Instructions to use fuzzy-mittenz/Huihui-granite-4.0-h-tiny-abliterated-Q4_K_M-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use fuzzy-mittenz/Huihui-granite-4.0-h-tiny-abliterated-Q4_K_M-GGUF with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("fuzzy-mittenz/Huihui-granite-4.0-h-tiny-abliterated-Q4_K_M-GGUF", dtype="auto")

llama-cpp-python

How to use fuzzy-mittenz/Huihui-granite-4.0-h-tiny-abliterated-Q4_K_M-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="fuzzy-mittenz/Huihui-granite-4.0-h-tiny-abliterated-Q4_K_M-GGUF",
	filename="huihui-granite-4.0-h-tiny-abliterated-q4_k_m-imat.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 fuzzy-mittenz/Huihui-granite-4.0-h-tiny-abliterated-Q4_K_M-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 fuzzy-mittenz/Huihui-granite-4.0-h-tiny-abliterated-Q4_K_M-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf fuzzy-mittenz/Huihui-granite-4.0-h-tiny-abliterated-Q4_K_M-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 fuzzy-mittenz/Huihui-granite-4.0-h-tiny-abliterated-Q4_K_M-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf fuzzy-mittenz/Huihui-granite-4.0-h-tiny-abliterated-Q4_K_M-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 fuzzy-mittenz/Huihui-granite-4.0-h-tiny-abliterated-Q4_K_M-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf fuzzy-mittenz/Huihui-granite-4.0-h-tiny-abliterated-Q4_K_M-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 fuzzy-mittenz/Huihui-granite-4.0-h-tiny-abliterated-Q4_K_M-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf fuzzy-mittenz/Huihui-granite-4.0-h-tiny-abliterated-Q4_K_M-GGUF:Q4_K_M

Use Docker

docker model run hf.co/fuzzy-mittenz/Huihui-granite-4.0-h-tiny-abliterated-Q4_K_M-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use fuzzy-mittenz/Huihui-granite-4.0-h-tiny-abliterated-Q4_K_M-GGUF with Ollama:
```
ollama run hf.co/fuzzy-mittenz/Huihui-granite-4.0-h-tiny-abliterated-Q4_K_M-GGUF:Q4_K_M
```

Unsloth Studio

How to use fuzzy-mittenz/Huihui-granite-4.0-h-tiny-abliterated-Q4_K_M-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 fuzzy-mittenz/Huihui-granite-4.0-h-tiny-abliterated-Q4_K_M-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 fuzzy-mittenz/Huihui-granite-4.0-h-tiny-abliterated-Q4_K_M-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for fuzzy-mittenz/Huihui-granite-4.0-h-tiny-abliterated-Q4_K_M-GGUF to start chatting

Atomic Chat new
Docker Model Runner
How to use fuzzy-mittenz/Huihui-granite-4.0-h-tiny-abliterated-Q4_K_M-GGUF with Docker Model Runner:
```
docker model run hf.co/fuzzy-mittenz/Huihui-granite-4.0-h-tiny-abliterated-Q4_K_M-GGUF:Q4_K_M
```

Lemonade

How to use fuzzy-mittenz/Huihui-granite-4.0-h-tiny-abliterated-Q4_K_M-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull fuzzy-mittenz/Huihui-granite-4.0-h-tiny-abliterated-Q4_K_M-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Huihui-granite-4.0-h-tiny-abliterated-Q4_K_M-GGUF-Q4_K_M

List all available models

lemonade list

Huihui-granite-4.0-h-tiny-abliterated-Q4_K_M-GGUF / README.md

fuzzy-mittenz

Update README.md

7c517f4 verified 9 months ago

preview code

Raw

History Blame Contribute Delete

1.3 kB

metadata

base_model: huihui-ai/Huihui-granite-4.0-h-tiny-abliterated
license: apache-2.0
library_name: transformers
tags:
  - language
  - granite-4.0
  - abliterated
  - uncensored
  - llama-cpp
datasets:
  - IntelligentEstate/The_Key

..untested.. only available for evaluation

IntelligentEstate/Jari-7B-Q4_K_M-GGUF

After the experts over at IBM highjacked the work of our counterparts here in the 🤗 we thought it prudent to abliterate their finely crafted granite and set it back upon the masses as a 4 headed beast and as they continue so will we, rinse remark on that which is remarkable and repeat.. This model was converted to GGUF format from huihui-ai/Huihui-granite-4.0-h-tiny-abliterated using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to IBMs Granite hybrid model suite for foundation information as well as the abliteration process for further reference. Overall enjoy.

Use with llama.cpp

Install llama.cpp through brew (works on Mac and Linux)

brew install llama.cpp

Invoke the llama.cpp server or the CLI.