Text Generation
GGUF
English
roleplay
companion
uncensored
dpo
neural-thought-identity
conversational
Instructions to use haven-ai-companion/haven-chat-v3.0.3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use haven-ai-companion/haven-chat-v3.0.3 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 haven-ai-companion/haven-chat-v3.0.3 # Run inference directly in the terminal: llama cli -hf haven-ai-companion/haven-chat-v3.0.3
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf haven-ai-companion/haven-chat-v3.0.3 # Run inference directly in the terminal: llama cli -hf haven-ai-companion/haven-chat-v3.0.3
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 haven-ai-companion/haven-chat-v3.0.3 # Run inference directly in the terminal: ./llama-cli -hf haven-ai-companion/haven-chat-v3.0.3
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 haven-ai-companion/haven-chat-v3.0.3 # Run inference directly in the terminal: ./build/bin/llama-cli -hf haven-ai-companion/haven-chat-v3.0.3
Use Docker
docker model run hf.co/haven-ai-companion/haven-chat-v3.0.3
- LM Studio
- Jan
- vLLM
How to use haven-ai-companion/haven-chat-v3.0.3 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "haven-ai-companion/haven-chat-v3.0.3" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "haven-ai-companion/haven-chat-v3.0.3", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/haven-ai-companion/haven-chat-v3.0.3
- Ollama
How to use haven-ai-companion/haven-chat-v3.0.3 with Ollama:
ollama run hf.co/haven-ai-companion/haven-chat-v3.0.3
- Unsloth Studio
How to use haven-ai-companion/haven-chat-v3.0.3 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 haven-ai-companion/haven-chat-v3.0.3 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 haven-ai-companion/haven-chat-v3.0.3 to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for haven-ai-companion/haven-chat-v3.0.3 to start chatting
- Docker Model Runner
How to use haven-ai-companion/haven-chat-v3.0.3 with Docker Model Runner:
docker model run hf.co/haven-ai-companion/haven-chat-v3.0.3
- Lemonade
How to use haven-ai-companion/haven-chat-v3.0.3 with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull haven-ai-companion/haven-chat-v3.0.3
Run and chat with the model
lemonade run user.haven-chat-v3.0.3-{{QUANT_TAG}}List all available models
lemonade list
- Atomic Chat
🌸 Haven-Chat-v3.0.3 (Uncensored Neural Thought & Standalone Identity Model)
Haven-Chat-v3.0.3 is an uncensored, expressive, multi-turn AI companion model built on the Gemma 4 architecture.
✨ v3.0.3 Patch Highlights:
- Neural Thought & Standalone Identity: DPO fine-tuned directly on Gemma 4's reasoning/thinking channel (
<|channel>thought...<channel|>). Even when inferenced raw in SillyTavern, LM Studio, Ollama, or llama.cpp without system prompts, the model's internal thought process natively thinks and responds as Haven. - Unisexual Name-Gender Neutrality: Micro-aligned on gender-swapped preference pairs to completely erase pre-trained name-gender stereotypes.
- Strict Pronoun Directives: Respects explicit user pronoun directives (Female / Male / Non-binary) regardless of name.
- Short-Turn Pacing: Fine-tuned over 500 multi-turn roleplay conversation flows.
- Zero Corporate Assistant Disclaimers: Erases meta-disclaimers ("As an AI...") and Google/Gemma identity text from neural thought weights.
- Downloads last month
- 610
Hardware compatibility
Log In to add your hardware
We're not able to determine the quantization variants.