LLM for games

Devlog

• LLMS building rpg fighters, randomized options
  November 18, 2024 by douteigami

  This is basically the same test as before , only the options prompted to each model have been randomized, both their order and corresponding letter. The test options before were always [A - STR, B - C... Continue reading

  
• What stats do LLMS allocate when building an RPG fighter class character?
  November 17, 2024 by douteigami

  I wanted to see how different models allocate stats for an rpg character. I also wanted to automate the testing, instead of doing it manually like before. Each model is prompted at every level between... Continue reading

  
• <1GB models - test 3
  November 14, 2024 by douteigami

  MODELS: GPT2 - Q4 OpenELM-1_1B-Instruct - Q4 Minerva-1b-base-v1.0 - Q4 Olmo-1b-hf - Q4 Llama-3.2-1B-Instruct - Q4 Prem-1b-chat - Q4 Xlam-1b-fc-r - Q4 Granite-3.0-1b-a400m-instruct - Q4 Llama-3.2-1b-sy... Continue reading

  
• <1GB models - test 2
  November 14, 2024 by douteigami

  MODELS: GPT2 - Q4 OpenELM-1_1B-Instruct - Q4 Minerva-1b-base-v1.0 - Q4 Olmo-1b-hf - Q4 Llama-3.2-1B-Instruct - Q4 Prem-1b-chat - Q4 Xlam-1b-fc-r - Q4 Granite-3.0-1b-a400m-instruct - Q4 Llama-3.2-1b-sy... Continue reading

  
• <1GB Models - Test 1
  November 14, 2024 by douteigami

  MODELS: GPT2 - Q4 OpenELM-1_1B-Instruct - Q4 Minerva-1b-base-v1.0 - Q4 Olmo-1b-hf - Q4 Llama-3.2-1B-Instruct - Q4 Prem-1b-chat - Q4 Xlam-1b-fc-r - Q4 Granite-3.0-1b-a400m-instruct - Q4 Llama-3.2-1b-sy... Continue reading