Instructions to use datasysdev/ann-sparseattention with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use datasysdev/ann-sparseattention with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("datasysdev/ann-sparseattention", dtype="auto")

llama-cpp-python

How to use datasysdev/ann-sparseattention with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="datasysdev/ann-sparseattention",
	filename="gguf/Qwen3-4B-Instruct-2507-F16-ann-6layer-k128-v2.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use datasysdev/ann-sparseattention 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 datasysdev/ann-sparseattention:F16
# Run inference directly in the terminal:
llama cli -hf datasysdev/ann-sparseattention:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf datasysdev/ann-sparseattention:F16
# Run inference directly in the terminal:
llama cli -hf datasysdev/ann-sparseattention:F16

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 datasysdev/ann-sparseattention:F16
# Run inference directly in the terminal:
./llama-cli -hf datasysdev/ann-sparseattention:F16

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 datasysdev/ann-sparseattention:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf datasysdev/ann-sparseattention:F16

Use Docker

docker model run hf.co/datasysdev/ann-sparseattention:F16

LM Studio
Jan
Ollama
How to use datasysdev/ann-sparseattention with Ollama:
```
ollama run hf.co/datasysdev/ann-sparseattention:F16
```

Unsloth Studio

How to use datasysdev/ann-sparseattention 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 datasysdev/ann-sparseattention 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 datasysdev/ann-sparseattention to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for datasysdev/ann-sparseattention to start chatting

How to use datasysdev/ann-sparseattention with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf datasysdev/ann-sparseattention:F16

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "datasysdev/ann-sparseattention:F16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use datasysdev/ann-sparseattention with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf datasysdev/ann-sparseattention:F16

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default datasysdev/ann-sparseattention:F16

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use datasysdev/ann-sparseattention with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf datasysdev/ann-sparseattention:F16

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "datasysdev/ann-sparseattention:F16" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Docker Model Runner
How to use datasysdev/ann-sparseattention with Docker Model Runner:
```
docker model run hf.co/datasysdev/ann-sparseattention:F16
```

Lemonade

How to use datasysdev/ann-sparseattention with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull datasysdev/ann-sparseattention:F16

Run and chat with the model

lemonade run user.ann-sparseattention-F16

List all available models

lemonade list

datasysdev commited on May 9

Commit

f5d4c18

verified ·

1 Parent(s): b1978ad

Update model card with runtime GGUF links

Browse files

Files changed (1) hide show

README.md +23 -0

README.md CHANGED Viewed

@@ -23,6 +23,29 @@ retrieved native KV vectors.
 This is a research prototype, not a production sparse-attention runtime.
 ## Current status
 Validated clean pilot:

 This is a research prototype, not a production sparse-attention runtime.
+## Extremely preliminary llama.cpp runtime GGUFs
+Merged ANN GGUFs from the llama.cpp runtime branch are available under
+[`gguf/`](https://huggingface.co/datasysdev/ann-sparseattention/tree/main/gguf):
+| variant | hosted file | intended use |
+|---|---|---|
+| 6-layer pilot | [`Qwen3-4B-Instruct-2507-F16-ann-6layer-k128-v2.gguf`](https://huggingface.co/datasysdev/ann-sparseattention/blob/main/gguf/Qwen3-4B-Instruct-2507-F16-ann-6layer-k128-v2.gguf) | best strict HNSW password-recall behavior so far |
+| all32 reserved-edge | [`Qwen3-4B-Instruct-2507-F16-ann-all32-k128-v2.gguf`](https://huggingface.co/datasysdev/ann-sparseattention/blob/main/gguf/Qwen3-4B-Instruct-2507-F16-ann-all32-k128-v2.gguf) | strongest broad-layer exact-runtime speed/quality candidate |
+| all36 full substitution | [`Qwen3-4B-Instruct-2507-F16-ann-all36-k128-v2.gguf`](https://huggingface.co/datasysdev/ann-sparseattention/blob/main/gguf/Qwen3-4B-Instruct-2507-F16-ann-all36-k128-v2.gguf) | full-substitution stress test; visibly weaker quality |
+The corresponding runtime branch is
+[`feat/llama-ann-runtime`](https://github.com/unixsysdev/ann-sparseattention/tree/feat/llama-ann-runtime).
+That branch intentionally contains only the runtime snapshot and its logs.
+These GGUFs are extremely preliminary. The current llama.cpp integration is
+useful for reproducing CPU/ROCm correctness and early speed tests, but it is
+not a production sparse-attention runtime. The HNSW path performs real
+approximate ANN candidate selection, but currently rebuilds indices during
+decode; it validates behavior rather than final latency. The exact top-K path
+is the current correctness oracle and showed an early 33.6k-context speed
+signal for all32, but prompt quality tests remain synthetic and incomplete.
 ## Current status
 Validated clean pilot: