Iq Code Evmind V1 Granite 8b Instruct

🚀 iq-code-evmind-v1-granite-8b-instruct模型項目

本項目提供了一個基於iq-code-evmind-v1-granite-8b-instruct模型的代碼示例，可用於生成智能合約相關內容，解決了在特定場景下智能合約生成的需求，為開發者提供了便利。

🚀 快速開始

以下是使用iq-code-evmind-v1-granite-8b-instruct模型生成智能合約內容的示例代碼：

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)

💻 使用示例

基礎用法

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)

高級用法

# 可根據實際需求修改輸入的聊天內容，以生成不同的智能合約相關內容。
# 例如，可以修改用戶的提問，讓模型生成不同功能的智能合約。
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()

# 修改聊天內容
chat = [
    {
        "role": "user",
        "content": "Create a different smart contract for a decentralized voting system. This contract should allow users to vote on proposals, count votes, and ensure the fairness and transparency of the voting process."
    },
]

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)

📄 許可證

本項目使用的許可證為Apache-2.0。

📦 相關信息