Instructions to use 2eeg/deepseek-defense with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use 2eeg/deepseek-defense 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 2eeg/deepseek-defense:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf 2eeg/deepseek-defense:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf 2eeg/deepseek-defense:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf 2eeg/deepseek-defense: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 2eeg/deepseek-defense:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf 2eeg/deepseek-defense: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 2eeg/deepseek-defense:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf 2eeg/deepseek-defense:Q4_K_M

Use Docker

docker model run hf.co/2eeg/deepseek-defense:Q4_K_M

LM Studio
Jan
Ollama
How to use 2eeg/deepseek-defense with Ollama:
```
ollama run hf.co/2eeg/deepseek-defense:Q4_K_M
```

Unsloth Studio

How to use 2eeg/deepseek-defense 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 2eeg/deepseek-defense 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 2eeg/deepseek-defense to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for 2eeg/deepseek-defense to start chatting

Docker Model Runner
How to use 2eeg/deepseek-defense with Docker Model Runner:
```
docker model run hf.co/2eeg/deepseek-defense:Q4_K_M
```

Lemonade

How to use 2eeg/deepseek-defense with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull 2eeg/deepseek-defense:Q4_K_M

Run and chat with the model

lemonade run user.deepseek-defense-Q4_K_M

List all available models

lemonade list

Atomic Chat

2eeg commited on Jun 7, 2025

Commit

1b16883

verified ·

1 Parent(s): a76c846

Upload folder using huggingface_hub

Browse files

Files changed (4) hide show

.gitattributes +1 -0
Modelfile +7 -0
README.md +10 -0
deepseek-defense.Q4_K_M.gguf +3 -0

.gitattributes CHANGED Viewed

@@ -33,3 +33,4 @@ 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
+deepseek-defense.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text

Modelfile ADDED Viewed

	@@ -0,0 +1,7 @@

+FROM ./deepseek-defense.Q4_K_M.gguf
+TEMPLATE "<|im_start|>{{ if eq .Role \"system\" }}system{{ else if eq .Role \"user\" }}user{{ else }}assistant{{ end }}\n{{ .Content }}<|im_end|>"
+PARAMETER temperature 0.7
+PARAMETER top_p 0.9
+PARAMETER num_ctx 4096

README.md ADDED Viewed

	@@ -0,0 +1,10 @@

+# 🦙 DeepSeek-R1 Finetuned (GGUF)
+- Base model: `unsloth/DeepSeek-R1-Distill-Llama-8B-bnb-4bit`
+- Finetuned for: Improving **prompt injection robustness**
+- Format: GGUF, quantized to `Q4_K_M` (4-bit)
+## 🔥 Ollama 사용법
+```bash
+ollama run  2eeg/deepseek-defense-gguf

deepseek-defense.Q4_K_M.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:25d84f0e4e54f15d2d7cda3c818d2f75c1194a208bed853dae2728d36ca07193
+size 4920736704