EXAONE-3.5-2.4B-Instruct-python-safe

🎯 PYTHON-optimized | 📦 Safe pruning | ⚡ 1% weights pruned

This model is a conservatively pruned version of TinyLlama/TinyLlama-1.1B-Chat-v1.0.

Performance Comparison

Category	Original	Pruned	Change
Python	0.0%	0.0% ⭐	→
Html	0.0%	0.0%	→
Trivia	11.1%	11.1%	→
Math	0.0%	0.0%	→
Reasoning	0.0%	0.0%	→
Medical	0.0%	0.0%	→
Linux	0.0%	0.0%	→
Writing	0.0%	0.0%	→

Average: 1.4% → 1.4% (+0.0%)

Quick Start

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("CompactAI/EXAONE-3.5-2.4B-Instruct-python-safe")
tokenizer = AutoTokenizer.from_pretrained("CompactAI/EXAONE-3.5-2.4B-Instruct-python-safe")

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	Qwen/Qwen2.5-0.5B,TinyLlama/TinyLlama-1.1B-Chat-v1.0,Qwen/Qwen3-1.7B,HuggingFaceTB/SmolLM3-3B,Qwen/Qwen3-0.6B,Qwen/Qwen2.5-3B-Instruct,LGAI-EXAONE/EXAONE-3.5-2.4B-Instruct
Specialization	Python
Prune Mode	Safe
Weight Reduction	1% weights pruned

License

This model inherits the license from the base model.