Instructions to use Supernova11c/Supernova-Transformer-V2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Supernova11c/Supernova-Transformer-V2 with Transformers:

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

pipe = pipeline("text-generation", model="Supernova11c/Supernova-Transformer-V2")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("Supernova11c/Supernova-Transformer-V2", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Supernova11c/Supernova-Transformer-V2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Supernova11c/Supernova-Transformer-V2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Supernova11c/Supernova-Transformer-V2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Supernova11c/Supernova-Transformer-V2

SGLang

How to use Supernova11c/Supernova-Transformer-V2 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 "Supernova11c/Supernova-Transformer-V2" \
    --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": "Supernova11c/Supernova-Transformer-V2",
		"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 "Supernova11c/Supernova-Transformer-V2" \
        --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": "Supernova11c/Supernova-Transformer-V2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Supernova11c/Supernova-Transformer-V2 with Docker Model Runner:
```
docker model run hf.co/Supernova11c/Supernova-Transformer-V2
```

Supernova-Transformer-V2 / metadata.json

Supernova11c

Upload folder using huggingface_hub

29a4421 verified about 1 month ago

Raw History Blame Contribute Delete

771 Bytes

{
  "model": "Supernova Transformer V2",
  "organization": "Supernova11c",
  "framework": "PyTorch",
  "architecture": "Decoder-only causal Transformer",
  "vocab_size": 131,
  "hidden_size": 256,
  "attention_heads": 8,
  "layers": 4,
  "feed_forward_size": 1024,
  "max_sequence_length": 512,
  "state_dict_tensors": 53,
  "state_dict_elements": 3357696,
  "unique_trainable_parameters": 3357696,
  "embedding_lm_head": "separate_parameters",
  "best_validation_loss": 0.14225323487189598,
  "training_examples": 2601,
  "validation_examples": 289,
  "training_type": "Supervised causal language modeling",
  "loss_scope": "Assistant-only loss",
  "checkpoint_source": "supernova_transformer_v2_best.pt",
  "export_verification": "Exact tensor-by-tensor verification"
}

	{
	"model": "Supernova Transformer V2",
	"organization": "Supernova11c",
	"framework": "PyTorch",
	"architecture": "Decoder-only causal Transformer",
	"vocab_size": 131,
	"hidden_size": 256,
	"attention_heads": 8,
	"layers": 4,
	"feed_forward_size": 1024,
	"max_sequence_length": 512,
	"state_dict_tensors": 53,
	"state_dict_elements": 3357696,
	"unique_trainable_parameters": 3357696,
	"embedding_lm_head": "separate_parameters",
	"best_validation_loss": 0.14225323487189598,
	"training_examples": 2601,
	"validation_examples": 289,
	"training_type": "Supervised causal language modeling",
	"loss_scope": "Assistant-only loss",
	"checkpoint_source": "supernova_transformer_v2_best.pt",
	"export_verification": "Exact tensor-by-tensor verification"
	}