Instructions to use Guilherme34/Firefly-V2Q-Beta-ALL-Loras with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Guilherme34/Firefly-V2Q-Beta-ALL-Loras with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Guilherme34/Firefly-V2Q-Beta-ALL-Loras", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Unsloth Desktop
another firefly
#1
by simonko912 - opened
another? Lol
its just the loras, this new one is gonna almost the final version of the qwen3.5 vrsion
its just the loras, this new one is gonna almost the final version of the qwen3.5 vrsion
great hope it's gonna be good
Guilherme34/Firefly-V2Q-Think-RP thinking version here
Guilherme34/Firefly-V2Q-Think-RP thinking version here
How much params?