Instructions to use lightblue/jod with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use lightblue/jod with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="lightblue/jod")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("lightblue/jod") model = AutoModelForCausalLM.from_pretrained("lightblue/jod") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use lightblue/jod with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "lightblue/jod" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "lightblue/jod", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/lightblue/jod
- SGLang
How to use lightblue/jod 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 "lightblue/jod" \ --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": "lightblue/jod", "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 "lightblue/jod" \ --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": "lightblue/jod", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use lightblue/jod with Docker Model Runner:
docker model run hf.co/lightblue/jod
Update README.md
Browse files
README.md
CHANGED
|
@@ -13,10 +13,12 @@ We write our prompts in the ChatML format.
|
|
| 13 |
### With vLLM (recommended for much faster inference)
|
| 14 |
|
| 15 |
<details><summary>Install vLLM</summary>
|
|
|
|
|
|
|
|
|
|
| 16 |
```bash
|
| 17 |
pip install vllm
|
| 18 |
```
|
| 19 |
-
[Reference](https://vllm.readthedocs.io/en/latest/getting_started/installation.html)
|
| 20 |
</details>
|
| 21 |
|
| 22 |
```python
|
|
|
|
| 13 |
### With vLLM (recommended for much faster inference)
|
| 14 |
|
| 15 |
<details><summary>Install vLLM</summary>
|
| 16 |
+
|
| 17 |
+
[Reference](https://vllm.readthedocs.io/en/latest/getting_started/installation.html)
|
| 18 |
+
|
| 19 |
```bash
|
| 20 |
pip install vllm
|
| 21 |
```
|
|
|
|
| 22 |
</details>
|
| 23 |
|
| 24 |
```python
|