Files
IcaroLM/README.md
ModelHub XC 1a9ad1b646 初始化项目,由ModelHub XC社区提供模型
Model: alexsobolev/IcaroLM
Source: Original Platform
2026-09-06 00:36:23 +08:00

78 lines
2.6 KiB
Markdown

---
license: apache-2.0
---
![icaro](https://huggingface.co/alexsobolev/IcaroLM/resolve/main/assets/icaro.jpg)
# IcaroLM
IcaroLM is a fine-tuned and quantized version of Qwen2 1.5B, designed specifically for on-device mobile applications. By leveraging a 1.5B parameter architecture and quantization, the model is approximately **600MB** in size, making it practical for local deployment on smartphones and edge devices without requiring cloud connectivity.
IcaroLM has been fine-tuned for two primary objectives: maintaining emotionally intelligent conversations and executing reliable function calls within a chat flow.
## Key Features
- **Mobile-Ready Footprint:** The quantized model is roughly 600MB, allowing for efficient storage and inference on consumer mobile hardware.
- **Function Calling:** Explicitly fine-tuned to understand and execute function calls, enabling local task automation and tool use.
- **Empathetic Chat:** Trained on datasets curated for emotional intelligence, allowing for more natural and supportive interactions compared to base models.
## Use Cases
- **Mobile Assistants:** Local chatbots that can perform actions on the device (via function calling) without sending data to the server.
- **Emotional Support Apps:** Companion applications requiring a more empathetic and nuanced conversational tone.
- **Edge Automation:** Task-oriented agents that need to run locally with low latency.
## 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|>
```