗂️ ** An Open File Format**: Conversations and model settings stay on your computer and can be exported or deleted at any time.
🌐 OpenAI Compatible: Local server on port 1337 with OpenAI compatible endpoints
🌍 Open Source & Free: We build in public; check out our Github

About Jan

Jan believes in the need for an open-source AI ecosystem and is building the infra and tooling to allow open-source AIs to compete on a level playing field with proprietary ones.

Jan's long-term vision is to build a cognitive framework for future robots, who are practical, useful assistants for humans and businesses in everyday life.