Instructions to use arcee-ai/Trinity-Large-Preview-W4A16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use arcee-ai/Trinity-Large-Preview-W4A16 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="arcee-ai/Trinity-Large-Preview-W4A16", 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-Large-Preview-W4A16", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("arcee-ai/Trinity-Large-Preview-W4A16", 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 Settings

vLLM

How to use arcee-ai/Trinity-Large-Preview-W4A16 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "arcee-ai/Trinity-Large-Preview-W4A16"
# 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-Large-Preview-W4A16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/arcee-ai/Trinity-Large-Preview-W4A16

SGLang

How to use arcee-ai/Trinity-Large-Preview-W4A16 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-Large-Preview-W4A16" \
    --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-Large-Preview-W4A16",
		"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-Large-Preview-W4A16" \
        --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-Large-Preview-W4A16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use arcee-ai/Trinity-Large-Preview-W4A16 with Docker Model Runner:
```
docker model run hf.co/arcee-ai/Trinity-Large-Preview-W4A16
```

Trinity-Large-Preview-W4A16

Commit History

Adopt OpenMDW-1.1 license (#1)

525bb3e

annekethvij commited on 7 days ago

Update README.md

525db1d
verified

Anneketh Vij commited on Apr 1

Update README.md

a9d565a
verified

Anneketh Vij commited on Apr 1

Fix tokenizer export artifact: remove fixed padding/truncation from tokenizer.json

8a9fc41
verified

Anneketh Vij commited on Mar 20

Create README.md

79c0813
verified

Anneketh Vij commited on Feb 25

Upload folder using huggingface_hub

d9bfce6
verified

Anneketh Vij commited on Feb 13

initial commit

6d863e4
verified

Anneketh Vij commited on Feb 13

Commit History

Adopt OpenMDW-1.1 license (#1) 525bb3e

Update README.md 525db1d verified

Update README.md a9d565a verified

Fix tokenizer export artifact: remove fixed padding/truncation from tokenizer.json 8a9fc41 verified

Create README.md 79c0813 verified

Upload folder using huggingface_hub d9bfce6 verified

initial commit 6d863e4 verified