Instructions to use Azurro/APT3-1B-Base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Azurro/APT3-1B-Base with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Azurro/APT3-1B-Base")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Azurro/APT3-1B-Base") model = AutoModelForCausalLM.from_pretrained("Azurro/APT3-1B-Base") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use Azurro/APT3-1B-Base with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Azurro/APT3-1B-Base" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Azurro/APT3-1B-Base", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Azurro/APT3-1B-Base
- SGLang
How to use Azurro/APT3-1B-Base 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 "Azurro/APT3-1B-Base" \ --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": "Azurro/APT3-1B-Base", "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 "Azurro/APT3-1B-Base" \ --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": "Azurro/APT3-1B-Base", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Azurro/APT3-1B-Base with Docker Model Runner:
docker model run hf.co/Azurro/APT3-1B-Base
Commit ·
671c53c
1
Parent(s): 939c3b4
Update README.md
Browse files
README.md
CHANGED
|
@@ -86,7 +86,10 @@ A special tokenizer has been prepared and trained for the purpose of training th
|
|
| 86 |
* Visualizations: [W&B](https://wandb.ai)
|
| 87 |
|
| 88 |
<p align="center">
|
| 89 |
-
<img src="https://huggingface.co/Azurro/APT3-1B-Base/raw/main/apt3-1b-base.jpg">
|
|
|
|
|
|
|
|
|
|
| 90 |
</p>
|
| 91 |
|
| 92 |
### Training hyperparameters:
|
|
|
|
| 86 |
* Visualizations: [W&B](https://wandb.ai)
|
| 87 |
|
| 88 |
<p align="center">
|
| 89 |
+
<img src="https://huggingface.co/Azurro/APT3-1B-Base/raw/main/apt3-1b-base-train.jpg">
|
| 90 |
+
</p>
|
| 91 |
+
<p align="center">
|
| 92 |
+
<img src="https://huggingface.co/Azurro/APT3-1B-Base/raw/main/apt3-1b-base-eval.jpg">
|
| 93 |
</p>
|
| 94 |
|
| 95 |
### Training hyperparameters:
|