Kunorzn Llama 3 3B

🚀 KunoRZN-Llama-3-3B

KunoRZN-Llama-3-3B 是 VinkuraAI 推出的一款強大的語言模型，它支持 12 種以上印度語言以及英語。該模型結合了“直覺式”傳統模式響應和長鏈思維推理響應，用戶可通過系統提示進行切換，能廣泛應用於教育、醫療、交通管理等多個領域，為印度地區提供了便捷且強大的 AI 能力。

🚀 快速開始

模型信息

示例配置

{
    "example_title": "KunoRZN",
    "messages": [
        {
            "role": "system",
            "content": "You are KunoRZN, a multilingual AI assistant fluent in both English and Indian languages, designed to help with education, healthcare information, and daily tasks."
        },
        {
            "role": "user",
            "content": "मुझे भारत के शिक्षा प्रणाली के बारे में बताएं।"
        }
    ]
}

推理基準

評估指標

在 IndicGLUE 數據集上進行文本生成任務，平均準確率達到 79.8%。

✨ 主要特性

• 多語言支持：支持 12 種以上印度語言和英語，打破語言障礙，為不同地區用戶提供服務。
• 混合推理模式：統一“直覺式”傳統模式響應和長鏈思維推理響應，用戶可通過系統提示靈活切換。
• 廣泛應用場景：適用於教育、醫療信息傳遞、交通管理系統等多個領域，滿足不同場景需求。
• 低資源適配：能夠在印度常見的低資源計算環境中運行。

📦 安裝指南

使用 vLLM 運行該模型，首先確保已安裝 vLLM：

pip install vllm

然後在終端運行以下命令：

vllm serve VinkuraAI/KunoRZN-Llama-3-3B

💻 使用示例

基礎用法

深度思考模式

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
import flash_attn
import time

tokenizer = AutoTokenizer.from_pretrained("VinkuraAI/KunoRZN-Llama-3-3B")

model = AutoModelForCausalLM.from_pretrained(
    "VinkuraAI/KunoRZN-Llama-3-3B",
    torch_dtype=torch.float16,
    device_map="auto",
    attn_implementation="flash_attention_2",
)

messages = [
    {
        "role": "system",
        "content": "You are a deep thinking AI assistant who can communicate in multiple Indian languages. You may use extremely long chains of thought to deeply consider the problem and deliberate with yourself via systematic reasoning processes to help come to a correct solution prior to answering. You should enclose your thoughts and internal monologue inside <thinking> </thinking> tags, and then provide your solution or response to the problem."
    },
    {
        "role": "user",
        "content": "भारतीय संविधान के मूल अधिकारों के बारे में बताइए और उनका महत्व समझाइए।"
    }
]

input_ids = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors='pt').to("cuda")
generated_ids = model.generate(input_ids, max_new_tokens=3000, temperature=0.8, repetition_penalty=1.1, do_sample=True, eos_token_id=tokenizer.eos_token_id)
print(f"Generated Tokens: {generated_ids.shape[-1:]}")
response = tokenizer.decode(generated_ids[0], skip_special_tokens=True, clean_up_tokenization_space=True)
print(f"Response: {response}")

⚠️ 重要提示

對於複雜推理任務，KunoRZN 在思考過程中可能會使用多達 10,000 個標記。對於難題，您可能需要增加 max_new_tokens 的值。

標準“直覺式”響應模式

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
import flash_attn
import time

tokenizer = AutoTokenizer.from_pretrained("VinkuraAI/KunoRZN-Llama-3-3B")

model = AutoModelForCausalLM.from_pretrained(
    "VinkuraAI/KunoRZN-Llama-3-3B",
    torch_dtype=torch.float16,
    device_map="auto",
    attn_implementation="flash_attention_2",
)

messages = [
    {
        "role": "system",
        "content": "You are KunoRZN, a multilingual AI assistant fluent in both English and Indian languages."
    },
    {
        "role": "user",
        "content": "தமிழ்நாட்டில் உள்ள பிரபலமான சுற்றுலா தலங்கள் என்ன?"
    }
]

input_ids = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors='pt').to("cuda")
generated_ids = model.generate(input_ids, max_new_tokens=2500, temperature=0.8, repetition_penalty=1.1, do_sample=True, eos_token_id=tokenizer.eos_token_id)
print(f"Generated Tokens: {generated_ids.shape[-1:]}")
response = tokenizer.decode(generated_ids[0], skip_special_tokens=True, clean_up_tokenization_space=True)
print(f"Response: {response}")

高級用法

多語言用例

教育領域

messages = [
    {
        "role": "system",
        "content": "You are KunoRZN, an educational AI assistant that can explain concepts in simple terms for students."
    },
    {
        "role": "user",
        "content": "ಸೌರವ್ಯೂಹದ ಗ್ರಹಗಳ ಬಗ್ಗೆ ವಿವರಿಸಿ."
    }
]

醫療領域

messages = [
    {
        "role": "system",
        "content": "You are KunoRZN, a healthcare information assistant. Provide general health information while always recommending consultation with healthcare professionals."
    },
    {
        "role": "user",
        "content": "ডায়াবেটিস রোগের লক্ষণগুলি কী কী?"
    }
]

交通管理領域

messages = [
    {
        "role": "system",
        "content": "You are KunoRZN, a traffic management assistant. Help users navigate local traffic conditions and understand traffic rules."
    },
    {
        "role": "user",
        "content": "मुंबई में ट्रैफिक जाम से बचने के लिए क्या सुझाव हैं?"
    }
]

函數調用

使用特定系統提示和結構進行函數調用，示例如下：

<|start_header_id|>system<|end_header_id|>
You are a function calling AI model fluent in multiple Indian languages. You are provided with function signatures within <tools></tools> XML tags. You may call one or more functions to assist with the user query. Don't make assumptions about what values to plug into functions. Here are the available tools: <tools> {"type": "function", "function": {"name": "get_weather", "description": "get_weather(city: str, state: str, country: str='India') -> dict - Get weather information for a given city.\\n\\n    Args:\\n        city (str): The city name.\\n        state (str): The state name.\\n        country (str): The country name, defaults to India.\\n\\n    Returns:\\n        dict: A dictionary containing weather information.\\n            Keys:\\n                - \'city\': The city name.\\n                - \'state\': The state name.\\n                - \'temperature\': The current temperature in Celsius.\\n                - \'humidity\': The current humidity percentage.\\n                - \'description\': Weather description.\\n                - \'forecast\': Forecast for next 3 days.", "parameters": {"type": "object", "properties": {"city": {"type": "string"}, "state": {"type": "string"}, "country": {"type": "string"}}, "required": ["city", "state"]}}}  </tools> Use the following pydantic model json schema for each tool call you will make: {"properties": {"arguments": {"title": "Arguments", "type": "object"}, "name": {"title": "Name", "type": "string"}}, "required": ["arguments", "name"], "title": "FunctionCall", "type": "object"} For each function call return a json object with function name and arguments within <tool_call></tool_call> XML tags as follows:
<tool_call>
{"arguments": <args-dict>, "name": <function-name>}
</tool_call><|eot_id|><|start_header_id|>user<|end_header_id|>

📚 詳細文檔

量化版本

GGUF 量化版本：https://huggingface.co/VinkuraAI/KunoRZN-Llama-3-3B-GGUF

引用方式

@misc{
      title={KunoRZN-Llama-3-3B}, 
      author={VinkuraAI},
      year={2025}
}

📄 許可證

KunoRZN-Llama-3-3B 基於 Meta Llama 3 構建，並遵循 Meta Llama 3 社區許可證，版權所有 © Meta Platforms, Inc. 保留所有權利。

🔗 聯繫與支持

如需更多信息和支持，請訪問 vinkura.in 或通過 support@vinkura.in 聯繫我們。