Instructions to use jan-hq/trinity-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jan-hq/trinity-v1 with Transformers:

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

pipe = pipeline("text-generation", model="jan-hq/trinity-v1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("jan-hq/trinity-v1")
model = AutoModelForCausalLM.from_pretrained("jan-hq/trinity-v1")
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 jan-hq/trinity-v1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jan-hq/trinity-v1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jan-hq/trinity-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/jan-hq/trinity-v1

SGLang

How to use jan-hq/trinity-v1 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 "jan-hq/trinity-v1" \
    --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": "jan-hq/trinity-v1",
		"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 "jan-hq/trinity-v1" \
        --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": "jan-hq/trinity-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use jan-hq/trinity-v1 with Docker Model Runner:
```
docker model run hf.co/jan-hq/trinity-v1
```

trinity-v1

Commit History

Update README.md

ed8a3f0

jan-hq commited on Jan 3, 2024

Update README.md

15fc7e9

jan-hq commited on Dec 18, 2023

Update README.md

016dfa2

jan-hq commited on Dec 18, 2023

Update README.md

8cc1383

jan-hq commited on Dec 18, 2023

Update README.md

ef63ef7

jan-hq commited on Dec 17, 2023

Update README.md

f914883

jan-hq commited on Dec 17, 2023

Update tokenizer_config.json

d4052a1

jan-hq commited on Dec 17, 2023

Update README.md

34974ae

Jan commited on Dec 15, 2023

Update README.md

038f277

Jan commited on Dec 14, 2023

Update README.md

4b2fb94

Jan commited on Dec 14, 2023

Update README.md

6220554

Jan commited on Dec 14, 2023

Update README.md

e24ab99

Jan commited on Dec 14, 2023

Update README.md

2fcb077

Jan commited on Dec 14, 2023

Update README.md

a2d076b

Jan commited on Dec 14, 2023

Create README.md

e6e4843

Jan commited on Dec 14, 2023

Upload folder using huggingface_hub

6eefd99

Jan commited on Dec 14, 2023

initial commit

6276278

Jan commited on Dec 14, 2023

Commit History

Update README.md ed8a3f0

Update README.md 15fc7e9

Update README.md 016dfa2

Update README.md 8cc1383

Update README.md ef63ef7

Update README.md f914883

Update tokenizer_config.json d4052a1

Update README.md 34974ae

Update README.md 038f277

Update README.md 4b2fb94

Update README.md 6220554

Update README.md e24ab99

Update README.md 2fcb077

Update README.md a2d076b

Create README.md e6e4843

Upload folder using huggingface_hub 6eefd99

initial commit 6276278

Update README.md

ed8a3f0

Update README.md

15fc7e9

Update README.md

016dfa2

Update README.md

8cc1383

Update README.md

ef63ef7

Update README.md

f914883

Update tokenizer_config.json

d4052a1

Update README.md

34974ae

Update README.md

038f277

Update README.md

4b2fb94

Update README.md

6220554

Update README.md

e24ab99

Update README.md

2fcb077

Update README.md

a2d076b

Create README.md

e6e4843

Upload folder using huggingface_hub

6eefd99

initial commit

6276278