Instructions to use QuantFactory/diffullama-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use QuantFactory/diffullama-GGUF with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("QuantFactory/diffullama-GGUF", dtype="auto")

llama-cpp-python

How to use QuantFactory/diffullama-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="QuantFactory/diffullama-GGUF",
	filename="diffullama.Q2_K.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use QuantFactory/diffullama-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf QuantFactory/diffullama-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf QuantFactory/diffullama-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 QuantFactory/diffullama-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf QuantFactory/diffullama-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 QuantFactory/diffullama-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf QuantFactory/diffullama-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 QuantFactory/diffullama-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf QuantFactory/diffullama-GGUF:Q4_K_M

Use Docker

docker model run hf.co/QuantFactory/diffullama-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use QuantFactory/diffullama-GGUF with Ollama:
```
ollama run hf.co/QuantFactory/diffullama-GGUF:Q4_K_M
```

Unsloth Studio new

How to use QuantFactory/diffullama-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 QuantFactory/diffullama-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 QuantFactory/diffullama-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

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

Docker Model Runner
How to use QuantFactory/diffullama-GGUF with Docker Model Runner:
```
docker model run hf.co/QuantFactory/diffullama-GGUF:Q4_K_M
```

Lemonade

How to use QuantFactory/diffullama-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull QuantFactory/diffullama-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.diffullama-GGUF-Q4_K_M

List all available models

lemonade list

QuantFactory/diffullama-GGUF

This is quantized version of diffusionfamily/diffullama created using llama.cpp

Original Model Card

diffullama

This model is a fine-tuned version of [llama2].

Model description

Details and model loading can be seen https://github.com/HKUNLP/DiffuLLaMA.

Framework versions

Transformers 4.44.2
Pytorch 2.1.1+cu121
Datasets 2.21.0
Tokenizers 0.19.1

@misc{gong2024scalingdiffusionlanguagemodels,
      title={Scaling Diffusion Language Models via Adaptation from Autoregressive Models}, 
      author={Shansan Gong and Shivam Agarwal and Yizhe Zhang and Jiacheng Ye and Lin Zheng and Mukai Li and Chenxin An and Peilin Zhao and Wei Bi and Jiawei Han and Hao Peng and Lingpeng Kong},
      year={2024},
      eprint={2410.17891},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2410.17891}, 
}

Downloads last month: 266

GGUF

Model size

7B params

Architecture

llama

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for QuantFactory/diffullama-GGUF

Base model

meta-llama/Llama-2-7b-hf

Quantized

(73)

this model

Dataset used to train QuantFactory/diffullama-GGUF

Paper for QuantFactory/diffullama-GGUF

Scaling Diffusion Language Models via Adaptation from Autoregressive Models

Paper • 2410.17891 • Published Oct 23, 2024 • 18