Instructions to use arcee-ai/Trinity-Mini with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use arcee-ai/Trinity-Mini with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="arcee-ai/Trinity-Mini", trust_remote_code=True) messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("arcee-ai/Trinity-Mini", trust_remote_code=True) model = AutoModelForCausalLM.from_pretrained("arcee-ai/Trinity-Mini", trust_remote_code=True) messages = [ {"role": "user", "content": "Who are you?"}, ] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=40) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use arcee-ai/Trinity-Mini with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "arcee-ai/Trinity-Mini" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "arcee-ai/Trinity-Mini", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/arcee-ai/Trinity-Mini
- SGLang
How to use arcee-ai/Trinity-Mini 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 "arcee-ai/Trinity-Mini" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "arcee-ai/Trinity-Mini", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'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 "arcee-ai/Trinity-Mini" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "arcee-ai/Trinity-Mini", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use arcee-ai/Trinity-Mini with Docker Model Runner:
docker model run hf.co/arcee-ai/Trinity-Mini
Upload Dockerfile
#6
by kyleone - opened
- Dockerfile +62 -0
Dockerfile
ADDED
|
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Build frontend
|
| 2 |
+
FROM node:18 as frontend-build
|
| 3 |
+
WORKDIR /app
|
| 4 |
+
COPY frontend/package*.json ./
|
| 5 |
+
RUN npm install
|
| 6 |
+
COPY frontend/ ./
|
| 7 |
+
|
| 8 |
+
RUN npm run build
|
| 9 |
+
|
| 10 |
+
# Build backend
|
| 11 |
+
FROM python:3.12-slim
|
| 12 |
+
WORKDIR /app
|
| 13 |
+
|
| 14 |
+
# Create non-root user
|
| 15 |
+
RUN useradd -m -u 1000 user
|
| 16 |
+
|
| 17 |
+
# Install poetry
|
| 18 |
+
RUN pip install poetry
|
| 19 |
+
|
| 20 |
+
# Create and configure cache directory
|
| 21 |
+
RUN mkdir -p /app/.cache && \
|
| 22 |
+
chown -R user:user /app
|
| 23 |
+
|
| 24 |
+
# Copy and install backend dependencies
|
| 25 |
+
COPY backend/pyproject.toml backend/poetry.lock* ./
|
| 26 |
+
RUN poetry config virtualenvs.create false \
|
| 27 |
+
&& poetry install --no-interaction --no-ansi --no-root --only main
|
| 28 |
+
|
| 29 |
+
# Copy backend code
|
| 30 |
+
COPY backend/ .
|
| 31 |
+
|
| 32 |
+
# Install Node.js and npm
|
| 33 |
+
RUN apt-get update && apt-get install -y \
|
| 34 |
+
curl \
|
| 35 |
+
netcat-openbsd \
|
| 36 |
+
&& curl -fsSL https://deb.nodesource.com/setup_18.x | bash - \
|
| 37 |
+
&& apt-get install -y nodejs \
|
| 38 |
+
&& rm -rf /var/lib/apt/lists/*
|
| 39 |
+
|
| 40 |
+
# Copy frontend server and build
|
| 41 |
+
COPY --from=frontend-build /app/build ./frontend/build
|
| 42 |
+
COPY --from=frontend-build /app/package*.json ./frontend/
|
| 43 |
+
COPY --from=frontend-build /app/server.js ./frontend/
|
| 44 |
+
|
| 45 |
+
# Install frontend production dependencies
|
| 46 |
+
WORKDIR /app/frontend
|
| 47 |
+
RUN npm install --production
|
| 48 |
+
WORKDIR /app
|
| 49 |
+
|
| 50 |
+
# Environment variables
|
| 51 |
+
ENV HF_HOME=/app/.cache \
|
| 52 |
+
HF_DATASETS_CACHE=/app/.cache \
|
| 53 |
+
INTERNAL_API_PORT=7861 \
|
| 54 |
+
PORT=7860 \
|
| 55 |
+
NODE_ENV=production
|
| 56 |
+
|
| 57 |
+
# Note: HF_TOKEN should be provided at runtime, not build time
|
| 58 |
+
USER user
|
| 59 |
+
EXPOSE 7860
|
| 60 |
+
|
| 61 |
+
# Start both servers with wait-for
|
| 62 |
+
CMD ["sh", "-c", "uvicorn app.asgi:app --host 0.0.0.0 --port 7861 & while ! nc -z localhost 7861; do sleep 1; done && cd frontend && npm run serve"]
|