Instructions to use trillionlabs/Trillion-7B-preview with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use trillionlabs/Trillion-7B-preview with Transformers:

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

pipe = pipeline("text-generation", model="trillionlabs/Trillion-7B-preview")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("trillionlabs/Trillion-7B-preview")
model = AutoModelForCausalLM.from_pretrained("trillionlabs/Trillion-7B-preview", device_map="auto")
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 trillionlabs/Trillion-7B-preview with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "trillionlabs/Trillion-7B-preview"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "trillionlabs/Trillion-7B-preview",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/trillionlabs/Trillion-7B-preview

SGLang

How to use trillionlabs/Trillion-7B-preview 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 "trillionlabs/Trillion-7B-preview" \
    --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": "trillionlabs/Trillion-7B-preview",
		"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 "trillionlabs/Trillion-7B-preview" \
        --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": "trillionlabs/Trillion-7B-preview",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use trillionlabs/Trillion-7B-preview with Docker Model Runner:
```
docker model run hf.co/trillionlabs/Trillion-7B-preview
```

nielsr HF Staff commited on Apr 25, 2025

Commit

797ecea

verified ·

1 Parent(s): e6ca2fd

Add paper link to model card

Browse files

This PR adds a link to the paper in the model card for better context and discoverability. The paper is: [Trillion-7B-preview](https://huggingface.co/papers/2504.15431).

Files changed (1) hide show

README.md +7 -7

README.md CHANGED Viewed

@@ -1,15 +1,15 @@
 ---
-license: apache-2.0
-tags:
-- finetuned
-- chat
 language:
 - en
 - ko
 - ja
 - zh
-pipeline_tag: text-generation
 library_name: transformers
 ---
 # Trillion-7B-preview
@@ -22,7 +22,7 @@ library_name: transformers
 ## Introduction
-We introduce Trillion-7B-preview, a preview of our latest large language model designed to push the boundaries of multilingual scalability and performance.
 When comparing performance to training FLOPs for Trillion-7B-preview with competitive models, our model pushes the Pareto frontier, achieving around 66.5% average performance while using significantly fewer compute (~9.3×10²² FLOPs). It outperforms models like Mistral-7B-Instruct-v0.3 and SOLAR-10.7B-Instruct-v1.0 while remaining competitive with models requiring 3-8× more compute such as Qwen2.5-7B-Instruct and EXAONE-3.5-7.8B-Instruct. For full benchmark results, see tables below.
@@ -240,4 +240,4 @@ This model repository is licensed under the Apache-2.0 License.
 }
 ```
 ## Contact
-For inquiries, please contact: info@trillionlabs.co

 ---
 language:
 - en
 - ko
 - ja
 - zh
 library_name: transformers
+license: apache-2.0
+pipeline_tag: text-generation
+tags:
+- finetuned
+- chat
 ---
 # Trillion-7B-preview
 ## Introduction
+We introduce Trillion-7B-preview, a preview of our latest large language model designed to push the boundaries of multilingual scalability and performance.  This model is presented in the paper: [Trillion-7B-preview](https://huggingface.co/papers/2504.15431).
 When comparing performance to training FLOPs for Trillion-7B-preview with competitive models, our model pushes the Pareto frontier, achieving around 66.5% average performance while using significantly fewer compute (~9.3×10²² FLOPs). It outperforms models like Mistral-7B-Instruct-v0.3 and SOLAR-10.7B-Instruct-v1.0 while remaining competitive with models requiring 3-8× more compute such as Qwen2.5-7B-Instruct and EXAONE-3.5-7.8B-Instruct. For full benchmark results, see tables below.
 }
 ```
 ## Contact
+For inquiries, please contact: info@trillionlabs.co