Instructions to use Azurro/APT3-275M-Base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Azurro/APT3-275M-Base with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Azurro/APT3-275M-Base")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Azurro/APT3-275M-Base") model = AutoModelForCausalLM.from_pretrained("Azurro/APT3-275M-Base", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Azurro/APT3-275M-Base with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Azurro/APT3-275M-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/APT3-275M-Base", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Azurro/APT3-275M-Base
- SGLang
How to use Azurro/APT3-275M-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/APT3-275M-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/APT3-275M-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/APT3-275M-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/APT3-275M-Base", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Azurro/APT3-275M-Base with Docker Model Runner:
docker model run hf.co/Azurro/APT3-275M-Base
Update README.md
Browse files
README.md
CHANGED
|
@@ -170,10 +170,10 @@ Please cite this model using the following format:
|
|
| 170 |
|
| 171 |
```
|
| 172 |
@online{AzurroAPT3Base275M,
|
| 173 |
-
author = {
|
| 174 |
title = {Introducing APT3-275M-Base: Polish Language Model},
|
| 175 |
year = {2023},
|
| 176 |
-
url = {
|
| 177 |
note = {Accessed: 2023-11-20}, % change this date
|
| 178 |
urldate = {2023-11-20} % change this date
|
| 179 |
}
|
|
|
|
| 170 |
|
| 171 |
```
|
| 172 |
@online{AzurroAPT3Base275M,
|
| 173 |
+
author = {Ociepa, Krzysztof and {Azurro Team}},
|
| 174 |
title = {Introducing APT3-275M-Base: Polish Language Model},
|
| 175 |
year = {2023},
|
| 176 |
+
url = {https://azurro.pl/apt3-275m-base-en},
|
| 177 |
note = {Accessed: 2023-11-20}, % change this date
|
| 178 |
urldate = {2023-11-20} % change this date
|
| 179 |
}
|