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

llama.cpp

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

Install from brew

brew install llama.cpp
# 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

Install from WinGet (Windows)

winget install llama.cpp
# 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

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-server -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-server -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

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 23 days ago

Commit

95766a4

verified ·

1 Parent(s): e0267d4

Update checkpoints_all32_d128_block_reserve_0_1_2_35/search_step_1000.compare_retrieval.json

Browse files

Files changed (1) hide show

checkpoints_all32_d128_block_reserve_0_1_2_35/search_step_1000.compare_retrieval.json +159 -0

checkpoints_all32_d128_block_reserve_0_1_2_35/search_step_1000.compare_retrieval.json ADDED Viewed

	@@ -0,0 +1,159 @@

+{
+  "model": "Qwen/Qwen3-4B-Instruct-2507",
+  "ckpt": "/tmp/checkpoints_all32_d128_block_reserve_0_1_2_35/search_step_1000.pt",
+  "by_K": {
+    "128": {
+      "raw_qk": {
+        "per_layer": {
+          "3": 0.9387637376785278,
+          "4": 0.9440614581108093,
+          "5": 0.96429443359375,
+          "6": 0.9560344219207764,
+          "7": 0.9818542897701263,
+          "8": 0.9707900285720825,
+          "9": 0.9587394297122955,
+          "10": 0.9742867350578308,
+          "11": 0.9763059914112091,
+          "12": 0.9611693322658539,
+          "13": 0.9707654714584351,
+          "14": 0.9733296930789948,
+          "15": 0.9675203263759613,
+          "16": 0.9556995928287506,
+          "17": 0.9593449831008911,
+          "18": 0.9652450382709503,
+          "19": 0.9612957835197449,
+          "20": 0.9591256380081177,
+          "21": 0.9657162129878998,
+          "22": 0.962736189365387,
+          "23": 0.9788879752159119,
+          "24": 0.9710511267185211,
+          "25": 0.9860879778862,
+          "26": 0.9775076508522034,
+          "27": 0.977691113948822,
+          "28": 0.9794201850891113,
+          "29": 0.9821525514125824,
+          "30": 0.9875719547271729,
+          "31": 0.9842455685138702,
+          "32": 0.9791028797626495,
+          "33": 0.9772593379020691,
+          "34": 0.9759000241756439
+        },
+        "avg": 0.969498660415411
+      },
+      "learned": {
+        "per_layer": {
+          "3": 0.9244755506515503,
+          "4": 0.9368151426315308,
+          "5": 0.9484244585037231,
+          "6": 0.939052551984787,
+          "7": 0.9830892086029053,
+          "8": 0.9710568785667419,
+          "9": 0.9766820967197418,
+          "10": 0.9707906544208527,
+          "11": 0.9762083292007446,
+          "12": 0.9698493182659149,
+          "13": 0.9710436761379242,
+          "14": 0.9732040166854858,
+          "15": 0.972749650478363,
+          "16": 0.9609748125076294,
+          "17": 0.9665586054325104,
+          "18": 0.9724838137626648,
+          "19": 0.9691765010356903,
+          "20": 0.9757413268089294,
+          "21": 0.9799380302429199,
+          "22": 0.9698161482810974,
+          "23": 0.9849565327167511,
+          "24": 0.9785935282707214,
+          "25": 0.9885723888874054,
+          "26": 0.9855012595653534,
+          "27": 0.9834729731082916,
+          "28": 0.9848337769508362,
+          "29": 0.98735311627388,
+          "30": 0.9873296022415161,
+          "31": 0.9829616844654083,
+          "32": 0.9795172214508057,
+          "33": 0.9666652083396912,
+          "34": 0.9603306651115417
+        },
+        "avg": 0.9711943352594972
+      }
+    },
+    "256": {
+      "raw_qk": {
+        "per_layer": {
+          "3": 0.9856403172016144,
+          "4": 0.9863723814487457,
+          "5": 0.9927175343036652,
+          "6": 0.9899796843528748,
+          "7": 0.9961064755916595,
+          "8": 0.9944310188293457,
+          "9": 0.9924624264240265,
+          "10": 0.9945598244667053,
+          "11": 0.9956617951393127,
+          "12": 0.9914700388908386,
+          "13": 0.9947893917560577,
+          "14": 0.9956192076206207,
+          "15": 0.9947386384010315,
+          "16": 0.9918601512908936,
+          "17": 0.9932802319526672,
+          "18": 0.994801938533783,
+          "19": 0.9929636716842651,
+          "20": 0.9928486049175262,
+          "21": 0.9940518736839294,
+          "22": 0.9925838708877563,
+          "23": 0.9956205189228058,
+          "24": 0.9944405257701874,
+          "25": 0.99702388048172,
+          "26": 0.9963724911212921,
+          "27": 0.9952751994132996,
+          "28": 0.9952269494533539,
+          "29": 0.9970046579837799,
+          "30": 0.9976439476013184,
+          "31": 0.9967932999134064,
+          "32": 0.9949435591697693,
+          "33": 0.9954463541507721,
+          "34": 0.9949491024017334
+        },
+        "avg": 0.9939899863675237
+      },
+      "learned": {
+        "per_layer": {
+          "3": 0.9771333336830139,
+          "4": 0.9823162257671356,
+          "5": 0.9861737489700317,
+          "6": 0.9809035956859589,
+          "7": 0.9963934123516083,
+          "8": 0.9932794272899628,
+          "9": 0.9953930974006653,
+          "10": 0.9923880398273468,
+          "11": 0.994959145784378,
+          "12": 0.9928728640079498,
+          "13": 0.9931342303752899,
+          "14": 0.9937034547328949,
+          "15": 0.9947409331798553,
+          "16": 0.9912147521972656,
+          "17": 0.99372997879982,
+          "18": 0.9954918026924133,
+          "19": 0.9936331808567047,
+          "20": 0.9959999024868011,
+          "21": 0.99661585688591,
+          "22": 0.993903785943985,
+          "23": 0.9974819421768188,
+          "24": 0.9961839318275452,
+          "25": 0.9976893067359924,
+          "26": 0.9971556663513184,
+          "27": 0.9965596199035645,
+          "28": 0.9969134330749512,
+          "29": 0.9974974989891052,
+          "30": 0.9971778690814972,
+          "31": 0.9964099228382111,
+          "32": 0.9948908686637878,
+          "33": 0.9909328520298004,
+          "34": 0.98967644572258
+        },
+        "avg": 0.9932046914473176
+      }
+    }
+  },
+  "learned_over_raw_K128": 1.0017490223693137
+}