Posted January 31, 2025 by Soul Shell
I have managed to integrate the LlaMaC++ project in UE5 to load Large Language Models (Meta Llama 3.1) and generate text dynamically. The main improvement is that now the speed in the generation of the responses is substantially better than previous versions. Specific advances:
Next step: State machine for animations, localization for different languages, auto-save option, etc.
Note: I have managed to apply a workaround to completely decensor the LLM, however, it seems to cause the LLM to become more repetitive, more experimentation is necessary.