Instructions to use arcee-ai/Trinity-Large-Thinking-NVFP4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use arcee-ai/Trinity-Large-Thinking-NVFP4 with Transformers:

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

pipe = pipeline("text-generation", model="arcee-ai/Trinity-Large-Thinking-NVFP4", 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-Thinking-NVFP4", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("arcee-ai/Trinity-Large-Thinking-NVFP4", 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-Large-Thinking-NVFP4 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-Thinking-NVFP4"
# 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-Thinking-NVFP4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/arcee-ai/Trinity-Large-Thinking-NVFP4

SGLang

How to use arcee-ai/Trinity-Large-Thinking-NVFP4 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-Thinking-NVFP4" \
    --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-Thinking-NVFP4",
		"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-Thinking-NVFP4" \
        --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-Thinking-NVFP4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use arcee-ai/Trinity-Large-Thinking-NVFP4 with Docker Model Runner:
```
docker model run hf.co/arcee-ai/Trinity-Large-Thinking-NVFP4
```

Trinity-Large-Thinking-NVFP4 / hf_quant_config.json

Anneketh Vij

Add files using upload-large-folder tool

bfc8daf verified about 1 month ago

raw

history blame contribute delete

7.82 kB

	{
	"producer": {
	"name": "modelopt",
	"version": "0.0.1.dev582+gbe5626cb9.d20260408"
	},
	"quantization": {
	"quant_algo": "NVFP4",
	"kv_cache_quant_algo": null,
	"group_size": 16,
	"exclude_modules": [
	"lm_head",
	"model.layers.0*",
	"model.layers.1.*",
	"model.layers.10.mlp.router*",
	"model.layers.10.mlp.shared_experts*",
	"model.layers.10.self_attn*",
	"model.layers.11.mlp.router*",
	"model.layers.11.mlp.shared_experts*",
	"model.layers.11.self_attn*",
	"model.layers.12.mlp.router*",
	"model.layers.12.mlp.shared_experts*",
	"model.layers.12.self_attn*",
	"model.layers.13.mlp.router*",
	"model.layers.13.mlp.shared_experts*",
	"model.layers.13.self_attn*",
	"model.layers.14.mlp.router*",
	"model.layers.14.mlp.shared_experts*",
	"model.layers.14.self_attn*",
	"model.layers.15.mlp.router*",
	"model.layers.15.mlp.shared_experts*",
	"model.layers.15.self_attn*",
	"model.layers.16.mlp.router*",
	"model.layers.16.mlp.shared_experts*",
	"model.layers.16.self_attn*",
	"model.layers.17.mlp.router*",
	"model.layers.17.mlp.shared_experts*",
	"model.layers.17.self_attn*",
	"model.layers.18.mlp.router*",
	"model.layers.18.mlp.shared_experts*",
	"model.layers.18.self_attn*",
	"model.layers.19.mlp.router*",
	"model.layers.19.mlp.shared_experts*",
	"model.layers.19.self_attn*",
	"model.layers.2.*",
	"model.layers.20.mlp.router*",
	"model.layers.20.mlp.shared_experts*",
	"model.layers.20.self_attn*",
	"model.layers.21.mlp.router*",
	"model.layers.21.mlp.shared_experts*",
	"model.layers.21.self_attn*",
	"model.layers.22.mlp.router*",
	"model.layers.22.mlp.shared_experts*",
	"model.layers.22.self_attn*",
	"model.layers.23.mlp.router*",
	"model.layers.23.mlp.shared_experts*",
	"model.layers.23.self_attn*",
	"model.layers.24.mlp.router*",
	"model.layers.24.mlp.shared_experts*",
	"model.layers.24.self_attn*",
	"model.layers.25.mlp.router*",
	"model.layers.25.mlp.shared_experts*",
	"model.layers.25.self_attn*",
	"model.layers.26.mlp.router*",
	"model.layers.26.mlp.shared_experts*",
	"model.layers.26.self_attn*",
	"model.layers.27.mlp.router*",
	"model.layers.27.mlp.shared_experts*",
	"model.layers.27.self_attn*",
	"model.layers.28.mlp.router*",
	"model.layers.28.mlp.shared_experts*",
	"model.layers.28.self_attn*",
	"model.layers.29.mlp.router*",
	"model.layers.29.mlp.shared_experts*",
	"model.layers.29.self_attn*",
	"model.layers.3.*",
	"model.layers.30.mlp.router*",
	"model.layers.30.mlp.shared_experts*",
	"model.layers.30.self_attn*",
	"model.layers.31.mlp.router*",
	"model.layers.31.mlp.shared_experts*",
	"model.layers.31.self_attn*",
	"model.layers.32.mlp.router*",
	"model.layers.32.mlp.shared_experts*",
	"model.layers.32.self_attn*",
	"model.layers.33.mlp.router*",
	"model.layers.33.mlp.shared_experts*",
	"model.layers.33.self_attn*",
	"model.layers.34.mlp.router*",
	"model.layers.34.mlp.shared_experts*",
	"model.layers.34.self_attn*",
	"model.layers.35.mlp.router*",
	"model.layers.35.mlp.shared_experts*",
	"model.layers.35.self_attn*",
	"model.layers.36.mlp.router*",
	"model.layers.36.mlp.shared_experts*",
	"model.layers.36.self_attn*",
	"model.layers.37.mlp.router*",
	"model.layers.37.mlp.shared_experts*",
	"model.layers.37.self_attn*",
	"model.layers.38.mlp.router*",
	"model.layers.38.mlp.shared_experts*",
	"model.layers.38.self_attn*",
	"model.layers.39.mlp.router*",
	"model.layers.39.mlp.shared_experts*",
	"model.layers.39.self_attn*",
	"model.layers.4.*",
	"model.layers.40.mlp.router*",
	"model.layers.40.mlp.shared_experts*",
	"model.layers.40.self_attn*",
	"model.layers.41.mlp.router*",
	"model.layers.41.mlp.shared_experts*",
	"model.layers.41.self_attn*",
	"model.layers.42.mlp.router*",
	"model.layers.42.mlp.shared_experts*",
	"model.layers.42.self_attn*",
	"model.layers.43.mlp.router*",
	"model.layers.43.mlp.shared_experts*",
	"model.layers.43.self_attn*",
	"model.layers.44.mlp.router*",
	"model.layers.44.mlp.shared_experts*",
	"model.layers.44.self_attn*",
	"model.layers.45.mlp.router*",
	"model.layers.45.mlp.shared_experts*",
	"model.layers.45.self_attn*",
	"model.layers.46.mlp.router*",
	"model.layers.46.mlp.shared_experts*",
	"model.layers.46.self_attn*",
	"model.layers.47.mlp.router*",
	"model.layers.47.mlp.shared_experts*",
	"model.layers.47.self_attn*",
	"model.layers.48.mlp.router*",
	"model.layers.48.mlp.shared_experts*",
	"model.layers.48.self_attn*",
	"model.layers.49.mlp.router*",
	"model.layers.49.mlp.shared_experts*",
	"model.layers.49.self_attn*",
	"model.layers.5.*",
	"model.layers.50.mlp.router*",
	"model.layers.50.mlp.shared_experts*",
	"model.layers.50.self_attn*",
	"model.layers.51.mlp.router*",
	"model.layers.51.mlp.shared_experts*",
	"model.layers.51.self_attn*",
	"model.layers.52.mlp.router*",
	"model.layers.52.mlp.shared_experts*",
	"model.layers.52.self_attn*",
	"model.layers.53.mlp.router*",
	"model.layers.53.mlp.shared_experts*",
	"model.layers.53.self_attn*",
	"model.layers.54.mlp.router*",
	"model.layers.54.mlp.shared_experts*",
	"model.layers.54.self_attn*",
	"model.layers.55.mlp.router*",
	"model.layers.55.mlp.shared_experts*",
	"model.layers.55.self_attn*",
	"model.layers.56.mlp.router*",
	"model.layers.56.mlp.shared_experts*",
	"model.layers.56.self_attn*",
	"model.layers.57.mlp.router*",
	"model.layers.57.mlp.shared_experts*",
	"model.layers.57.self_attn*",
	"model.layers.58.mlp.router*",
	"model.layers.58.mlp.shared_experts*",
	"model.layers.58.self_attn*",
	"model.layers.59.mlp.router*",
	"model.layers.59.mlp.shared_experts*",
	"model.layers.59.self_attn*",
	"model.layers.6.mlp.router*",
	"model.layers.6.mlp.shared_experts*",
	"model.layers.6.self_attn*",
	"model.layers.7.mlp.router*",
	"model.layers.7.mlp.shared_experts*",
	"model.layers.7.self_attn*",
	"model.layers.8.mlp.router*",
	"model.layers.8.mlp.shared_experts*",
	"model.layers.8.self_attn*",
	"model.layers.9.mlp.router*",
	"model.layers.9.mlp.shared_experts*",
	"model.layers.9.self_attn*"
	]
	}
	}