Iq Code Evmind V1 Granite 8b Instruct

🚀 IQ Code EvMind v1 Granite 8B Instruct

This project provides a model for generating smart - contract code based on user instructions, using the braindao/iq-code-evmind-v1-granite-8b-instruct model.

🚀 Quick Start

The following steps and code examples show how to use the braindao/iq-code-evmind-v1-granite-8b-instruct model to generate smart - contract code.

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
device = "cuda"
model_path = "braindao/iq-code-evmind-v1-granite-8b-instruct"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, device_map=device)
model.eval()

chat = [
    {
        "role": "user",
        "content": "Create a smart contract to serve as a centralized review system called ReviewHub. This contract should allow users to submit and manage reviews for various products or services, rate them on a scale of 1 to 5, and provide detailed comments. It should include functionalities for assigning unique identifiers to products or services, storing and retrieving reviews, allowing users to edit or delete their reviews, calculating average ratings, and enabling an administrator to moderate content. The contract must incorporate robust security measures to ensure review integrity and prevent spam or malicious activity."
    },
]

chat = tokenizer.apply_chat_template(chat, tokenize=False, add_generation_prompt=True)
input_tokens = tokenizer(chat, return_tensors="pt")
for i in input_tokens:
    input_tokens[i] = input_tokens[i].to(device)
output = model.generate(**input_tokens, max_new_tokens=4096)
output = tokenizer.batch_decode(output)
for i in output:
    print(i)

📄 License

This project is licensed under the Apache 2.0 license.

📦 Datasets

The model uses the following dataset:

• AlfredPros/smart-contracts-instructions

🔖 Tags

• ibm-granite/granite-8b-code-instruct