Instructions to use nvidia/Riva-Translate-4B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nvidia/Riva-Translate-4B-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="nvidia/Riva-Translate-4B-Instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("nvidia/Riva-Translate-4B-Instruct")
model = AutoModelForCausalLM.from_pretrained("nvidia/Riva-Translate-4B-Instruct")
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 nvidia/Riva-Translate-4B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nvidia/Riva-Translate-4B-Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nvidia/Riva-Translate-4B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/nvidia/Riva-Translate-4B-Instruct

SGLang

How to use nvidia/Riva-Translate-4B-Instruct 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 "nvidia/Riva-Translate-4B-Instruct" \
    --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": "nvidia/Riva-Translate-4B-Instruct",
		"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 "nvidia/Riva-Translate-4B-Instruct" \
        --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": "nvidia/Riva-Translate-4B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use nvidia/Riva-Translate-4B-Instruct with Docker Model Runner:
```
docker model run hf.co/nvidia/Riva-Translate-4B-Instruct
```

Mujojojo commited on Jun 11, 2025

Commit

b8329ea

1 Parent(s): 0bc46a7

change the model files

Browse files

Files changed (8) hide show

Mistral_NeMo_Minitron_4B_8K_MT-hf/config.json → config.json +0 -1
Mistral_NeMo_Minitron_4B_8K_MT-hf/generation_config.json → generation_config.json +0 -0
Mistral_NeMo_Minitron_4B_8K_MT-hf/model-00001-of-00002.safetensors → model-00001-of-00002.safetensors +0 -0
Mistral_NeMo_Minitron_4B_8K_MT-hf/model-00002-of-00002.safetensors → model-00002-of-00002.safetensors +0 -0
Mistral_NeMo_Minitron_4B_8K_MT-hf/model.safetensors.index.json → model.safetensors.index.json +0 -0
Mistral_NeMo_Minitron_4B_8K_MT-hf/special_tokens_map.json → special_tokens_map.json +0 -0
Mistral_NeMo_Minitron_4B_8K_MT-hf/tokenizer.json → tokenizer.json +0 -0
Mistral_NeMo_Minitron_4B_8K_MT-hf/tokenizer_config.json → tokenizer_config.json +0 -0

Mistral_NeMo_Minitron_4B_8K_MT-hf/config.json → config.json RENAMED Viewed

@@ -1,5 +1,4 @@
 {
-  "_name_or_path": "/lustre/fsw/portfolios/llmservice/users/mengruw/sft_mistral_4b_8k/conversion_models/deployment_workspace/Mistral-Nemo-Base-2407",
   "activation": "silu",
   "architectures": [
     "MistralForCausalLM"

 {
   "activation": "silu",
   "architectures": [
     "MistralForCausalLM"

Mistral_NeMo_Minitron_4B_8K_MT-hf/generation_config.json → generation_config.json RENAMED Viewed

File without changes

Mistral_NeMo_Minitron_4B_8K_MT-hf/model-00001-of-00002.safetensors → model-00001-of-00002.safetensors RENAMED Viewed

File without changes

Mistral_NeMo_Minitron_4B_8K_MT-hf/model-00002-of-00002.safetensors → model-00002-of-00002.safetensors RENAMED Viewed

File without changes

Mistral_NeMo_Minitron_4B_8K_MT-hf/model.safetensors.index.json → model.safetensors.index.json RENAMED Viewed

File without changes

Mistral_NeMo_Minitron_4B_8K_MT-hf/special_tokens_map.json → special_tokens_map.json RENAMED Viewed

File without changes

Mistral_NeMo_Minitron_4B_8K_MT-hf/tokenizer.json → tokenizer.json RENAMED Viewed

File without changes

Mistral_NeMo_Minitron_4B_8K_MT-hf/tokenizer_config.json → tokenizer_config.json RENAMED Viewed

File without changes