# LFM2.5-230M - Core ML (fp16)

[![License: Other](https://img.shields.io/badge/License-Other-lightgrey.svg)](https://huggingface.co/code-and-canvas/lfm2.5-230m-coreML-fp16)
[![Model Size](https://img.shields.io/badge/Size-230M_Params-orange)](https://huggingface.co/code-and-canvas/lfm2.5-230m-coreML-fp16)
[![Quantization](https://img.shields.io/badge/Precision-fp16-green)](https://developer.apple.com/machine-learning/core-ml/)
[![Framework](https://img.shields.io/badge/Framework-Core_ML-blue)](https://developer.apple.com/machine-learning/)
[![Context Length](https://img.shields.io/badge/Context-128K_tokens-cyan)](https://huggingface.co/LiquidAI/LFM2.5-230M)

**A Core ML-optimized, 16-bit floating-point conversion of [LiquidAI's LFM2.5-230M](https://huggingface.co/LiquidAI/LFM2.5-230M)**, designed for **fast, on-device inference on Apple devices** (iPhone, iPad, Mac). Retains full precision for maximum accuracy while enabling seamless integration with iOS/macOS apps via Core ML.

---

## 🔍 **Model Overview**

| Feature               | Details                                                                                     |
|----------------------|---------------------------------------------------------------------------------------------|
| **Base Model**       | [`LiquidAI/LFM2.5-230M-Base`](https://huggingface.co/LiquidAI/LFM2.5-230M-Base)               |
| **Fine-tuned Model** | [`LiquidAI/LFM2.5-230M`](https://huggingface.co/LiquidAI/LFM2.5-230M)                       |
| **Precision**        | **fp16** (16-bit floating point)                                                            |
| **Framework**        | **Core ML** (Apple's machine learning framework)                                           |
| **Architecture**     | `Lfm2ForCausalLM` (Hybrid: **8× Double-Gated LIV Convolution + 6× Grouped-Query Attention**) |
| **Parameters**       | **230M**                                                                                   |
| **Context Length**   | **128,000 tokens**                                                                         |
| **Vocabulary**       | 65,536 tokens                                                                              |
| **License**          | **Other** (Check [LiquidAI](https://www.liquid.ai/) for details)                           |
| **Download Size**    | ~1.06 GB (`.mlpackage` + `.safetensors`)                                                   |

---

## 🎯 **Capabilities**

✅ **On-Device Inference** – Optimized for **Apple Silicon** (iPhone, iPad, Mac) via Core ML.
✅ **Blazing Fast** – **213 tok/s** on Galaxy S25 Ultra, **42 tok/s** on Raspberry Pi 5 (LiquidAI benchmarks).
✅ **Efficient Architecture** – Hybrid **convolution + attention** layers for speed and accuracy.
✅ **Long Context** – **128K token** context window (32K extension phase included in training).
✅ **General-Purpose** – Text-only model trained on **19T tokens** with **distillation, DPO, and RL**.
✅ **Agentic-Ready** – Designed for **agent workflows, automation, and edge deployment**.

---

## 📊 **Performance Highlights**

| Metric                     | Value                          | Notes                                                                 |
|----------------------------|--------------------------------|-----------------------------------------------------------------------|
| **Parameters**             | 230M                           | Compact yet powerful.                                                 |
| **Layers**                 | 14                             | 8× Convolution (LIV) + 6× Grouped-Query Attention (GQA).                |
| **Hidden Size**            | 1,024                          |                                                                       |
| **Intermediate Size**      | 2,560                          |                                                                       |
| **Attention Heads**        | 16 (8 KV heads)                | Grouped-Query Attention for efficiency.                              |
| **Pre-training Tokens**    | **19T**                        | Including 32K context extension phase.                                |
| **Post-Training**          | SFT + DPO + Multi-Domain RL    | Distilled from **LFM2.5-350M** for competitive performance.            |
| **Speed (Edge)**           | **213 tok/s** (S25 Ultra)      | **42 tok/s** (Raspberry Pi 5).                                         |

> 💡 **Why LFM2.5?**
> - **Faster than SSM hybrids & Gated Delta Networks** of similar size.
> - **Runs everywhere**: Cloud GPUs → CPUs → Mobile devices.
> - **Day-one ecosystem support**: llama.cpp, MLX, vLLM, SGLang, ONNX, **Core ML**.

---

## 🚀 **Quick Start**

---

### **🍎 1. Use in iOS/macOS Apps (Core ML)**
#### **Prerequisites**
- Xcode 15+
- macOS 14+ / iOS 17+
- Core ML framework

#### **Step 1: Download the Model**
```bash
git lfs install
git clone https://huggingface.co/code-and-canvas/lfm2.5-230m-coreML-fp16
cd lfm2.5-230m-coreML-fp16
```

#### **Step 2: Integrate into Xcode**
1. Drag `model.mlpackage` into your Xcode project.
2. Ensure it's added to your **target's "Build Phases" → "Copy Bundle Resources"**.
3. Import Core ML in your Swift code:

```swift
import CoreML

// Load the model
guard let modelURL = Bundle.main.url(forResource: "model", withExtension: "mlpackage") else {
    fatalError("Model file not found")
}

do {
    let model = try MLModel(contentsOf: modelURL)
    // Use the model for inference
    let input = try MLDictionaryFeatureProvider(dictionary: ["input": "Your prompt here"])
    let prediction = try model.prediction(from: input)
    // Handle output
} catch {
    print("Error loading model: \(error)")
}
```

#### **Step 3: Use with `coremltools` (Python)**
```python
import coremltools as ct

# Load the model
model = ct.models.MLModel("model.mlpackage")

# Run inference
input_data = {"input": "What is the capital of France?"}
prediction = model.predict(input_data)
print(prediction)
```

---

### **🐍 2. Use with Transformers (Hugging Face Format)**
The repository includes **both Core ML and Hugging Face formats** (`hf_model/`).

#### **Install Dependencies**
```bash
pip install transformers torch
```

#### **Load and Run**
```python
from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "code-and-canvas/lfm2.5-230m-coreML-fp16"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    device_map="auto",
    torch_dtype="auto"
)

# Generate text
inputs = tokenizer("Write a haiku about coding:", return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=50)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
```

#### **Streaming Generation**
```python
from transformers import TextStreamer

streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
outputs = model.generate(**inputs, streamer=streamer, max_new_tokens=100)
```

---

### **3. Command Line (llama.cpp)**
If you convert to GGUF:
```bash
# Example (requires GGUF conversion first)
llama-cli -m lfm2.5-230m-fp16.gguf -p "Explain quantum computing simply."
```

---

## 🛠️ **Configuration**

### **Model Architecture**
| Setting                     | Value                     |
|----------------------------|---------------------------|
| **Architecture**           | `Lfm2ForCausalLM`         |
| **Layers**                 | 14 (8× Conv + 6× GQA)     |
| **Hidden Size**            | 1,024                     |
| **Intermediate Size**      | 2,560                     |
| **Attention Heads**        | 16                        |
| **Key-Value Heads**        | 8                         |
| **Vocabulary Size**        | 65,536                    |
| **Max Position Embeddings** | 128,000                 |
| **ROPE Theta**             | 1,000,000                 |
| **Tie Word Embeddings**    | True                      |
| **Use Cache**              | True                      |

### **Generation Config (Default)**
```json
{
  "bos_token_id": 1,
  "eos_token_id": 7,
  "pad_token_id": 0,
  "do_sample": true,
  "temperature": 0.1,
  "top_k": 50,
  "repetition_penalty": 1.05,
  "use_cache": true
}
```

### **Special Tokens**
| Token Type | ID |
|------------|----|
| **BOS**    | 1  |
| **EOS**    | 7  |
| **PAD**    | 0  |

---

## 📁 **Files**
| File                          | Description                                                                 |
|-------------------------------|-----------------------------------------------------------------------------|
| `model.mlpackage/`            | **Core ML model** (for iOS/macOS integration).                              |
| `hf_model/config.json`        | Hugging Face model configuration.                                           |
| `hf_model/generation_config.json` | Default generation parameters.                                          |
| `hf_model/model.safetensors` | Model weights in safetensors format (fp16).                                |
| `hf_model/tokenizer.json`     | Tokenizer configuration.                                                   |
| `hf_model/tokenizer_config.json` | Tokenizer metadata.                                                     |
| `model_config.json`           | Core ML model configuration.                                               |

---

## 🔧 **Use Cases**

### **✅ Recommended**
- **On-Device AI Apps** – Deploy on **iPhone, iPad, or Mac** with Core ML.
- **Edge Deployment** – Run on **Raspberry Pi, Jetson, or low-power devices**.
- **Agentic Workflows** – Lightweight model for **automation, chatbots, or tools**.
- **Local Inference** – Fast, private inference **without cloud dependency**.
- **Prototyping** – Quickly test ideas **offline or on-device**.

### **⚠️ Considerations**
| Aspect               | LFM2.5-230M (fp16) |
|----------------------|--------------------|
| **Size**             | ~1.06 GB           |
| **Speed**            | **Very Fast** (213 tok/s on high-end mobile) |
| **Accuracy**         | Competitive with larger models (thanks to distillation) |
| **Context**          | **128K tokens** (long conversations, documents) |
| **Multimodal**       | ❌ Text-only        |
| **Fine-Tunable**     | ✅ Yes (Hugging Face format included) |

> 💡 **Why choose this over larger models?**
> - **Speed**: Optimized for **real-time on-device inference**.
> - **Size**: Fits on **mobile devices** with limited storage.
> - **Efficiency**: Lower **power consumption** and **memory usage**.

---

## 🔄 **Training & Architecture Details**

### **Base Model**
- **Original**: [`LiquidAI/LFM2.5-230M-Base`](https://huggingface.co/LiquidAI/LFM2.5-230M-Base)
- **Pre-training**: **19T tokens**, including **32K context extension phase**.

### **Post-Training (LFM2.5-230M)**
1. **Supervised Fine-Tuning (SFT)** – Distilled from **LFM2.5-350M**.
2. **Direct Preference Optimization (DPO)** – Alignment for quality.
3. **Multi-Domain Reinforcement Learning (RL)** – Flexibility for downstream tasks.

### **Architecture (LFM2)**
- **Hybrid Design**: Combines **convolution (LIV blocks)** and **attention (GQA)**.
- **Double-Gated LIV Convolution**: 8 layers for **efficient sequence processing**.
- **Grouped-Query Attention (GQA)**: 6 layers for **scalable attention**.
- **Efficiency**: Faster than **SSM hybrids** and **Gated Delta Networks** of similar size.

### **Core ML Conversion**
- **Precision**: **fp16** (16-bit floating point) for **balance of speed and accuracy**.
- **Compatibility**: Works on **all Apple devices** supporting Core ML.
- **Format**: `.mlpackage` (modern Core ML bundle format).

---
---
## 📜 **License**
**Other** – Refer to [LiquidAI's terms](https://www.liquid.ai/) for usage rights.
(Original LFM2.5 models may have specific licensing; verify before commercial use.)

---
---
## 🙏 **Acknowledgments**
- **Base Model**: [LiquidAI/LFM2.5-230M](https://huggingface.co/LiquidAI/LFM2.5-230M) (Liquid AI).
- **Architecture**: [LFM2](https://www.liquid.ai/blog/lfm2-5-230m) (Hybrid convolution + attention).
- **Core ML**: [Apple Core ML](https://developer.apple.com/machine-learning/) framework.
- **Conversion**: Powered by `coremltools` and Hugging Face ecosystem.

---
---
## 💬 **Example Prompts**

### **General Q&A**
```text
What are the key differences between Python and JavaScript?
```

### **Coding**
```text
Write a Python function to reverse a linked list in-place.
```

### **Creative Writing**
```text
Write a short story about a robot discovering emotions.
```

### **Agentic Tasks**
```text
Act as a personal assistant. My calendar is empty tomorrow. Suggest 3 productive things I could do.
```

### **Long Context**
```text
Here's a 500-line Python script. Can you:
1. Summarize what it does.
2. Identify potential bugs.
3. Suggest improvements.
[Insert long script here...]
```

---
---
## 🐛 **Issues & Support**
- **Bugs**: Open an issue on the [repository](https://huggingface.co/code-and-canvas/lfm2.5-230m-coreML-fp16).
- **Questions**: Ask in [Discussions](https://huggingface.co/code-and-canvas).
- **Contributions**: PRs welcome!

---
---
## 📚 **Additional Resources**
- [LiquidAI LFM2.5 Blog Post](https://www.liquid.ai/blog/lfm2-5-230m)
- [Core ML Documentation](https://developer.apple.com/machine-learning/)
- [Hugging Face LFM2.5-230M](https://huggingface.co/LiquidAI/LFM2.5-230M)
- [MarkTechPost Coverage](https://www.marktechpost.com/2026/06/27/liquid-ai-ships-lfm2-5-230m)

---
**🚀 Happy Building!**
*Built with ❤️ by [Code and Canvas](https://huggingface.co/code-and-canvas).*