Instructions to use QuantFactory/Hathor_Sofit-L3-8B-v1-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 QuantFactory/Hathor_Sofit-L3-8B-v1-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 QuantFactory/Hathor_Sofit-L3-8B-v1-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf QuantFactory/Hathor_Sofit-L3-8B-v1-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 QuantFactory/Hathor_Sofit-L3-8B-v1-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf QuantFactory/Hathor_Sofit-L3-8B-v1-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 QuantFactory/Hathor_Sofit-L3-8B-v1-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf QuantFactory/Hathor_Sofit-L3-8B-v1-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 QuantFactory/Hathor_Sofit-L3-8B-v1-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf QuantFactory/Hathor_Sofit-L3-8B-v1-GGUF:Q4_K_M

Use Docker

docker model run hf.co/QuantFactory/Hathor_Sofit-L3-8B-v1-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use QuantFactory/Hathor_Sofit-L3-8B-v1-GGUF with Ollama:
```
ollama run hf.co/QuantFactory/Hathor_Sofit-L3-8B-v1-GGUF:Q4_K_M
```

Unsloth Studio

How to use QuantFactory/Hathor_Sofit-L3-8B-v1-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 QuantFactory/Hathor_Sofit-L3-8B-v1-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 QuantFactory/Hathor_Sofit-L3-8B-v1-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for QuantFactory/Hathor_Sofit-L3-8B-v1-GGUF to start chatting

Docker Model Runner
How to use QuantFactory/Hathor_Sofit-L3-8B-v1-GGUF with Docker Model Runner:
```
docker model run hf.co/QuantFactory/Hathor_Sofit-L3-8B-v1-GGUF:Q4_K_M
```

Lemonade

How to use QuantFactory/Hathor_Sofit-L3-8B-v1-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull QuantFactory/Hathor_Sofit-L3-8B-v1-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Hathor_Sofit-L3-8B-v1-GGUF-Q4_K_M

List all available models

lemonade list

Atomic Chat

QuantFactory/Hathor_Sofit-L3-8B-v1-GGUF

This is quantized version of Nitral-AI/Hathor_Sofit-L3-8B-v1 created using llama.cpp

Original Model Card

Hathor_Sofit [v1] is designed to seamlessly integrate the qualities of creativity, intelligence, and robust performance.

GGUF Quant's available Thanks to: Mradermacher <3 GGUF Here

EXL2 Quant's available Thanks to RiveRiPH <3 Exl2 8bpw Here Exl2 6.3bpw Here

Recomended ST Presets: Hathor Presets(Updated)

Training-Note: Hathor_Sofit [v1] is trained on 1 epoch of Private - STEM (Intruction/Dialogs), Hathor_0.5 Instructions, mixture of creative writing data (light/web/classical novels), roleplaying chat pairs over Hathor_0.85.

Additional Notes: This will be the last of the Hathor Model series, and all my trains over Llama 3.

Downloads last month: 43

GGUF

Model size

8B params

Architecture

llama

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support