Instructions to use nllg/tikzero-plus-10b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use nllg/tikzero-plus-10b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="nllg/tikzero-plus-10b")# Load model directly from transformers import AutoModelForSeq2SeqLM model = AutoModelForSeq2SeqLM.from_pretrained("nllg/tikzero-plus-10b", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use nllg/tikzero-plus-10b with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "nllg/tikzero-plus-10b" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "nllg/tikzero-plus-10b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/nllg/tikzero-plus-10b
- SGLang
How to use nllg/tikzero-plus-10b 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 "nllg/tikzero-plus-10b" \ --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": "nllg/tikzero-plus-10b", "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 "nllg/tikzero-plus-10b" \ --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": "nllg/tikzero-plus-10b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use nllg/tikzero-plus-10b with Docker Model Runner:
docker model run hf.co/nllg/tikzero-plus-10b
Update README.md
Browse files
README.md
CHANGED
|
@@ -33,4 +33,10 @@ fig = pipeline.sample(text=caption)
|
|
| 33 |
# if it compiles, rasterize it and show it
|
| 34 |
if fig.is_rasterizable:
|
| 35 |
fig.rasterize().show()
|
| 36 |
-
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 33 |
# if it compiles, rasterize it and show it
|
| 34 |
if fig.is_rasterizable:
|
| 35 |
fig.rasterize().show()
|
| 36 |
+
```
|
| 37 |
+
|
| 38 |
+
## Acknowledgments
|
| 39 |
+
This model was trained using computational resources provided by the
|
| 40 |
+
bwForCluster Helix, as part of the bwHPC-S5 project. The authors acknowledge
|
| 41 |
+
support from the state of Baden-Württemberg through the bwHPC initiative and
|
| 42 |
+
the German Research Foundation (DFG) under grant INST 35/1597-1 FUGG.
|