Instructions to use nvidia/Minitron-8B-Base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use nvidia/Minitron-8B-Base with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="nvidia/Minitron-8B-Base")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("nvidia/Minitron-8B-Base", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use nvidia/Minitron-8B-Base with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "nvidia/Minitron-8B-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-8B-Base", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/nvidia/Minitron-8B-Base
- SGLang
How to use nvidia/Minitron-8B-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-8B-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-8B-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-8B-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-8B-Base", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use nvidia/Minitron-8B-Base with Docker Model Runner:
docker model run hf.co/nvidia/Minitron-8B-Base
Replace kv_channels with head_dim
Browse files- config.json +1 -1
config.json
CHANGED
|
@@ -13,7 +13,7 @@
|
|
| 13 |
"model_type": "nemotron",
|
| 14 |
"num_attention_heads": 48,
|
| 15 |
"num_hidden_layers": 32,
|
| 16 |
-
"
|
| 17 |
"num_key_value_heads": 8,
|
| 18 |
"norm_eps": 1e-05,
|
| 19 |
"rope_theta": 10000,
|
|
|
|
| 13 |
"model_type": "nemotron",
|
| 14 |
"num_attention_heads": 48,
|
| 15 |
"num_hidden_layers": 32,
|
| 16 |
+
"head_dim": 128,
|
| 17 |
"num_key_value_heads": 8,
|
| 18 |
"norm_eps": 1e-05,
|
| 19 |
"rope_theta": 10000,
|