Instructions to use TNSA/NGen2-170M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use TNSA/NGen2-170M with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="TNSA/NGen2-170M")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("TNSA/NGen2-170M", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use TNSA/NGen2-170M with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "TNSA/NGen2-170M" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "TNSA/NGen2-170M", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/TNSA/NGen2-170M
- SGLang
How to use TNSA/NGen2-170M 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 "TNSA/NGen2-170M" \ --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": "TNSA/NGen2-170M", "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 "TNSA/NGen2-170M" \ --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": "TNSA/NGen2-170M", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use TNSA/NGen2-170M with Docker Model Runner:
docker model run hf.co/TNSA/NGen2-170M
Update README.md
Browse files
README.md
CHANGED
|
@@ -25,7 +25,7 @@ NGen 2 is an advanced Transformer model training pipeline that supports multiple
|
|
| 25 |
|
| 26 |
> **Note:** Although NGen 2 is designed to train a 1B-parameter model, its advanced architecture pushes its performance closer to that of much larger models. Try using NGen3 for performance.
|
| 27 |
|
| 28 |
-
|
| 29 |
|
| 30 |
|
| 31 |
## Model Variants
|
|
|
|
| 25 |
|
| 26 |
> **Note:** Although NGen 2 is designed to train a 1B-parameter model, its advanced architecture pushes its performance closer to that of much larger models. Try using NGen3 for performance.
|
| 27 |
|
| 28 |
+
# The NGen2 Series was only Produced till 170M and The other Variants were produced but were never made public
|
| 29 |
|
| 30 |
|
| 31 |
## Model Variants
|