metadata
license: apache-2.0
tags:
- pruned
- linux
- optimized
- wanda
- activation-pruning
base_model: LiquidAI/LFM2.5-1.2B-Thinking
pipeline_tag: text-generation
LFM2.5-1.2B-Thinking-linux-extra-light
🎯 LINUX-optimized | 📦 Extra Light pruning | ⚡ 3% weights pruned
This model is a minimally pruned version of LiquidAI/LFM2.5-1.2B-Thinking, specialized for LINUX tasks using activation-aware weight pruning (Wanda-style).
✨ Key Features
- Specialization: Optimized for Linux tasks
- Pruning Method: Wanda-style (|W| × |activation|) importance scoring
- Size Reduction: 3% weights pruned
- Use Case: Highest accuracy retention with slight size reduction
📊 Performance Comparison
| Category | Original | Pruned | Change |
|---|---|---|---|
| Python | 0.0% | 0.0% | → |
| Html | 0.0% | 0.0% | → |
| Trivia | 93.3% | 93.3% | → |
| Math | 100.0% | 100.0% | → |
| Reasoning | N/A | N/A | |
| Medical | 86.7% | 80.0% | ↓ 6.7% |
| Linux | 86.7% | 93.3% ⭐ | ↑ 6.7% |
| Writing | 60.0% | 66.7% | ↑ 6.7% |
Average: 61.0% → 61.9% (+1.0%)
Linux Retention: 107.7% of original performance
🚀 Quick Start
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained("CompactAI/LFM2.5-1.2B-Thinking-linux-extra-light")
tokenizer = AutoTokenizer.from_pretrained("CompactAI/LFM2.5-1.2B-Thinking-linux-extra-light")
# Example usage
inputs = tokenizer("Your prompt here", return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=100)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
📋 Technical Details
| Property | Value |
|---|---|
| Base Model | LiquidAI/LFM2.5-1.2B-Thinking |
| Specialization | Linux |
| Prune Mode | Extra Light |
| Pruning Method | Activation-based weight pruning (Wanda) |
| Weight Reduction | 3% weights pruned |
🔗 Related Models
This model is part of the LFM2.5-1.2B-Thinking pruned model collection. Other variants:
- Extra-light (minimal pruning)
- Light
- Medium-light
- Medium
- Medium-heavy
- Heavy
- Extra-heavy (maximum compression)
📜 License
This model inherits the license from the base model LiquidAI/LFM2.5-1.2B-Thinking.
Generated by ZANNPS [Zeto Automatic Neural Network Pruning System]