Instructions to use nvidia/Minitron-4B-Base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use nvidia/Minitron-4B-Base with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="nvidia/Minitron-4B-Base")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("nvidia/Minitron-4B-Base", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use nvidia/Minitron-4B-Base with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "nvidia/Minitron-4B-Base" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "nvidia/Minitron-4B-Base", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/nvidia/Minitron-4B-Base
- SGLang
How to use nvidia/Minitron-4B-Base 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/Minitron-4B-Base" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "nvidia/Minitron-4B-Base", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'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/Minitron-4B-Base" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "nvidia/Minitron-4B-Base", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use nvidia/Minitron-4B-Base with Docker Model Runner:
docker model run hf.co/nvidia/Minitron-4B-Base
Update tokenizer config
Browse files- special_tokens_map.json +4 -1
- tokenizer_config.json +3 -1
special_tokens_map.json
CHANGED
|
@@ -1 +1,4 @@
|
|
| 1 |
-
{
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"eos_token": "</s>"
|
| 4 |
+
}
|
tokenizer_config.json
CHANGED
|
@@ -8025,10 +8025,12 @@
|
|
| 8025 |
"special": false
|
| 8026 |
}
|
| 8027 |
},
|
|
|
|
| 8028 |
"clean_up_tokenization_spaces": true,
|
|
|
|
| 8029 |
"model_input_names": [
|
| 8030 |
"input_ids",
|
| 8031 |
-
"
|
| 8032 |
],
|
| 8033 |
"model_max_length": 1000000000000000019884624838656,
|
| 8034 |
"tokenizer_class": "PreTrainedTokenizerFast"
|
|
|
|
| 8025 |
"special": false
|
| 8026 |
}
|
| 8027 |
},
|
| 8028 |
+
"bos_token": "<s>",
|
| 8029 |
"clean_up_tokenization_spaces": true,
|
| 8030 |
+
"eos_token": "</s>",
|
| 8031 |
"model_input_names": [
|
| 8032 |
"input_ids",
|
| 8033 |
+
"attention_mask"
|
| 8034 |
],
|
| 8035 |
"model_max_length": 1000000000000000019884624838656,
|
| 8036 |
"tokenizer_class": "PreTrainedTokenizerFast"
|