Instructions to use Von-R/VerilogProtoToken with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Von-R/VerilogProtoToken with Transformers:

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

pipe = pipeline("text-generation", model="Von-R/VerilogProtoToken")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Von-R/VerilogProtoToken")
model = AutoModelForCausalLM.from_pretrained("Von-R/VerilogProtoToken", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Von-R/VerilogProtoToken with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Von-R/VerilogProtoToken

SGLang

How to use Von-R/VerilogProtoToken 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 "Von-R/VerilogProtoToken" \
    --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": "Von-R/VerilogProtoToken",
		"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 "Von-R/VerilogProtoToken" \
        --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": "Von-R/VerilogProtoToken",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Von-R/VerilogProtoToken with Docker Model Runner:
```
docker model run hf.co/Von-R/VerilogProtoToken
```

VerilogProtoToken

File size: 358 Bytes

c16c7a7

{
    "Next Token Prediction Loss": 0.8175709573030472,
    "Perplexity": 2.2649913893200004,
    "Accuracy": 0.52189453125,
    "Precision": 0.023324851765829015,
    "Recall": 0.023883036472085516,
    "F1 Score": 0.02345157579189002,
    "Top-5 Accuracy": 0.50113671875,
    "Entropy": 0.8339920132160187,
    "Prediction Confidence": 0.8293982080221176
}