Instructions to use giannisan/Jett-w26-abliterated-GGUf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use giannisan/Jett-w26-abliterated-GGUf with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("giannisan/Jett-w26-abliterated-GGUf", dtype="auto")

llama-cpp-python

How to use giannisan/Jett-w26-abliterated-GGUf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="giannisan/Jett-w26-abliterated-GGUf",
	filename="Jett-w26-abliterated.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 giannisan/Jett-w26-abliterated-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 giannisan/Jett-w26-abliterated-GGUf:Q4_1
# Run inference directly in the terminal:
llama cli -hf giannisan/Jett-w26-abliterated-GGUf:Q4_1

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf giannisan/Jett-w26-abliterated-GGUf:Q4_1
# Run inference directly in the terminal:
llama cli -hf giannisan/Jett-w26-abliterated-GGUf:Q4_1

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 giannisan/Jett-w26-abliterated-GGUf:Q4_1
# Run inference directly in the terminal:
./llama-cli -hf giannisan/Jett-w26-abliterated-GGUf:Q4_1

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 giannisan/Jett-w26-abliterated-GGUf:Q4_1
# Run inference directly in the terminal:
./build/bin/llama-cli -hf giannisan/Jett-w26-abliterated-GGUf:Q4_1

Use Docker

docker model run hf.co/giannisan/Jett-w26-abliterated-GGUf:Q4_1

LM Studio
Jan
Ollama
How to use giannisan/Jett-w26-abliterated-GGUf with Ollama:
```
ollama run hf.co/giannisan/Jett-w26-abliterated-GGUf:Q4_1
```

Unsloth Studio

How to use giannisan/Jett-w26-abliterated-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 giannisan/Jett-w26-abliterated-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 giannisan/Jett-w26-abliterated-GGUf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for giannisan/Jett-w26-abliterated-GGUf to start chatting

Atomic Chat new
Docker Model Runner
How to use giannisan/Jett-w26-abliterated-GGUf with Docker Model Runner:
```
docker model run hf.co/giannisan/Jett-w26-abliterated-GGUf:Q4_1
```

Lemonade

How to use giannisan/Jett-w26-abliterated-GGUf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull giannisan/Jett-w26-abliterated-GGUf:Q4_1

Run and chat with the model

lemonade run user.Jett-w26-abliterated-GGUf-Q4_1

List all available models

lemonade list

Jett-w26

THIS IS THE Q8_0 GGUF QUANT of giannisan/Jett-w26 USING faispy's notebook. It should be uncensored. Prompting may be beneficial.

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the DARE TIES merge method using yam-peleg/Experiment26-7B as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: yam-peleg/Experiment26-7B
    # No parameters necessary for base model
  - model: Kukedlc/Jupiter-k-7B-slerp
    parameters:
      density: 0.58
      weight: 0.25
  - model: S-miguel/The-Trinity-Coder-7B
    parameters:
      density: 0.6
      weight: 0.20
  - model: chihoonlee10/T3Q-Mistral-Orca-Math-DPO
    parameters:
      density: 0.6
      weight: 0.20
  - model: senseable/WestLake-7B-v2
    parameters:
      density: 0.56
      weight: 0.20
  - model: InferenceIllusionist/Excalibur-7b-DPO
    parameters:
      density: 0.58
      weight: 0.15
merge_method: dare_ties
base_model: yam-peleg/Experiment26-7B
dtype: bfloat16