Instructions to use mradermacher/DASD-4B-Thinking-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mradermacher/DASD-4B-Thinking-GGUF with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("mradermacher/DASD-4B-Thinking-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use mradermacher/DASD-4B-Thinking-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 mradermacher/DASD-4B-Thinking-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf mradermacher/DASD-4B-Thinking-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 mradermacher/DASD-4B-Thinking-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf mradermacher/DASD-4B-Thinking-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 mradermacher/DASD-4B-Thinking-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf mradermacher/DASD-4B-Thinking-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 mradermacher/DASD-4B-Thinking-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf mradermacher/DASD-4B-Thinking-GGUF:Q4_K_M

Use Docker

docker model run hf.co/mradermacher/DASD-4B-Thinking-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use mradermacher/DASD-4B-Thinking-GGUF with Ollama:
```
ollama run hf.co/mradermacher/DASD-4B-Thinking-GGUF:Q4_K_M
```
Unsloth Desktop

How to use mradermacher/DASD-4B-Thinking-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf mradermacher/DASD-4B-Thinking-GGUF:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "mradermacher/DASD-4B-Thinking-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use mradermacher/DASD-4B-Thinking-GGUF with Docker Model Runner:
```
docker model run hf.co/mradermacher/DASD-4B-Thinking-GGUF:Q4_K_M
```

Lemonade

How to use mradermacher/DASD-4B-Thinking-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull mradermacher/DASD-4B-Thinking-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.DASD-4B-Thinking-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use mradermacher/DASD-4B-Thinking-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf mradermacher/DASD-4B-Thinking-GGUF:Q4_K_M

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 mradermacher/DASD-4B-Thinking-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use mradermacher/DASD-4B-Thinking-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf mradermacher/DASD-4B-Thinking-GGUF:Q4_K_M

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 "mradermacher/DASD-4B-Thinking-GGUF:Q4_K_M" \
  --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"

mradermacher commited on Jan 15

Commit

844c677

verified ·

1 Parent(s): cabfef3

uploaded from back

Browse files

Files changed (13) hide show

.gitattributes +12 -0
DASD-4B-Thinking.IQ4_XS.gguf +3 -0
DASD-4B-Thinking.Q2_K.gguf +3 -0
DASD-4B-Thinking.Q3_K_L.gguf +3 -0
DASD-4B-Thinking.Q3_K_M.gguf +3 -0
DASD-4B-Thinking.Q3_K_S.gguf +3 -0
DASD-4B-Thinking.Q4_K_M.gguf +3 -0
DASD-4B-Thinking.Q4_K_S.gguf +3 -0
DASD-4B-Thinking.Q5_K_M.gguf +3 -0
DASD-4B-Thinking.Q5_K_S.gguf +3 -0
DASD-4B-Thinking.Q6_K.gguf +3 -0
DASD-4B-Thinking.Q8_0.gguf +3 -0
DASD-4B-Thinking.f16.gguf +3 -0

@@ -33,3 +33,15 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text

 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+DASD-4B-Thinking.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
+DASD-4B-Thinking.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+DASD-4B-Thinking.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+DASD-4B-Thinking.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+DASD-4B-Thinking.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+DASD-4B-Thinking.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+DASD-4B-Thinking.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+DASD-4B-Thinking.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+DASD-4B-Thinking.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+DASD-4B-Thinking.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+DASD-4B-Thinking.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+DASD-4B-Thinking.f16.gguf filter=lfs diff=lfs merge=lfs -text

+version https://git-lfs.github.com/spec/v1
+oid sha256:c71753a15d84240ac083fca1855ceba19f8c59eac203f67822f9508287171735
+size 2286316896

+version https://git-lfs.github.com/spec/v1
+oid sha256:76806899fc5037d74716b7bce820d7c87746f1f2c1808a18f0e9a26bf7c80532
+size 1669500256

+version https://git-lfs.github.com/spec/v1
+oid sha256:14a37f4ffb3d8e5228a9be3041f0a176d1980aaba87161942d93dd092d69db47
+size 2239786336

+version https://git-lfs.github.com/spec/v1
+oid sha256:309860c903f33bd8314e5c88c43b9e0fd7c9206e0df73e9eb24ad7bf3a981b6f
+size 2075618656

+version https://git-lfs.github.com/spec/v1
+oid sha256:858e4735867ad81f13da71080155925276842f7066b5b87ea1ad5ea12481cac7
+size 1886997856

+version https://git-lfs.github.com/spec/v1
+oid sha256:11e95b9455d84dff393e43d161c238ab65ded003bc85c3f29b628e2461c8879d
+size 2497281376

+version https://git-lfs.github.com/spec/v1
+oid sha256:8804b4e79cd47933eb377ff6b259f599e8fd7dc0729e9c92aa3727c513b3677e
+size 2383310176

+version https://git-lfs.github.com/spec/v1
+oid sha256:7a92987eeeac8d241ef5e832eb7d41bc71077f0714a72acc91ab055506658e2f
+size 2889514336

+version https://git-lfs.github.com/spec/v1
+oid sha256:c2cc6cc589cb5a0f5b9d372c6cefcef4de84c51d541c13f35394c623b14faeae
+size 2823712096

+version https://git-lfs.github.com/spec/v1
+oid sha256:d2ef3cb68edc095f941199debe9e16df29680f23a1dc352b3afbfa4a63fa5721
+size 3306261856

	@@ -0,0 +1,3 @@

	@@ -0,0 +1,3 @@

	@@ -0,0 +1,3 @@

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:2c8c0aa94dd1e4bd710440c4256cb96a48d2f3954127db8e2a65341e7fd2e265
+size 4280405856

+version https://git-lfs.github.com/spec/v1
+oid sha256:8dc7f12bcd1015e1877fc39592c4924edc01432d436f2733a5e4a451f39905a5
+size 8051285856