Instructions to use trillionlabs/Tri-21B-Think with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use trillionlabs/Tri-21B-Think with Transformers:

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

pipe = pipeline("text-generation", model="trillionlabs/Tri-21B-Think", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("trillionlabs/Tri-21B-Think", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use trillionlabs/Tri-21B-Think with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "trillionlabs/Tri-21B-Think"
# 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/Tri-21B-Think",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/trillionlabs/Tri-21B-Think

SGLang

How to use trillionlabs/Tri-21B-Think 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/Tri-21B-Think" \
    --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/Tri-21B-Think",
		"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/Tri-21B-Think" \
        --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/Tri-21B-Think",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use trillionlabs/Tri-21B-Think with Docker Model Runner:
```
docker model run hf.co/trillionlabs/Tri-21B-Think
```

Tri-21B-Think

File size: 1,075 Bytes

{
    "architectures": [
        "TrillionForCausalLM"
    ],
    "attention_bias": false,
    "attention_dropout": 0.0,
    "attn_scale": 1.0,
    "attn_temperature_tuning": false,
    "auto_map": {
        "AutoConfig": "configuration_trillion.TrillionConfig",
        "AutoModelForCausalLM": "modeling_trillion.TrillionForCausalLM",
        "AutoModel": "modeling_trillion.TrillionModel"
    },
    "bos_token_id": 123964,
    "dtype": "float32",
    "eos_token_id": 123965,
    "floor_scale": 1.0,
    "head_dim": 160,
    "hidden_act": "silu",
    "hidden_size": 5120,
    "initializer_range": 0.02,
    "intermediate_size": 27392,
    "max_position_embeddings": 32768,
    "mlp_bias": false,
    "model_type": "trillion",
    "num_attention_heads": 32,
    "num_hidden_layers": 40,
    "num_key_value_heads": 8,
    "pad_token_id": 124415,
    "pretraining_tp": 1,
    "rms_norm_eps": 1e-05,
    "rope_scaling": null,
    "rope_theta": 1000000.0,
    "tie_word_embeddings": false,
    "transformers_version": "4.57.3",
    "use_cache": true,
    "vocab_size": 124416
}