Not-For-All-Audiences

Instructions to use Casual-Autopsy/The-True-Abomination-24B-imat-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Casual-Autopsy/The-True-Abomination-24B-imat-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Casual-Autopsy/The-True-Abomination-24B-imat-GGUF",
	filename="The-True-Abomination-24B-iq4_nl.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Casual-Autopsy/The-True-Abomination-24B-imat-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Casual-Autopsy/The-True-Abomination-24B-imat-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Casual-Autopsy/The-True-Abomination-24B-imat-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Casual-Autopsy/The-True-Abomination-24B-imat-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Casual-Autopsy/The-True-Abomination-24B-imat-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 Casual-Autopsy/The-True-Abomination-24B-imat-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Casual-Autopsy/The-True-Abomination-24B-imat-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 Casual-Autopsy/The-True-Abomination-24B-imat-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Casual-Autopsy/The-True-Abomination-24B-imat-GGUF:Q4_K_M

Use Docker

docker model run hf.co/Casual-Autopsy/The-True-Abomination-24B-imat-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use Casual-Autopsy/The-True-Abomination-24B-imat-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Casual-Autopsy/The-True-Abomination-24B-imat-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Casual-Autopsy/The-True-Abomination-24B-imat-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Casual-Autopsy/The-True-Abomination-24B-imat-GGUF:Q4_K_M

Ollama
How to use Casual-Autopsy/The-True-Abomination-24B-imat-GGUF with Ollama:
```
ollama run hf.co/Casual-Autopsy/The-True-Abomination-24B-imat-GGUF:Q4_K_M
```

Unsloth Studio

How to use Casual-Autopsy/The-True-Abomination-24B-imat-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 Casual-Autopsy/The-True-Abomination-24B-imat-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 Casual-Autopsy/The-True-Abomination-24B-imat-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Casual-Autopsy/The-True-Abomination-24B-imat-GGUF to start chatting

Docker Model Runner
How to use Casual-Autopsy/The-True-Abomination-24B-imat-GGUF with Docker Model Runner:
```
docker model run hf.co/Casual-Autopsy/The-True-Abomination-24B-imat-GGUF:Q4_K_M
```

Lemonade

How to use Casual-Autopsy/The-True-Abomination-24B-imat-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Casual-Autopsy/The-True-Abomination-24B-imat-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.The-True-Abomination-24B-imat-GGUF-Q4_K_M

List all available models

lemonade list

The-True-Abomination-24B-imat-GGUF

Calabration Datasets

The following calabration datasets were used to make the imatrix file:

Recipe

1. bartowski dataset:

./llama-imatrix -t 14 -c 2048 -b 1024 -ub 512 -f ../Datasets/imatrix_cal/bartowski_imatrix.text -ngl 8 -m ../Models/RP_Models/The-True-Abomination-24B-bf16.gguf -o ../Models/RP_Models/batowski_The-True-Abomination-24B-imatrix.dat --chunks 32

Avg. ppl. for Mistral-Small Models: ~5-6

2. virt-io dataset - pass 1:

./llama-imatrix -t 14 -c 8192 -b 2048 -ub 1024 -f ../Datasets/imatrix_cal/virt-io_imatrix.text -ngl 8 -m ../Models/RP_Models/The-True-Abomination-24B-bf16.gguf -o ../Models/RP_Models/virt-io_The-True-Abomination-24B-imatrix.dat --chunk 3 --chunks 17 --in-file ../Models/RP_Models/batowski_The-True-Abomination-24B-imatrix.dat

Avg. ppl. for Mistral-Small Models: ~3-4

3. virt-io dataset - pass 2:

./llama-imatrix -t 14 -c 8192 -b 2048 -ub 1024 -f ../Datasets/imatrix_cal/virt-io_imatrix.text -ngl 8 -m ../Models/RP_Models/The-True-Abomination-24B-bf16.gguf -o ../Models/RP_Models/virt-io_The-True-Abomination-24B-imatrix.dat --chunk 109 --in-file ../Models/RP_Models/virt-io_The-True-Abomination-24B-imatrix.dat

Avg. ppl. for Mistral-Small Models: ~2-3

4. lewdiculous dataset:

./llama-imatrix -t 14 -c 1024 -b 512 -ub 256 -f ../Datasets/imatrix_cal/lewdiculous_imatrix.text -ngl 8 -m ../Models/RP_Models/The-True-Abomination-24B-bf16.gguf -o ../Models/RP_Models/The-True-Abomination-24B-imatrix.dat --chunks 32 --in-file ../Models/RP_Models/virt-io_The-True-Abomination-24B-imatrix.dat --in-file ../Models/RP_Models/batowski_The-True-Abomination-24B-imatrix.dat

Avg. ppl. for Mistral-Small Models: ~5-6

Downloads last month: 5

GGUF

Model size

24B params

Architecture

llama

Hardware compatibility

4-bit

Model tree for Casual-Autopsy/The-True-Abomination-24B-imat-GGUF

Base model

Casual-Autopsy/The-True-Abomination-24B

Quantized

(4)

this model