TinyLlama-1.1B-Chat-v1.0-reasoning-safe

🎯 REASONING-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	83.3%	83.3%	→
Math	0.0%	0.0%	→
Reasoning	0.0%	0.0% ⭐	→
Medical	33.3%	33.3%	→
Linux	33.3%	33.3%	→
Writing	33.3%	33.3%	→

Average: 22.9% → 22.9% (+0.0%)

Quick Start

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("CompactAI/TinyLlama-1.1B-Chat-v1.0-reasoning-safe")
tokenizer = AutoTokenizer.from_pretrained("CompactAI/TinyLlama-1.1B-Chat-v1.0-reasoning-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	TinyLlama/TinyLlama-1.1B-Chat-v1.0
Specialization	Reasoning
Prune Mode	Safe
Weight Reduction	1% weights pruned

License

This model inherits the license from the base model.