Im a young AI/ML dev/enthusiast collected, training, and finetuning LLMs
-
s5
A model based on the GLM-4.6v-flash:9b q5_k_m, and uncensored. For local use I recommend editing the model context in modelfile as it is set to 128k. #EDIT: New local optimised model same with context 4096 https://ollama.com/ShreyanGondaliya/s5-reduced
353 Pulls 1 Tag Updated 2 months ago
-
s5-reduced
reduced s5 default context to 4096 tokens to allow better local inference thinks in chinese somtimes??
63 Pulls 1 Tag Updated 2 months ago