Not a "true" base model

#1
by ChuckMcSneed - opened

name-probs-bases.png
Good instruct model, but I'm skeptical of the "base". My testing shows a skewed, instruct-like bias, which is unexpected for a base model. More info: https://huggingface.co/blog/ChuckMcSneed/name-diversity-in-llms-experiment

Please don't release already pre-tuned fake base models like Qwen, but "uncontaminated" ones like DeepSeek.

Sign up or log in to comment