Instructions to use tsunemoto/GEITje-7B-chat-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tsunemoto/GEITje-7B-chat-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="tsunemoto/GEITje-7B-chat-GGUF",
	filename="geitje-7b-chat.Q2_K.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use tsunemoto/GEITje-7B-chat-GGUF 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 tsunemoto/GEITje-7B-chat-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf tsunemoto/GEITje-7B-chat-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf tsunemoto/GEITje-7B-chat-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf tsunemoto/GEITje-7B-chat-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 tsunemoto/GEITje-7B-chat-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf tsunemoto/GEITje-7B-chat-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 tsunemoto/GEITje-7B-chat-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf tsunemoto/GEITje-7B-chat-GGUF:Q4_K_M

Use Docker

docker model run hf.co/tsunemoto/GEITje-7B-chat-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use tsunemoto/GEITje-7B-chat-GGUF with Ollama:
```
ollama run hf.co/tsunemoto/GEITje-7B-chat-GGUF:Q4_K_M
```

Unsloth Studio

How to use tsunemoto/GEITje-7B-chat-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 tsunemoto/GEITje-7B-chat-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 tsunemoto/GEITje-7B-chat-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for tsunemoto/GEITje-7B-chat-GGUF to start chatting

Atomic Chat new
Docker Model Runner
How to use tsunemoto/GEITje-7B-chat-GGUF with Docker Model Runner:
```
docker model run hf.co/tsunemoto/GEITje-7B-chat-GGUF:Q4_K_M
```

Lemonade

How to use tsunemoto/GEITje-7B-chat-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull tsunemoto/GEITje-7B-chat-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.GEITje-7B-chat-GGUF-Q4_K_M

List all available models

lemonade list

Tsunemoto GGUF's of GEITje-7B-chat

This is a GGUF quantization of GEITje-7B-chat.

Original Repo Link:

Original Repository

Original Model Card:

GEITje-7B-chat

GEITje-7B

GEITje is a large open Dutch language model with 7 billion parameters, based on Mistral 7B. It has been further trained on 10 billion tokens of Dutch text. This has improved its Dutch language skills and increased its knowledge of Dutch topics.

Model description

Mistral – Base Model

GEITje is based on Mistral 7B. It's a large open language model with 7 billion parameters, trained by Mistral AI. According to Mistral AI, the 7B model performs better than Llama 2 13B on all (English-language) benchmarks they tested it on. Mistral 7B has been released under the Apache 2.0 open source license.

GEITje – Trained Further on Dutch Texts

GEITje was created by further training Mistral 7B on no less than 10 billion tokens of Dutch text from the Dutch Gigacorpus and the MADLAD-400 web crawling corpus. It is a so-called full-parameter finetune: performed on all parameters. It is not a PEFT or LoRA finetune. Like Mistral, GEITje has a context length of 8,192 tokens.

GEITje-chat – Finetuned for Dialogues

As a demonstration of GEITje's capabilities for chat applications, an initial chat variant of GEITje has also been finetuned: GEITje-chat. GEITje-chat can follow instructions, answer questions, and hold dialogues on a variety of topics.

More info

Read more about GEITje-chat in the 📄 README on GitHub.

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 1e-05
train_batch_size: 2
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 16
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss
1.0263	0.2	236	0.9482
1.0368	0.4	472	0.9574
0.9503	0.6	708	0.9492
1.1419	0.8	944	0.9406
1.2161	1.0	1180	0.9317
0.6695	1.2	1416	0.9407
0.7379	1.4	1652	0.9350
0.7695	1.6	1888	0.9282
0.6795	1.8	2124	0.9218
0.6217	2.0	2360	0.9174
0.438	2.2	2596	0.9546
0.3719	2.39	2832	0.9546
0.4853	2.59	3068	0.9548
0.3852	2.79	3304	0.9548
0.48	2.99	3540	0.9548

Framework versions

Transformers 4.36.0.dev0
Pytorch 2.1.1+cu121
Datasets 2.15.0
Tokenizers 0.15.0

Downloads last month: 9

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