Instructions to use cjvt/OPT_GaMS-1B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use cjvt/OPT_GaMS-1B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="cjvt/OPT_GaMS-1B")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("cjvt/OPT_GaMS-1B") model = AutoModelForCausalLM.from_pretrained("cjvt/OPT_GaMS-1B") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use cjvt/OPT_GaMS-1B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "cjvt/OPT_GaMS-1B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "cjvt/OPT_GaMS-1B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/cjvt/OPT_GaMS-1B
- SGLang
How to use cjvt/OPT_GaMS-1B with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "cjvt/OPT_GaMS-1B" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "cjvt/OPT_GaMS-1B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "cjvt/OPT_GaMS-1B" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "cjvt/OPT_GaMS-1B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use cjvt/OPT_GaMS-1B with Docker Model Runner:
docker model run hf.co/cjvt/OPT_GaMS-1B
Update README.md
Browse files
README.md
CHANGED
|
@@ -21,7 +21,7 @@ We thank everyone who worked on data collection and preparation, enabling us to
|
|
| 21 |
|
| 22 |
## Basic information
|
| 23 |
|
| 24 |
-
- **Developed by:** team of researchers at the University of Ljubljana, Faculty for Computer and Information Science and XLAB.doo. Team members: Domen Vreš, Martin Božič, Aljaž Potočnik, Tomaž Martinčič and Marko Robnik-Šikonja.
|
| 25 |
- **Languages:** Slovene (primary), English, Croatian, Bosnian and Serbian (secondary)
|
| 26 |
- **License:** Apache 2.0
|
| 27 |
- **Repository:** https://github.com/SloLama/NeMo
|
|
@@ -142,4 +142,14 @@ The models were evaluated using [Slovene SuperGLUE](https://slobench.cjvt.si/lea
|
|
| 142 |
|
| 143 |
*SlovenianGPT-Chat was obtained by instruction-tuning Aleksa Gordić's [SlovenianGPT](https://huggingface.co/gordicaleksa/SlovenianGPT) on our instruction dataset.
|
| 144 |
|
| 145 |
-

|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 21 |
|
| 22 |
## Basic information
|
| 23 |
|
| 24 |
+
- **Developed by:** team of researchers at the University of Ljubljana, Faculty for Computer and Information Science and XLAB.doo. Team members: Domen Vreš, Martin Božič, Aljaž Potočnik, Tomaž Martinčič, Iztok Lebar Bajec, Timotej Petrič and Marko Robnik-Šikonja.
|
| 25 |
- **Languages:** Slovene (primary), English, Croatian, Bosnian and Serbian (secondary)
|
| 26 |
- **License:** Apache 2.0
|
| 27 |
- **Repository:** https://github.com/SloLama/NeMo
|
|
|
|
| 142 |
|
| 143 |
*SlovenianGPT-Chat was obtained by instruction-tuning Aleksa Gordić's [SlovenianGPT](https://huggingface.co/gordicaleksa/SlovenianGPT) on our instruction dataset.
|
| 144 |
|
| 145 |
+

|
| 146 |
+
|
| 147 |
+
```
|
| 148 |
+
@inproceedings{GaMS,
|
| 149 |
+
author = {Vre{\v s}, Domen and Bo{\v z}i{\v c}, Martin and Poto{\v c}nik, Alja{\v z} and Martin{\v c}i{\v c}, Toma{\v z} and Robnik-{\v S}ikonja, Marko},
|
| 150 |
+
booktitle = {Language Technologies and Digital Humanities Conference},
|
| 151 |
+
title = {{Generative Model for Less-Resourced Language with 1 billion parameters}},
|
| 152 |
+
url = {https://www.sdjt.si/wp/wp-content/uploads/2024/09/JT-DH-2024_Vres_Bozic_Potocnik_Martincic_Robnik.pdf},
|
| 153 |
+
year = {2024}
|
| 154 |
+
}
|
| 155 |
+
```
|