Instructions to use Forceless/DeepPresenter-9B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Forceless/DeepPresenter-9B-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Forceless/DeepPresenter-9B-GGUF",
	filename="DeepPresenter-9B-GGUF-Q4_K_M.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 Forceless/DeepPresenter-9B-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Forceless/DeepPresenter-9B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Forceless/DeepPresenter-9B-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Forceless/DeepPresenter-9B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Forceless/DeepPresenter-9B-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 Forceless/DeepPresenter-9B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Forceless/DeepPresenter-9B-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 Forceless/DeepPresenter-9B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Forceless/DeepPresenter-9B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/Forceless/DeepPresenter-9B-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use Forceless/DeepPresenter-9B-GGUF with Ollama:
```
ollama run hf.co/Forceless/DeepPresenter-9B-GGUF:Q4_K_M
```

Unsloth Studio

How to use Forceless/DeepPresenter-9B-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 Forceless/DeepPresenter-9B-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 Forceless/DeepPresenter-9B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Forceless/DeepPresenter-9B-GGUF to start chatting

How to use Forceless/DeepPresenter-9B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Forceless/DeepPresenter-9B-GGUF:Q4_K_M

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": "Forceless/DeepPresenter-9B-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Forceless/DeepPresenter-9B-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Forceless/DeepPresenter-9B-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 Forceless/DeepPresenter-9B-GGUF:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use Forceless/DeepPresenter-9B-GGUF with Docker Model Runner:
```
docker model run hf.co/Forceless/DeepPresenter-9B-GGUF:Q4_K_M
```

Lemonade

How to use Forceless/DeepPresenter-9B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Forceless/DeepPresenter-9B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.DeepPresenter-9B-GGUF-Q4_K_M

List all available models

lemonade list

nielsr HF Staff commited on Mar 15

Commit

e4baaee

verified ·

1 Parent(s): 40bf39f

Add pipeline tag and improve model card documentation

Browse files

Hi! I'm Niels, part of the community science team at Hugging Face.

I've opened this PR to enhance the model card for DeepPresenter-9B. My changes include:
- Adding the `text-generation` pipeline tag to the metadata for better discoverability.
- Improving the model overview with details from the associated research paper.
- Ensuring the official GitHub repository and paper are properly linked.
- Adding the BibTeX citation for the paper.

This documentation helps users better understand and cite your work!

Files changed (1) hide show

README.md +29 -5

README.md CHANGED Viewed

@@ -1,30 +1,54 @@
 ---
-license: mit
 base_model:
 - Forceless/DeepPresenter-9B
 ---
 > This is a quantized version of the model for lightweight deployment on edge devices such as Macs.
 # DeepPresenter-9B
-**Project**: https://github.com/icip-cas/PPTAgent
-**Paper**: https://arxiv.org/abs/2602.22839
 ## Model Overview
 **DeepPresenter-9B** is a 9B-parameter language model designed for **automatic presentation generation**. It serves as the core model in the **DeepPresenter** framework, enabling agentic workflows that generate structured slide presentations from natural language instructions.
 ## Usage
-DeepPresenter-9B is intended to be used with the **PPTAgent framework** for full presentation generation:
 ```bash
 uvx pptagent onboard
 uvx pptagent generate "Single Page with Title: Hello World" -o hello.pptx
 ```
 ## Performance
-![image](https://cdn-uploads.huggingface.co/production/uploads/64380d17819f3ab20d17595b/PZgEPAPir2ygRvxtqtXnx.png)

 ---
 base_model:
 - Forceless/DeepPresenter-9B
+license: mit
+pipeline_tag: text-generation
 ---
 > This is a quantized version of the model for lightweight deployment on edge devices such as Macs.
 # DeepPresenter-9B
+**Project**: [https://github.com/icip-cas/PPTAgent](https://github.com/icip-cas/PPTAgent)
+**Paper**: [DeepPresenter: Environment-Grounded Reflection for Agentic Presentation Generation](https://huggingface.co/papers/2602.22839)
 ## Model Overview
 **DeepPresenter-9B** is a 9B-parameter language model designed for **automatic presentation generation**. It serves as the core model in the **DeepPresenter** framework, enabling agentic workflows that generate structured slide presentations from natural language instructions.
+DeepPresenter is an agentic framework that adapts to diverse user intents and enables effective feedback-driven refinement. Unlike existing agents that rely on self-reflection over internal signals, DeepPresenter uses environment-grounded reflection to condition the generation process on perceptual artifact states (e.g., rendered slides), allowing it to identify and correct presentation-specific issues during execution.
 ## Usage
+DeepPresenter-9B is intended to be used with the **PPTAgent framework** for full presentation generation. You can use the command-line interface provided by the project:
 ```bash
+# Install `uv` for package management
+curl -LsSf https://astral.sh/uv/install.sh | sh
+# Interactive configuration (first time)
 uvx pptagent onboard
+# Generate presentation
 uvx pptagent generate "Single Page with Title: Hello World" -o hello.pptx
 ```
 ## Performance
+![image](https://cdn-uploads.huggingface.co/production/uploads/64380d17819f3ab20d17595b/PZgEPAPir2ygRvxtqtXnx.png)
+## Citation
+If you find this project helpful, please use the following to cite it:
+```bibtex
+@misc{zheng2026deeppresenterenvironmentgroundedreflectionagentic,
+      title={DeepPresenter: Environment-Grounded Reflection for Agentic Presentation Generation},
+      author={Hao Zheng and Guozhao Mo and Xinru Yan and Qianhao Yuan and Wenkai Zhang and Xuanang Chen and Yaojie Lu and Hongyu Lin and Xianpei Han and Le Sun},
+      year={2026},
+      eprint={2602.22839},
+      archivePrefix={arXiv},
+      primaryClass={cs.AI},
+      url={https://arxiv.org/abs/2602.22839},
+}
+```