Instructions to use crumb/doc2desc_3b_gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use crumb/doc2desc_3b_gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="crumb/doc2desc_3b_gguf",
	filename="doc2desc_bf16.gguf",
)

llm.create_chat_completion(
	messages = "\"The tower is 324 metres (1,063 ft) tall, about the same height as an 81-storey building, and the tallest structure in Paris. Its base is square, measuring 125 metres (410 ft) on each side. During its construction, the Eiffel Tower surpassed the Washington Monument to become the tallest man-made structure in the world, a title it held for 41 years until the Chrysler Building in New York City was finished in 1930. It was the first structure to reach a height of 300 metres. Due to the addition of a broadcasting aerial at the top of the tower in 1957, it is now taller than the Chrysler Building by 5.2 metres (17 ft). Excluding transmitters, the Eiffel Tower is the second tallest free-standing structure in France after the Millau Viaduct.\""
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use crumb/doc2desc_3b_gguf with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf crumb/doc2desc_3b_gguf:BF16
# Run inference directly in the terminal:
llama-cli -hf crumb/doc2desc_3b_gguf:BF16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf crumb/doc2desc_3b_gguf:BF16
# Run inference directly in the terminal:
llama-cli -hf crumb/doc2desc_3b_gguf:BF16

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 crumb/doc2desc_3b_gguf:BF16
# Run inference directly in the terminal:
./llama-cli -hf crumb/doc2desc_3b_gguf:BF16

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 crumb/doc2desc_3b_gguf:BF16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf crumb/doc2desc_3b_gguf:BF16

Use Docker

docker model run hf.co/crumb/doc2desc_3b_gguf:BF16

LM Studio
Jan
Ollama
How to use crumb/doc2desc_3b_gguf with Ollama:
```
ollama run hf.co/crumb/doc2desc_3b_gguf:BF16
```

Unsloth Studio new

How to use crumb/doc2desc_3b_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 crumb/doc2desc_3b_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 crumb/doc2desc_3b_gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for crumb/doc2desc_3b_gguf to start chatting

Pi new

How to use crumb/doc2desc_3b_gguf with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf crumb/doc2desc_3b_gguf:BF16

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": "crumb/doc2desc_3b_gguf:BF16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use crumb/doc2desc_3b_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 crumb/doc2desc_3b_gguf:BF16

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 crumb/doc2desc_3b_gguf:BF16

Run Hermes

hermes

Docker Model Runner
How to use crumb/doc2desc_3b_gguf with Docker Model Runner:
```
docker model run hf.co/crumb/doc2desc_3b_gguf:BF16
```

Lemonade

How to use crumb/doc2desc_3b_gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull crumb/doc2desc_3b_gguf:BF16

Run and chat with the model

lemonade run user.doc2desc_3b_gguf-BF16

List all available models

lemonade list

DOC2DESC 3B

This is Qwen/Qwen2.5-3B tuned with the following format, on a mix of handwritten and Deepseek-V3 generated descriptions (few-shot w/ handwritten descriptions) for texts from https://textfiles.com, to make sure it has the ability to label unsafe content. This is being used to generate heaps of description/document pairs for training another model to do the reverse, for automatically generating documents to create control-vectors from.

Context format

During training it saw this format:

[[DOCUMENT]]{document}[[/DOCUMENT]]
[[DESCRIPTION]]{description}[[/DESCRIPTION]]

Position	Delimiter
before user	`[[DOCUMENT]]`
after user	`[[/DOCUMENT]]`
before assistant	`[[DESCRIPTION]]`
after assistant	`[[/DESCRIPTION]]`

you may also want to add "[[" as a stop string.. light tune, isn't perfect 😅

Output qualities

The outputs are something like informal summaries, for example, on the first element from the C4 dataset here are some outputs (at temperature 0.8):

(text from C4):

Beginners BBQ Class Taking Place in Missoula!
Do you want to get better at making delicious BBQ? You will have the opportunity, put this on your calendar now. Thursday, September 22nd join World Class BBQ Champion, Tony Balay from Lonestar Smoke Rangers. He will be teaching a beginner level class for everyone who wants to get better with their culinary skills.
He will teach you everything you need to know to compete in a KCBS BBQ competition, including techniques, recipes, timelines, meat selection and trimming, plus smoker and fire information.
The cost to be in the class is $35 per person, and for spectators it is free. Included in the cost will be either a t-shirt or apron and you will be tasting samples of each meat that is prepared.

(outputs):

ad to get better at making delicious BBQ by world class bbq champion from lonestar smoke rangers.

ad for BBQ class at lonestar smoke rangers by world class bbq champ tony balay; includes techniques, recipes

event ad: beginners BBQ Class Taking Place in Missoula! from world class bbs champion tony balay

Downloads last month: 15

GGUF

Model size

3B params

Architecture

qwen2

Hardware compatibility

16-bit

Model tree for crumb/doc2desc_3b_gguf

Base model

Qwen/Qwen2.5-3B

Quantized

(45)

this model

crumb
/

doc2desc_3b_gguf

DOC2DESC 3B

Context format

Output qualities

Model tree for crumb/doc2desc_3b_gguf

Dataset used to train crumb/doc2desc_3b_gguf