Text Generation
GGUF
English
Prototype
8X3B MOE
mixture of experts
reasoning
thinking
thoughts
deepseek
Mixture of Experts
context 128k
Llama 3.2 MOE
creative
creative writing
general usage
problem solving
brainstorming
solve riddles
fiction writing
plot generation
sub-plot generation
story generation
scene continue
storytelling
fiction story
story
writing
fiction
roleplaying
llama 3.2
mergekit
Merge
Inference Endpoints
conversational
Repetition for long token generation.
#1
by
lazyDataScientist
- opened
Looks like the model is stuck in an infinite loop "The skyscraper swayed again ...", "She thought, ..." occurs repeatedly in your example.
There is more work the be done with the moe/models in it. ;