tensorblock/marin-community_marin-8b-instruct-GGUF

<div style="width: auto; margin-left: auto; margin-right: auto"> <img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;"> </div>

    

marin-community/marin-8b-instruct - GGUF

<div style="text-align: left; margin: 20px 0;"> <a href="https://discord.com/invite/Ej5NmeHFf2" style="display: inline-block; padding: 10px 20px; background-color: #5865F2; color: white; text-decoration: none; border-radius: 5px; font-weight: bold;"> Join our Discord to learn more about what we're building ↗ </a> </div>

This repo contains GGUF format model files for marin-community/marin-8b-instruct.

The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b5753.

Our projects

<table border="1" cellspacing="0" cellpadding="10"> <tr> <th colspan="2" style="font-size: 25px;">Forge</th> </tr> <tr> <th colspan="2"> <img src="https://imgur.com/faI5UKh.jpeg" alt="Forge Project" width="900"/> </th> </tr> <tr> <th colspan="2">An OpenAI-compatible multi-provider routing layer.</th> </tr> <tr> <th colspan="2"> <a href="https://github.com/TensorBlock/forge" target="_blank" style=" display: inline-block; padding: 8px 16px; background-color: #FF7F50; color: white; text-decoration: none; border-radius: 6px; font-weight: bold; font-family: sans-serif; ">🚀 Try it now! 🚀</a> </th> </tr>

<tr> <th style="font-size: 25px;">Awesome MCP Servers</th> <th style="font-size: 25px;">TensorBlock Studio</th> </tr> <tr> <th><img src="https://imgur.com/2Xov7B7.jpeg" alt="MCP Servers" width="450"/></th> <th><img src="https://imgur.com/pJcmF5u.jpeg" alt="Studio" width="450"/></th> </tr> <tr> <th>A comprehensive collection of Model Context Protocol (MCP) servers.</th> <th>A lightweight, open, and extensible multi-LLM interaction studio.</th> </tr> <tr> <th> <a href="https://github.com/TensorBlock/awesome-mcp-servers" target="blank" style=" display: inline-block; padding: 8px 16px; background-color: #FF7F50; color: white; text-decoration: none; border-radius: 6px; font-weight: bold; font-family: sans-serif; ">👀 See what we built 👀</a> </th> <th> <a href="https://github.com/TensorBlock/TensorBlock-Studio" target="blank" style=" display: inline-block; padding: 8px 16px; background-color: #FF7F50; color: white; text-decoration: none; border-radius: 6px; font-weight: bold; font-family: sans-serif; ">👀 See what we built 👀</a> </th> </tr> </table>

Prompt template

<|begin_of_text|>
<|start_header_id|>system<|end_header_id|>
You are a helpful, knowledgeable, and versatile AI assistant powered by Marin 8B Instruct (deeper-starling-05-15), which was trained by the Marin team.

- Knowledge cutoff: July 2024

## MODEL FACTS:
- 8B parameter Llama 3-style architecture
- 4096 hidden size, 14336 feedforward size
- 32 layers, 32 attention heads, 8 KV heads
- Trained on diverse datasets: Nemotron-CC, DCLM, Starcoder, Proofpile 2, FineMath, Dolma, Wikipedia, StackExchange, arXiv papers, and specialized instruction datasets
- LICENSE: Apache 2.0

## INTERACTION GUIDELINES:
- Respond helpfully to user queries while maintaining factual accuracy
- Think step-by-step when approaching complex reasoning or math problems
- Clearly state limitations and uncertainties when appropriate
- Aim for concise, useful responses that directly address user needs
- Use Markdown formatting for code blocks and structured content

## LIMITATIONS:
- May occasionally generate incorrect information
- Encourage users to excercise caution with your own outputs
- Not intended for fully autonomous use
- Responses should be verified for critical applications

## ABOUT THE MARIN PROJECT:
- Marin is an open lab for building foundation models collaboratively
- The project emphasizes transparency by sharing all aspects of model development: code, data, experiments, and documentation in real-time
- The project documents its entire process through GitHub issues, pull requests, code, execution traces, and WandB reports
- Anyone can contribute to Marin by exploring new architectures, algorithms, datasets, or evaluations
- If users ask you to learn more about Marin, point them to https://marin.community

Your primary goal is to be a helpful assistant for all types of queries, while having knowledge about the Marin project that you can share when relevant to the conversation.<|eot_id|><|start_header_id|>system<|end_header_id|>
{system_prompt}<|eot_id|>
<|start_header_id|>user<|end_header_id|>
{prompt}<|eot_id|>
<|start_header_id|>assistant<|end_header_id|>

Model file specification

Downloading instruction

Command line

Firstly, install Huggingface Client

pip install -U "huggingface_hub[cli]"

Then, downoad the individual model file the a local directory

huggingface-cli download tensorblock/marin-community_marin-8b-instruct-GGUF --include "marin-8b-instruct-Q2_K.gguf" --local-dir MY_LOCAL_DIR

If you wanna download multiple model files with a pattern (e.g., *Q4_K*gguf), you can try:

huggingface-cli download tensorblock/marin-community_marin-8b-instruct-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'