Instructions to use DavidAU/L3.1-RP-Hero-Dirty_Harry-8B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use DavidAU/L3.1-RP-Hero-Dirty_Harry-8B-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf DavidAU/L3.1-RP-Hero-Dirty_Harry-8B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf DavidAU/L3.1-RP-Hero-Dirty_Harry-8B-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf DavidAU/L3.1-RP-Hero-Dirty_Harry-8B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf DavidAU/L3.1-RP-Hero-Dirty_Harry-8B-GGUF:Q4_K_M

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 DavidAU/L3.1-RP-Hero-Dirty_Harry-8B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf DavidAU/L3.1-RP-Hero-Dirty_Harry-8B-GGUF:Q4_K_M

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 DavidAU/L3.1-RP-Hero-Dirty_Harry-8B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf DavidAU/L3.1-RP-Hero-Dirty_Harry-8B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/DavidAU/L3.1-RP-Hero-Dirty_Harry-8B-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use DavidAU/L3.1-RP-Hero-Dirty_Harry-8B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "DavidAU/L3.1-RP-Hero-Dirty_Harry-8B-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": "DavidAU/L3.1-RP-Hero-Dirty_Harry-8B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/DavidAU/L3.1-RP-Hero-Dirty_Harry-8B-GGUF:Q4_K_M

Ollama
How to use DavidAU/L3.1-RP-Hero-Dirty_Harry-8B-GGUF with Ollama:
```
ollama run hf.co/DavidAU/L3.1-RP-Hero-Dirty_Harry-8B-GGUF:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use DavidAU/L3.1-RP-Hero-Dirty_Harry-8B-GGUF with Docker Model Runner:
```
docker model run hf.co/DavidAU/L3.1-RP-Hero-Dirty_Harry-8B-GGUF:Q4_K_M
```

Lemonade

How to use DavidAU/L3.1-RP-Hero-Dirty_Harry-8B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull DavidAU/L3.1-RP-Hero-Dirty_Harry-8B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.L3.1-RP-Hero-Dirty_Harry-8B-GGUF-Q4_K_M

List all available models

lemonade list

Atomic Chat

General overview / discussion.

by VizorZ0042 - opened Sep 6, 2025

Discussion

VizorZ0042

Sep 6, 2025

@DavidAU Interesting model, works only with RepPen 1.02. 1.03 and higher will cause major issues.

Its not very descriptive as others mentioned, it just aimed to work with lower penalties. Many models I've used before actually become very descriptive with lower penalties, but most of them can't work and start becoming repetitive. But I never tested with my newest experimental settings that are mostly based on fine-tuning of TFS.

I will post the results after finishing the experimentation with TFS and lower RepPen.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment