Which model is running in the demo, please?
Hello,
could you please let us know which model is running in the demo at https://blossom-chat.com/?
I'm very curious, because considering the model sizes in your collection, even if it was the largest one, the response it gave me to a specific prompt was probably the best one I received so far from any open weight model I ever tried.
Usually only big cloud models provide that level of precision.
Thank you in advance.
Thank you for your appreciation! Actually, due to cost constraints, the model running on https://blossom-chat.com/ is Blossom-V6.1-32B-AWQ, which is a quantized version of Blossom-V6.1-32B. If you have more VRAM available, you might want to try the non-quantized version, as it typically delivers better performance. Additionally, for daily tasks, Blossom-V6.1-GLM-32B often performs even better.
@MrDevolver You can also find another demo of it here: https://huggingface.co/spaces/Azure99/Blossom-V6.1-32B-AWQ-Demo