Instructions to use papahawk/keya-560m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use papahawk/keya-560m with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="papahawk/keya-560m")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("papahawk/keya-560m") model = AutoModelForCausalLM.from_pretrained("papahawk/keya-560m") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use papahawk/keya-560m with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "papahawk/keya-560m" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "papahawk/keya-560m", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/papahawk/keya-560m
- SGLang
How to use papahawk/keya-560m 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 "papahawk/keya-560m" \ --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": "papahawk/keya-560m", "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 "papahawk/keya-560m" \ --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": "papahawk/keya-560m", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use papahawk/keya-560m with Docker Model Runner:
docker model run hf.co/papahawk/keya-560m
dev commited on
Commit ·
2edae46
1
Parent(s): 3e59760
Committer: dev <dev@alt-web.xyz>
Browse filesOn branch main
Changes to be committed:
new file: Dockerfile
Untracked files:
app.py
prompt.txt
requirements.txt
static/
templates/
- Dockerfile +24 -0
Dockerfile
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Use an official Python runtime as a parent image
|
| 2 |
+
FROM python:3.11
|
| 3 |
+
|
| 4 |
+
# Set environment variables
|
| 5 |
+
ENV TRANSFORMERS_CACHE=/tmp
|
| 6 |
+
|
| 7 |
+
# Set work directory
|
| 8 |
+
WORKDIR /usr/src/app
|
| 9 |
+
|
| 10 |
+
# Install any needed packages specified in requirements.txt
|
| 11 |
+
COPY requirements.txt ./
|
| 12 |
+
RUN pip install --no-cache-dir -r requirements.txt
|
| 13 |
+
|
| 14 |
+
# Copy the current directory contents into the container at /app
|
| 15 |
+
COPY . .
|
| 16 |
+
|
| 17 |
+
# Make port 80 available to the world outside this container
|
| 18 |
+
EXPOSE 80
|
| 19 |
+
|
| 20 |
+
# Run app.py when the container launches
|
| 21 |
+
CMD ["python", "app.py"]
|
| 22 |
+
|
| 23 |
+
|
| 24 |
+
|