Instructions to use RichardErkhov/GroNLP_-_gpt2-small-dutch-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RichardErkhov/GroNLP_-_gpt2-small-dutch-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="RichardErkhov/GroNLP_-_gpt2-small-dutch-gguf",
	filename="gpt2-small-dutch.IQ3_M.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use RichardErkhov/GroNLP_-_gpt2-small-dutch-gguf with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf RichardErkhov/GroNLP_-_gpt2-small-dutch-gguf:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf RichardErkhov/GroNLP_-_gpt2-small-dutch-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 RichardErkhov/GroNLP_-_gpt2-small-dutch-gguf:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf RichardErkhov/GroNLP_-_gpt2-small-dutch-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 RichardErkhov/GroNLP_-_gpt2-small-dutch-gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf RichardErkhov/GroNLP_-_gpt2-small-dutch-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 RichardErkhov/GroNLP_-_gpt2-small-dutch-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf RichardErkhov/GroNLP_-_gpt2-small-dutch-gguf:Q4_K_M

Use Docker

docker model run hf.co/RichardErkhov/GroNLP_-_gpt2-small-dutch-gguf:Q4_K_M

LM Studio
Jan
Ollama
How to use RichardErkhov/GroNLP_-_gpt2-small-dutch-gguf with Ollama:
```
ollama run hf.co/RichardErkhov/GroNLP_-_gpt2-small-dutch-gguf:Q4_K_M
```

Unsloth Studio

How to use RichardErkhov/GroNLP_-_gpt2-small-dutch-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 RichardErkhov/GroNLP_-_gpt2-small-dutch-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 RichardErkhov/GroNLP_-_gpt2-small-dutch-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for RichardErkhov/GroNLP_-_gpt2-small-dutch-gguf to start chatting

Atomic Chat new
Docker Model Runner
How to use RichardErkhov/GroNLP_-_gpt2-small-dutch-gguf with Docker Model Runner:
```
docker model run hf.co/RichardErkhov/GroNLP_-_gpt2-small-dutch-gguf:Q4_K_M
```

Lemonade

How to use RichardErkhov/GroNLP_-_gpt2-small-dutch-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull RichardErkhov/GroNLP_-_gpt2-small-dutch-gguf:Q4_K_M

Run and chat with the model

lemonade run user.GroNLP_-_gpt2-small-dutch-gguf-Q4_K_M

List all available models

lemonade list

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

Quantization made by Richard Erkhov.

Github

Discord

Request more models

gpt2-small-dutch - GGUF

Model creator: https://huggingface.co/GroNLP/
Original model: https://huggingface.co/GroNLP/gpt2-small-dutch/

Name	Quant method	Size
gpt2-small-dutch.Q2_K.gguf	Q2_K	0.07GB
gpt2-small-dutch.IQ3_XS.gguf	IQ3_XS	0.07GB
gpt2-small-dutch.IQ3_S.gguf	IQ3_S	0.07GB
gpt2-small-dutch.Q3_K_S.gguf	Q3_K_S	0.07GB
gpt2-small-dutch.IQ3_M.gguf	IQ3_M	0.08GB
gpt2-small-dutch.Q3_K.gguf	Q3_K	0.08GB
gpt2-small-dutch.Q3_K_M.gguf	Q3_K_M	0.08GB
gpt2-small-dutch.Q3_K_L.gguf	Q3_K_L	0.08GB
gpt2-small-dutch.IQ4_XS.gguf	IQ4_XS	0.08GB
gpt2-small-dutch.Q4_0.gguf	Q4_0	0.09GB
gpt2-small-dutch.IQ4_NL.gguf	IQ4_NL	0.09GB
gpt2-small-dutch.Q4_K_S.gguf	Q4_K_S	0.09GB
gpt2-small-dutch.Q4_K.gguf	Q4_K	0.09GB
gpt2-small-dutch.Q4_K_M.gguf	Q4_K_M	0.09GB
gpt2-small-dutch.Q4_1.gguf	Q4_1	0.09GB
gpt2-small-dutch.Q5_0.gguf	Q5_0	0.1GB
gpt2-small-dutch.Q5_K_S.gguf	Q5_K_S	0.1GB
gpt2-small-dutch.Q5_K.gguf	Q5_K	0.11GB
gpt2-small-dutch.Q5_K_M.gguf	Q5_K_M	0.11GB
gpt2-small-dutch.Q5_1.gguf	Q5_1	0.11GB
gpt2-small-dutch.Q6_K.gguf	Q6_K	0.12GB

Original model description:

language: nl tags: - adaption - recycled - gpt2-small pipeline_tag: text-generation

GPT-2 recycled for Dutch (small)

Wietse de Vries • Malvina Nissim

Model description

This model is based on the small OpenAI GPT-2 (gpt2) model.

For details, check out our paper on arXiv and the code on Github.

Related models

Dutch

gpt2-small-dutch-embeddings: Small model size with only retrained lexical embeddings.
gpt2-small-dutch: Small model size with retrained lexical embeddings and additional fine-tuning of the full model. (Recommended)
gpt2-medium-dutch-embeddings: Medium model size with only retrained lexical embeddings.

Italian

gpt2-small-italian-embeddings: Small model size with only retrained lexical embeddings.
gpt2-small-italian: Small model size with retrained lexical embeddings and additional fine-tuning of the full model. (Recommended)
gpt2-medium-italian-embeddings: Medium model size with only retrained lexical embeddings.

How to use

from transformers import pipeline

pipe = pipeline("text-generation", model="GroNLP/gpt2-small-dutch")

from transformers import AutoTokenizer, AutoModel, TFAutoModel

tokenizer = AutoTokenizer.from_pretrained("GroNLP/gpt2-small-dutch")
model = AutoModel.from_pretrained("GroNLP/gpt2-small-dutch")  # PyTorch
model = TFAutoModel.from_pretrained("GroNLP/gpt2-small-dutch")  # Tensorflow

BibTeX entry

@misc{devries2020good,
      title={As good as new. How to successfully recycle English GPT-2 to make models for other languages}, 
      author={Wietse de Vries and Malvina Nissim},
      year={2020},
      eprint={2012.05628},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}

Downloads last month: 66

GGUF

Model size

0.1B params

Architecture

gpt2

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

Inference Providers NEW

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

Paper for RichardErkhov/GroNLP_-_gpt2-small-dutch-gguf

As Good as New. How to Successfully Recycle English GPT-2 to Make Models for Other Languages

Paper • 2012.05628 • Published Dec 10, 2020