Instructions to use shailja/fine-tuned-codegen-16B-Verilog with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use shailja/fine-tuned-codegen-16B-Verilog with Transformers:

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

pipe = pipeline("text-generation", model="shailja/fine-tuned-codegen-16B-Verilog")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("shailja/fine-tuned-codegen-16B-Verilog")
model = AutoModelForCausalLM.from_pretrained("shailja/fine-tuned-codegen-16B-Verilog")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use shailja/fine-tuned-codegen-16B-Verilog with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "shailja/fine-tuned-codegen-16B-Verilog"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "shailja/fine-tuned-codegen-16B-Verilog",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/shailja/fine-tuned-codegen-16B-Verilog

SGLang

How to use shailja/fine-tuned-codegen-16B-Verilog 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 "shailja/fine-tuned-codegen-16B-Verilog" \
    --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": "shailja/fine-tuned-codegen-16B-Verilog",
		"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 "shailja/fine-tuned-codegen-16B-Verilog" \
        --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": "shailja/fine-tuned-codegen-16B-Verilog",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use shailja/fine-tuned-codegen-16B-Verilog with Docker Model Runner:
```
docker model run hf.co/shailja/fine-tuned-codegen-16B-Verilog
```

VeriGen

Model Summary
Use
Limitations
Training
License
Citation

Model Summary

The VeriGen model is 16B parameter models fine-tuned version of CodeGen-multi-16B trained on Verilog code dataset .

Repository: shailja-thakur/VGen
Baseline LLM SalesForce/CodeGen
Paper: Benchmarking Large Language Models for Automated Verilog RTL Code Generation
Point of Contact: contact@shailja
Languages: Verilog (Hardware Description Language)

Use

Intended use

The model was trained on Verilog from GitHub and textbooks. As such it is not an instruction model and commands like "Write a module that implements a 2-to-1 Mux." do not work well. However, by additing a partial line of module header like "module mux" in addition with the text in the prompt turns it into a capable Verilog teaching assistant.

Feel free to share your generations in the Community tab!

Generation

# pip install -q transformers
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
# Prompt
prompt = "//module half adder "
device='cuda'
# Load model and tokenizer
model_name = "shailja/fine-tuned-codegen-16B-Verilog"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name).to(device)

# Sample
input_ids = tokenizer(prompt, return_tensors="pt").input_ids.to(device)
sample = model.generate(input_ids, max_length=128, temperature=0.5, top_p=0.9)

print(tokenizer.decode(sample[0], truncate_before_pattern=[r"endmodule"]) + "endmodule")

Attribution & Other Requirements

The pretraining dataset of the model was not filtered for permissive licenses only. Nevertheless, the model can generate source code verbatim from the dataset. The code's license might require attribution and/or other specific requirements that must be respected.

Limitations

The model has been trained on Verilog source code from open sources. The predominant natural language in source code is English, although other languages are also present. As such the model is capable of generating Verilog snippets provided some context but the generated code is not guaranteed to work as intended. It can be inefficient, contain bugs or exploits. See the paper for an in-depth discussion of the model limitations.

Training

Model

Architecture: GPT-2 model with multi-query attention
Pretraining steps: 150k
Pretraining tokens: ~72B
Precision: fp16

Hardware

GPUs: 4 Tesla A100
Training time: 15 days

License

The model is licensed under the BigCode OpenRAIL-M v1 license agreement. You can find the full agreement here.

Citation

@misc{https://doi.org/10.48550/arxiv.2212.11140,
  doi = {10.48550/ARXIV.2212.11140},
  url = {https://arxiv.org/abs/2212.11140},
  author = {Thakur, Shailja and Ahmad, Baleegh and Fan, Zhenxing and Pearce, Hammond and Tan, Benjamin and Karri, Ramesh and Dolan-Gavitt, Brendan and Garg, Siddharth},
  title = {Benchmarking Large Language Models for Automated Verilog RTL Code Generation},
  publisher = {arXiv},
  year = {2022},
  copyright = {arXiv.org perpetual, non-exclusive license}
}

Downloads last month: 1,210

Dataset used to train shailja/fine-tuned-codegen-16B-Verilog

Paper for shailja/fine-tuned-codegen-16B-Verilog

Benchmarking Large Language Models for Automated Verilog RTL Code Generation

Paper • 2212.11140 • Published Dec 13, 2022 • 1

Evaluation results

pass@1 on VeriEval (Prompted)
self-reported

shailja
/

fine-tuned-codegen-16B-Verilog