Clarification on Commencis/Commencis-LLM training origin

#1
by dqdw - opened

Dear [Developer/Team],

I've been using Commencis/Commencis-LLM recently, and I find it quite useful for my tasks.

As I am planning to build upon this model, I would like to clarify its relationship with mistralai/Mistral-7B-Instruct-v0.1 based on the model tree on Hugging Face:

Direct Fine-tuning: Is Commencis/Commencis-LLM a direct fine-tuned version of mistralai/Mistral-7B-Instruct-v0.1, or were there intermediate models/checkpoints involved?

Inheritance: Was there any merging or distillation involved?

This would help me ensure I use the model correctly.

Appreciate your support!

Sign up or log in to comment