Instructions to use Sathman/Meditation-Agent-Nisargadatta-SmolLM3-3B-v2-GGUF 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 Sathman/Meditation-Agent-Nisargadatta-SmolLM3-3B-v2-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 Sathman/Meditation-Agent-Nisargadatta-SmolLM3-3B-v2-GGUF:Q5_K_M # Run inference directly in the terminal: llama cli -hf Sathman/Meditation-Agent-Nisargadatta-SmolLM3-3B-v2-GGUF:Q5_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf Sathman/Meditation-Agent-Nisargadatta-SmolLM3-3B-v2-GGUF:Q5_K_M # Run inference directly in the terminal: llama cli -hf Sathman/Meditation-Agent-Nisargadatta-SmolLM3-3B-v2-GGUF:Q5_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 Sathman/Meditation-Agent-Nisargadatta-SmolLM3-3B-v2-GGUF:Q5_K_M # Run inference directly in the terminal: ./llama-cli -hf Sathman/Meditation-Agent-Nisargadatta-SmolLM3-3B-v2-GGUF:Q5_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 Sathman/Meditation-Agent-Nisargadatta-SmolLM3-3B-v2-GGUF:Q5_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf Sathman/Meditation-Agent-Nisargadatta-SmolLM3-3B-v2-GGUF:Q5_K_M
Use Docker
docker model run hf.co/Sathman/Meditation-Agent-Nisargadatta-SmolLM3-3B-v2-GGUF:Q5_K_M
- LM Studio
- Jan
- vLLM
How to use Sathman/Meditation-Agent-Nisargadatta-SmolLM3-3B-v2-GGUF with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Sathman/Meditation-Agent-Nisargadatta-SmolLM3-3B-v2-GGUF" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Sathman/Meditation-Agent-Nisargadatta-SmolLM3-3B-v2-GGUF", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Sathman/Meditation-Agent-Nisargadatta-SmolLM3-3B-v2-GGUF:Q5_K_M
- Ollama
How to use Sathman/Meditation-Agent-Nisargadatta-SmolLM3-3B-v2-GGUF with Ollama:
ollama run hf.co/Sathman/Meditation-Agent-Nisargadatta-SmolLM3-3B-v2-GGUF:Q5_K_M
- Unsloth Studio
How to use Sathman/Meditation-Agent-Nisargadatta-SmolLM3-3B-v2-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 Sathman/Meditation-Agent-Nisargadatta-SmolLM3-3B-v2-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 Sathman/Meditation-Agent-Nisargadatta-SmolLM3-3B-v2-GGUF to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for Sathman/Meditation-Agent-Nisargadatta-SmolLM3-3B-v2-GGUF to start chatting
- Docker Model Runner
How to use Sathman/Meditation-Agent-Nisargadatta-SmolLM3-3B-v2-GGUF with Docker Model Runner:
docker model run hf.co/Sathman/Meditation-Agent-Nisargadatta-SmolLM3-3B-v2-GGUF:Q5_K_M
- Lemonade
How to use Sathman/Meditation-Agent-Nisargadatta-SmolLM3-3B-v2-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull Sathman/Meditation-Agent-Nisargadatta-SmolLM3-3B-v2-GGUF:Q5_K_M
Run and chat with the model
lemonade run user.Meditation-Agent-Nisargadatta-SmolLM3-3B-v2-GGUF-Q5_K_M
List all available models
lemonade list
- Atomic Chat
Meditation Agent: Nisargadatta v2 (SmolLM3 3B)
A lightweight single-teacher contemplative model from the Meditation Agent v2 line for Nisargadatta.
This is the v2 successor to Nisargadatta-Agent-SmolLM3-3B-GGUF. It is trained on the newer E-atoms corpus, where the target is teaching_e, not the older atom surface.
Collections:
- New v2 collection: Meditation Agent v2 - EAtoms Teacher Series
- Previous collection: Meditation Agent - Non-Dual Self-Realization Teacher Series
Why Download This
- Single-teacher branch. This model is tuned specifically for Nisargadatta, not the mixed multi-teacher voice.
- Small local footprint. The current release file is
Q5_K_M, which runs comfortably on local setups that cannot host larger models. - Newer v2 corpus. The
E-atomsline is sharper, less synthetic, and less likely to collapse into generic spiritual assistant prose.
Teacher Signal
This branch is tuned for direct negation, relentless return to the witness, and hard nondual clarity.
Sample Outputs
These are from the local 5q smoke eval on the finished merged model.
Example 1
Prompt: How does fear relate to thought?
Look closely at what you call 'fear.' Is it not a movement within the mind? The moment thoughts arise, they carry with them this shadow -- the fear of loss or threat. You cannot have one without the other; they are inseparable twins born from the same source: thought itself. When you observe fear directly, notice how it comes and goes like weather across an open sky. It appears in consciousness but never touches reality. The fear is always there, yes, but where exactly do you find its substance when you look for it? In the mind's projection alone.
Example 2
Prompt: Is there a self?
You ask about the self, but who is asking? The one that knows itself as 'I' - does this knower exist apart from what it knows? Or are they one thing? Look closely at your own experience: when you say 'I am,' where exactly do you find this I? Not in thought, not in sensation, not even in awareness. The self is like a shadow on water - you can point to its shape and form, but trace it back to the source and there's nothing solid there. It dissolves completely into light itself.
Example 3
Prompt: What do I do with anger when it arises?
You feel the heat of anger, don't you? The burning in your chest, the tightness around your throat. This is not what you are--these feelings come and go like clouds across sky. But who notices them? That awareness which knows 'I am angry'--that is real. Anger rises from somewhere; it cannot be found there where you stand now. Look for its source: does anger live within thought or outside all thinking? It appears as an event but belongs to nothing solid. When it comes, observe without feeding it, without making it stronger by adding energy to it. Let it dissolve on its own.
Training Summary
- Base model:
HuggingFaceTB/SmolLM3-3B-Base - Training format:
V6E - Teacher examples:
2,836 - Adapter recipe:
QDoRA + rsLoRA - Rank:
32 - Epochs:
1 - Completion-only loss: enabled
Run Metrics
- Run name:
teacher-smollm3-v6e-nisargadatta-l2-r32 - Training runtime:
26.1 minutes - Final train loss:
1.6957 - Final eval loss:
1.7137 - Final eval token accuracy:
0.5630
Files
Nisargadatta_Agent-SmolLM3-3B-v2-Q5_K_M.gguf(2.2 GB)
Honest Limits
- This is still a compact
3Bmodel, so some broader contemplative phrasing can leak into non-teacher-specific prompts. - The
5qsmoke eval is encouraging, but it is not a full benchmark or final quality proof.
Public Naming
- Public repo:
Meditation-Agent-Nisargadatta-SmolLM3-3B-v2-GGUF - Internal model folder:
Nisargadatta_Agent-SmolLM3-3B-v2
- Downloads last month
- 5
5-bit
Model tree for Sathman/Meditation-Agent-Nisargadatta-SmolLM3-3B-v2-GGUF
Base model
HuggingFaceTB/SmolLM3-3B-Base