It's more compliant with unaligned requests than the original, I believe, but you may still stumble upon times when it doesn't comply with certain requests.
Going to try and make it even more compliant and release another version when I get the chance.
Important note: This model is a quant of the original, specifically Llama-3.2-1B-Instruct-Q8_0
base_model: - meta-llama/Llama-3.2-1B-Instruct
- Downloads last month
- 125
Hardware compatibility
Log In
to view the estimation
We're not able to determine the quantization variants.
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
Model tree for ironvin/Llama3.2-1b-Instruct-Heretic-GGUF
Base model
meta-llama/Llama-3.2-1B-Instruct