Very strange that they did not encode the stop string "" as a special token.
this post was submitted on 11 Mar 2025
18 points (100.0% liked)
LocalLLaMA
2748 readers
19 users here now
Welcome to LocalLLama! This is a community to discuss local large language models such as LLama, Deepseek, Mistral, and Qwen.
Get support from the community! Ask questions, share prompts, discuss benchmarks, get hyped at the latest and greatest model releases! Enjoy talking about our awesome hobby.
As ambassadors of the self-hosting machine learning community, we strive to support eachother and share our enthusiasm in a positive constructive way.
founded 2 years ago
MODERATORS