Instructions to use bespokelabs/Bespoke-Nimble-9B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use bespokelabs/Bespoke-Nimble-9B with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3.5-9B") model = PeftModel.from_pretrained(base_model, "bespokelabs/Bespoke-Nimble-9B") - Notebooks
- Google Colab
- Kaggle
Request to Evaluate and Include DibaOne-X1 in the Bespoke Nimble 9B Benchmark
Hello Bespoke Labs team,
I would like to request that DibaOne-X1, our open-weight language model developed by Dibachain, be evaluated and considered for inclusion in the benchmark results for Bespoke-Nimble-9B.
Model: DibaOne-X1
Hugging Face: https://huggingface.co/Dibachain/DibaOne-X1
Organization: Dibachain
Model family: DibaOne
We would be happy to provide any additional information, model configuration, inference parameters, or evaluation details required to reproduce the results and ensure a fair comparison.
Including DibaOne-X1 would allow the model to be evaluated alongside other models under the same benchmark methodology and provide a more transparent comparison of its capabilities.
Thank you for your work on the benchmark and for considering DibaOne-X1 for evaluation.
Best regards,
Dibachain AI Research Team
https://dibachain.ir/