Falcon-H1-Tiny-R-0.6B
Collection
Pruned models based on tiiuae/Falcon-H1-Tiny-R-0.6B
β’
12 items
β’
Updated
TRIVIA-optimized | Aggressive pruning | 35% weights pruned
This model is a aggressively 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!
| Category | Original | Pruned | Change |
|---|---|---|---|
| Python | 0.0% | 0.0% | β |
| Html | 0.0% | 0.0% | β |
| Trivia | 0.0% | 0.0% β | β |
| Math | 0.0% | 0.0% | β |
| Reasoning | 0.0% | 0.0% | β |
| Medical | 0.0% | 0.0% | β |
| Linux | 0.0% | 0.0% | β |
| Writing | 0.0% | 0.0% | β |
Average: 0.0% -> 0.0% (+0.0%)
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained("CompactAI/Falcon-H1-Tiny-R-0.6B-trivia-aggressive")
tokenizer = AutoTokenizer.from_pretrained("CompactAI/Falcon-H1-Tiny-R-0.6B-trivia-aggressive")
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))
| Property | Value |
|---|---|
| Base Model | tiiuae/Falcon-H1-Tiny-R-0.6B |
| Specialization | Trivia |
| Prune Mode | Aggressive |
| Weight Reduction | 35% weights pruned |
This model inherits the license from the base model.
Base model
tiiuae/Falcon-H1-Tiny-R-0.6B