RE: Teaching AI to Play Chrome Dino Game: Reinforcement Learning
You are viewing a single comment's thread:
We did it on a VPS with low specs, but it took too long to develop a response and gave false information. Perhaps it is because of the components
0
0
0.000
I have now checked the 7B model I had used.
That explains it. It's really weak with just 7 billion parameters compared to the best 671 billion parameters.