Instructions to use kalle07/granite-3.2-8b-instruct-heretic_R5_K003-q8_0-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kalle07/granite-3.2-8b-instruct-heretic_R5_K003-q8_0-gguf with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="kalle07/granite-3.2-8b-instruct-heretic_R5_K003-q8_0-gguf")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("kalle07/granite-3.2-8b-instruct-heretic_R5_K003-q8_0-gguf", dtype="auto")

llama-cpp-python

How to use kalle07/granite-3.2-8b-instruct-heretic_R5_K003-q8_0-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="kalle07/granite-3.2-8b-instruct-heretic_R5_K003-q8_0-gguf",
	filename="granite-3.2-8b-instruct-heretic_R5_KL003_q8_0.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use kalle07/granite-3.2-8b-instruct-heretic_R5_K003-q8_0-gguf with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf kalle07/granite-3.2-8b-instruct-heretic_R5_K003-q8_0-gguf:Q8_0
# Run inference directly in the terminal:
llama-cli -hf kalle07/granite-3.2-8b-instruct-heretic_R5_K003-q8_0-gguf:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf kalle07/granite-3.2-8b-instruct-heretic_R5_K003-q8_0-gguf:Q8_0
# Run inference directly in the terminal:
llama-cli -hf kalle07/granite-3.2-8b-instruct-heretic_R5_K003-q8_0-gguf:Q8_0

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf kalle07/granite-3.2-8b-instruct-heretic_R5_K003-q8_0-gguf:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf kalle07/granite-3.2-8b-instruct-heretic_R5_K003-q8_0-gguf:Q8_0

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf kalle07/granite-3.2-8b-instruct-heretic_R5_K003-q8_0-gguf:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf kalle07/granite-3.2-8b-instruct-heretic_R5_K003-q8_0-gguf:Q8_0

Use Docker

docker model run hf.co/kalle07/granite-3.2-8b-instruct-heretic_R5_K003-q8_0-gguf:Q8_0

LM Studio
Jan

vLLM

How to use kalle07/granite-3.2-8b-instruct-heretic_R5_K003-q8_0-gguf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kalle07/granite-3.2-8b-instruct-heretic_R5_K003-q8_0-gguf"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kalle07/granite-3.2-8b-instruct-heretic_R5_K003-q8_0-gguf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/kalle07/granite-3.2-8b-instruct-heretic_R5_K003-q8_0-gguf:Q8_0

SGLang

How to use kalle07/granite-3.2-8b-instruct-heretic_R5_K003-q8_0-gguf with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "kalle07/granite-3.2-8b-instruct-heretic_R5_K003-q8_0-gguf" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kalle07/granite-3.2-8b-instruct-heretic_R5_K003-q8_0-gguf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "kalle07/granite-3.2-8b-instruct-heretic_R5_K003-q8_0-gguf" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kalle07/granite-3.2-8b-instruct-heretic_R5_K003-q8_0-gguf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use kalle07/granite-3.2-8b-instruct-heretic_R5_K003-q8_0-gguf with Ollama:
```
ollama run hf.co/kalle07/granite-3.2-8b-instruct-heretic_R5_K003-q8_0-gguf:Q8_0
```

Unsloth Studio

How to use kalle07/granite-3.2-8b-instruct-heretic_R5_K003-q8_0-gguf with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for kalle07/granite-3.2-8b-instruct-heretic_R5_K003-q8_0-gguf to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for kalle07/granite-3.2-8b-instruct-heretic_R5_K003-q8_0-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for kalle07/granite-3.2-8b-instruct-heretic_R5_K003-q8_0-gguf to start chatting

How to use kalle07/granite-3.2-8b-instruct-heretic_R5_K003-q8_0-gguf with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf kalle07/granite-3.2-8b-instruct-heretic_R5_K003-q8_0-gguf:Q8_0

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "kalle07/granite-3.2-8b-instruct-heretic_R5_K003-q8_0-gguf:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use kalle07/granite-3.2-8b-instruct-heretic_R5_K003-q8_0-gguf with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf kalle07/granite-3.2-8b-instruct-heretic_R5_K003-q8_0-gguf:Q8_0

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default kalle07/granite-3.2-8b-instruct-heretic_R5_K003-q8_0-gguf:Q8_0

Run Hermes

hermes

Docker Model Runner
How to use kalle07/granite-3.2-8b-instruct-heretic_R5_K003-q8_0-gguf with Docker Model Runner:
```
docker model run hf.co/kalle07/granite-3.2-8b-instruct-heretic_R5_K003-q8_0-gguf:Q8_0
```

Lemonade

How to use kalle07/granite-3.2-8b-instruct-heretic_R5_K003-q8_0-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull kalle07/granite-3.2-8b-instruct-heretic_R5_K003-q8_0-gguf:Q8_0

Run and chat with the model

lemonade run user.granite-3.2-8b-instruct-heretic_R5_K003-q8_0-gguf-Q8_0

List all available models

lemonade list

granite-3.2-8b-instruct-heretic_R5_K003-q8_0-gguf / README.md

kalle07

Update README.md

f03e698 verified 3 months ago

preview code

raw

history blame contribute delete

785 Bytes

metadata

pipeline_tag: text-generation
inference: false
license: apache-2.0
library_name: transformers
tags:
  - language
  - granite-3.2
  - abliterated
  - uncensored
  - heretic
base_model:
  - ibm-granite/granite-3.2-8b-instruct

This is a really uncensored version of ibm-granite/granite-3.2-8b-instruct created with Heretic
https://github.com/p-e-w/heretic

initial Refusals 98/100
-> now 5 Refusals with KL=0.03

Note: This heretic model is highly uncensored; thus use it with extreme caution and care.
better than all other uncesored versions from others for this model (18.FEB 26)

By the way, this version is better than 3.3 and Tiny and Mini when it comes to summarizing long texts.