Further training/distillation needed?

#5
by mingyi456 - opened

This pruned version fails to output any Python code for the flappy bird prompt in LM Studio. I downloaded the Q8 quant from bartowski, and after setting the parameters and retrying a few times the final output is still incoherent. Meanwhile the unpruned UD-Q4_K_XL quant from unsloth at least produces a block of code. Maybe there is still a need to train or distill this model to heal the damage from pruning? The full prompt is below:

Create a Flappy Bird game in Python. You must include these things:

  1. You must use pygame.
  2. The background color should be randomly chosen and is a light shade. Start with a light blue color.
  3. Pressing SPACE multiple times will accelerate the bird.
  4. The bird's shape should be randomly chosen as a square, circle or triangle. The color should be randomly chosen as a dark color.
  5. Place on the bottom some land colored as dark brown or yellow chosen randomly.
  6. Make a score shown on the top right side. Increment if you pass pipes and don't hit them.
  7. Make randomly spaced pipes with enough space. Color them randomly as dark green or light brown or a dark gray shade.
  8. When you lose, show the best score. Make the text inside the screen. Pressing q or Esc will quit the game. Restarting is pressing SPACE again.
    The final game should be inside a markdown section in Python. Check your code for errors and fix them before the final markdown section.

Yes, it is stated in the readme.

Sign up or log in to comment