Text Generation
Transformers
Safetensors
English
codegen
Solidity
BlockChain
Smart Contracts
Code Generation
Instructions to use Chain-GPT/Solidity-LLM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Chain-GPT/Solidity-LLM with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Chain-GPT/Solidity-LLM")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Chain-GPT/Solidity-LLM") model = AutoModelForCausalLM.from_pretrained("Chain-GPT/Solidity-LLM", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Chain-GPT/Solidity-LLM with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Chain-GPT/Solidity-LLM" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Chain-GPT/Solidity-LLM", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Chain-GPT/Solidity-LLM
- SGLang
How to use Chain-GPT/Solidity-LLM 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 "Chain-GPT/Solidity-LLM" \ --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": "Chain-GPT/Solidity-LLM", "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 "Chain-GPT/Solidity-LLM" \ --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": "Chain-GPT/Solidity-LLM", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Chain-GPT/Solidity-LLM with Docker Model Runner:
docker model run hf.co/Chain-GPT/Solidity-LLM
Upload folder using huggingface_hub
Browse files
README.md
CHANGED
|
@@ -52,8 +52,8 @@ Model is deployed on huggingface space for inference
|
|
| 52 |
We have compared our model with the following models
|
| 53 |
- GPT 4.5 Preview
|
| 54 |
- GPT 4o mini
|
| 55 |
-
-
|
| 56 |
-
- DeepSeek-Coder-7B-Instruct-v1.5
|
| 57 |
|
| 58 |
On the following parameters
|
| 59 |
- **Compilation(%)** - Percentage of generated contracts that compile successfully without modification.
|
|
@@ -68,9 +68,9 @@ Below is a figure summarizing the performance of each model across the four eval
|
|
| 68 |
|
| 69 |
Following obvservation were made regarding Solidity LLM.
|
| 70 |
- Highest Compilation Success Rate (~83%), demonstrating strong Solidity syntax and structure generation.
|
| 71 |
-
- Good OpenZeppelin Compliance (~65%), indicating frequent use of standard libraries and contract patterns.
|
| 72 |
- Top Gas Efficiency (~72%), producing optimized code as evaluated by tools like Slither.
|
| 73 |
-
- Moderate Security Score (~58%), showing acceptable security posture but room for improvement.
|
| 74 |
- Concise Code (~70% LOC score), generating relatively compact and efficient smart contracts.
|
| 75 |
|
| 76 |
|
|
|
|
| 52 |
We have compared our model with the following models
|
| 53 |
- GPT 4.5 Preview
|
| 54 |
- GPT 4o mini
|
| 55 |
+
- [Qwen 2.5-Coder-7B](https://huggingface.co/Qwen/Qwen2.5-Coder-7B)
|
| 56 |
+
- [DeepSeek-Coder-7B-Instruct-v1.5](https://huggingface.co/deepseek-ai/deepseek-coder-7b-instruct-v1.5)
|
| 57 |
|
| 58 |
On the following parameters
|
| 59 |
- **Compilation(%)** - Percentage of generated contracts that compile successfully without modification.
|
|
|
|
| 68 |
|
| 69 |
Following obvservation were made regarding Solidity LLM.
|
| 70 |
- Highest Compilation Success Rate (~83%), demonstrating strong Solidity syntax and structure generation.
|
| 71 |
+
- Good OpenZeppelin Compliance (~65%), indicating frequent use of standard libraries and contract patterns. While GPT-4.5, being a much larger model, naturally exhibits stronger adherence to OpenZeppelin standards due to its broader training data, Solidity LLM achieves commendable compliance given its smaller size.
|
| 72 |
- Top Gas Efficiency (~72%), producing optimized code as evaluated by tools like Slither.
|
| 73 |
+
- Moderate Security Score (~58%), showing acceptable security posture but room for improvement. GPT-4.5 benefits from its scale in handling more security cases.
|
| 74 |
- Concise Code (~70% LOC score), generating relatively compact and efficient smart contracts.
|
| 75 |
|
| 76 |
|