metadata
license: apache-2.0
tags:
- pruned
- linux
- optimized
- wanda
base_model: tiiuae/Falcon-H1-Tiny-R-0.6B
pipeline_tag: text-generation
Falcon-H1-Tiny-R-0.6B-linux-safe
LINUX-optimized | Safe pruning | 30% weights pruned
This model is a conservatively pruned version of tiiuae/Falcon-H1-Tiny-R-0.6B.
Pruning Alert: The benchmarks show virtually NO quality drop! This isn't a bug -- it is a feature. The Wanda pruning algorithm is so effective at identifying unimportant weights that it can remove a large percentage of parameters without affecting performance. Think of it like pruning dead leaves from a tree -- the tree does not miss them because they were not doing anything anyway!
Performance Comparison
| Category | Original | Pruned | Change |
|---|---|---|---|
| Python | 0.0% | 0.0% | → |
| Html | 0.0% | 0.0% | → |
| Trivia | 0.0% | 0.0% | → |
| 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: 0.0% -> 0.0% (+0.0%)
Quick Start
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained("CompactAI/Falcon-H1-Tiny-R-0.6B-linux-safe")
tokenizer = AutoTokenizer.from_pretrained("CompactAI/Falcon-H1-Tiny-R-0.6B-linux-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 | tiiuae/Falcon-H1-Tiny-R-0.6B |
| Specialization | Linux |
| Prune Mode | Safe |
| Weight Reduction | 30% weights pruned |
License
This model inherits the license from the base model.