README.md

---
license: apache-2.0
---
![icaro](https://huggingface.co/alexsobolev/IcaroLM/resolve/main/assets/icaro.jpg)
**IcaroLM**, is a language model based on Qwen2 1.5B, designed for mobile efficiency, empathetic chat, and function calling. 
This model is optimized for fast inference and low resource consumption on mobile devices, providing a seamless and responsive user experience. 
Icaro-LM is fine-tuned for empathetic conversations and can understand and execute function calls within the conversation flow, 
making it a versatile solution for various applications.


## Key Features:

1. **Mobile Efficiency**: Optimized for fast inference and low resource consumption on mobile devices.
2. **Empathetic Chat**: Fine-tuned on datasets curated for empathetic and emotionally intelligent conversations.
3. **Function Calling**: Can understand and execute function calls within the conversation flow.

## Use Cases:

- Mobile chatbots and virtual assistants
- Emotional support applications
- Task automation on mobile devices

## Prompt format

```
<|im_start|>system
{system_prompt}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant

```

## Function calling example
```
<|im_start|>system  
You are a helpful assistant with access to the following functions. Use them if required -[{ 
   "name":"get_news", 
   "description":"Get the latest news.", 
   "parameters":{ 
      "type":"object", 
      "properties":{ 
         "location":{ 
            "type":"string", 
            "description":"The location for which to fetch news" 
         } 
      }, 
      "required":[ 
         "location" 
      ] 
   } 
}, 
{ 
  "name": "get_current_weather", 
  "description": "Get the current weather", 
  "parameters": { 
      "type": "object", 
      "properties": { 
          "location": { 
              "type": "string", 
              "description": "The city and state, e.g. San Francisco, CA" 
          }, 
      }, 
      "required": ["location"], 
  }, 
}]<|im_end|>  
<|im_start|>user  
What's the latest news in Samara?<|im_end|>  
<|im_start|>assistant
```
Result:
```
<|im_start|>assistant
<functioncall> {"name": "get_news", "arguments": '{"location": "Samara"}'}  <|im_end|>
```