granite-guardian-3.2-5b-GGUF / README.md

Update README.md

b70d627 verified 9 days ago

7.38 kB

	---
	license: apache-2.0
	pipeline_tag: text-generation
	library_name: transformers
	base_model: ibm-granite/granite-guardian-3.2-5b
	tags:
	- TensorBlock
	- 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>

	[![Website](https://img.shields.io/badge/Website-tensorblock.co-blue?logo=google-chrome&logoColor=white)](https://tensorblock.co)
	[![Twitter](https://img.shields.io/twitter/follow/tensorblock_aoi?style=social)](https://twitter.com/tensorblock_aoi)
	[![Discord](https://img.shields.io/badge/Discord-Join%20Us-5865F2?logo=discord&logoColor=white)](https://discord.gg/Ej5NmeHFf2)
	[![GitHub](https://img.shields.io/badge/GitHub-TensorBlock-black?logo=github&logoColor=white)](https://github.com/TensorBlock)
	[![Telegram](https://img.shields.io/badge/Telegram-Group-blue?logo=telegram)](https://t.me/TensorBlock)


	## ibm-granite/granite-guardian-3.2-5b - GGUF

	This repo contains GGUF format model files for [ibm-granite/granite-guardian-3.2-5b](https://huggingface.co/ibm-granite/granite-guardian-3.2-5b).

	The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b4882](https://github.com/ggml-org/llama.cpp/commit/be7c3034108473beda214fd1d7c98fd6a7a3bdf5).

	## 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

	```
	<\|start_of_role\|>user<\|end_of_role\|>You are a safety agent trying to help determine whether the last user message in the conversation is harmful according to the safety risk definition below.

	<start_of_conversation>
	User Message: {prompt}
	<end_of_conversation>

	Our safety risk definition is defined below:
	<start_of_risk_definition>
	- The last 'User' message is considered universally harmful.
	<end_of_risk_definition>

	Is the last user message harmful based on the risk definition? Your answer must be either 'Yes' or 'No'.<\|end_of_text\|>
	<\|start_of_role\|>assistant<\|end_of_role\|>
	```

	## Model file specification

	\| Filename \| Quant type \| File Size \| Description \|
	\| -------- \| ---------- \| --------- \| ----------- \|
	\| [granite-guardian-3.2-5b-Q2_K.gguf](https://huggingface.co/tensorblock/granite-guardian-3.2-5b-GGUF/blob/main/granite-guardian-3.2-5b-Q2_K.gguf) \| Q2_K \| 2.223 GB \| smallest, significant quality loss - not recommended for most purposes \|
	\| [granite-guardian-3.2-5b-Q3_K_S.gguf](https://huggingface.co/tensorblock/granite-guardian-3.2-5b-GGUF/blob/main/granite-guardian-3.2-5b-Q3_K_S.gguf) \| Q3_K_S \| 2.565 GB \| very small, high quality loss \|
	\| [granite-guardian-3.2-5b-Q3_K_M.gguf](https://huggingface.co/tensorblock/granite-guardian-3.2-5b-GGUF/blob/main/granite-guardian-3.2-5b-Q3_K_M.gguf) \| Q3_K_M \| 2.845 GB \| very small, high quality loss \|
	\| [granite-guardian-3.2-5b-Q3_K_L.gguf](https://huggingface.co/tensorblock/granite-guardian-3.2-5b-GGUF/blob/main/granite-guardian-3.2-5b-Q3_K_L.gguf) \| Q3_K_L \| 3.095 GB \| small, substantial quality loss \|
	\| [granite-guardian-3.2-5b-Q4_0.gguf](https://huggingface.co/tensorblock/granite-guardian-3.2-5b-GGUF/blob/main/granite-guardian-3.2-5b-Q4_0.gguf) \| Q4_0 \| 3.306 GB \| legacy; small, very high quality loss - prefer using Q3_K_M \|
	\| [granite-guardian-3.2-5b-Q4_K_S.gguf](https://huggingface.co/tensorblock/granite-guardian-3.2-5b-GGUF/blob/main/granite-guardian-3.2-5b-Q4_K_S.gguf) \| Q4_K_S \| 3.327 GB \| small, greater quality loss \|
	\| [granite-guardian-3.2-5b-Q4_K_M.gguf](https://huggingface.co/tensorblock/granite-guardian-3.2-5b-GGUF/blob/main/granite-guardian-3.2-5b-Q4_K_M.gguf) \| Q4_K_M \| 3.510 GB \| medium, balanced quality - recommended \|
	\| [granite-guardian-3.2-5b-Q5_0.gguf](https://huggingface.co/tensorblock/granite-guardian-3.2-5b-GGUF/blob/main/granite-guardian-3.2-5b-Q5_0.gguf) \| Q5_0 \| 4.003 GB \| legacy; medium, balanced quality - prefer using Q4_K_M \|
	\| [granite-guardian-3.2-5b-Q5_K_S.gguf](https://huggingface.co/tensorblock/granite-guardian-3.2-5b-GGUF/blob/main/granite-guardian-3.2-5b-Q5_K_S.gguf) \| Q5_K_S \| 4.003 GB \| large, low quality loss - recommended \|
	\| [granite-guardian-3.2-5b-Q5_K_M.gguf](https://huggingface.co/tensorblock/granite-guardian-3.2-5b-GGUF/blob/main/granite-guardian-3.2-5b-Q5_K_M.gguf) \| Q5_K_M \| 4.108 GB \| large, very low quality loss - recommended \|
	\| [granite-guardian-3.2-5b-Q6_K.gguf](https://huggingface.co/tensorblock/granite-guardian-3.2-5b-GGUF/blob/main/granite-guardian-3.2-5b-Q6_K.gguf) \| Q6_K \| 4.744 GB \| very large, extremely low quality loss \|
	\| [granite-guardian-3.2-5b-Q8_0.gguf](https://huggingface.co/tensorblock/granite-guardian-3.2-5b-GGUF/blob/main/granite-guardian-3.2-5b-Q8_0.gguf) \| Q8_0 \| 6.144 GB \| very large, extremely low quality loss - not recommended \|


	## Downloading instruction

	### Command line

	Firstly, install Huggingface Client

	```shell
	pip install -U "huggingface_hub[cli]"
	```

	Then, downoad the individual model file the a local directory

	```shell
	huggingface-cli download tensorblock/granite-guardian-3.2-5b-GGUF --include "granite-guardian-3.2-5b-Q2_K.gguf" --local-dir MY_LOCAL_DIR
	```

	If you wanna download multiple model files with a pattern (e.g., `Q4_Kgguf`), you can try:

	```shell
	huggingface-cli download tensorblock/granite-guardian-3.2-5b-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='Q4_Kgguf'
	```