--- license: apache-2.0 base_model: - Qwen/Qwen3-235B-A22B-Instruct-2507 --- ## Model Details This model is gguf:q4km model of [Qwen/Qwen3-235B-A22B-Instruct-2507](https://huggingface.co/Qwen/Qwen3-235B-A22B-Instruct-2507) generated by [intel/auto-round](https://github.com/intel/auto-round) algorithm. Please refer to Section `Generate the model` for more details. ## How To Use ### LLamacpp Inference ~~~bash ./llama-cli -hf Intel/Qwen3-235B-A22B-Instruct-2507-gguf-q4km-AutoRound:q4_k_m --conversation ~~~ ~~~python """ > Hi Hello! ٩(◕‿◕｡)۶ How can I assist you today? > Code a flappy bird in python Sure! Below is a simple implementation of **Flappy Bird** using **Python** and the **Pygame** library. This version includes: - A bird that flaps when you press the spacebar or click. - Pipes that move from right to left. - Collision detection. - Score tracking. - Game over when the bird hits a pipe or the ground/ceiling. --- ### ✅ Requirements Make sure you have `pygame` installed: ```bash pip install pygame ``` --- ### 🐤 Flappy Bird Code ```python import pygame import random import sys # Initialize Pygame pygame.init() # Screen dimensions SCREEN_WIDTH = 400 SCREEN_HEIGHT = 600 screen = pygame.display.set_mode((SCREEN_WIDTH, SCREEN_HEIGHT)) pygame.display.set_caption("Flappy Bird") # Colors WHITE = (255, 255, 255) BLACK = (0, 0, 0) GREEN = (0, 255, 0) BLUE = (0, 0, 255) SKY_BLUE = (135, 206, 235) # Game settings GRAVITY = 0.5 FLAP_STRENGTH = -10 PIPE_SPEED = 3 PIPE_GAP = 150 PIPE_FREQUENCY = 1500 # milliseconds # Bird settings bird_x = 100 bird_y = SCREEN_HEIGHT // 2 bird_velocity = 0 bird_width = 40 bird_height = 30 # Pipe list pipes = [] last_pipe_time = 0 # Score score = 0 font = pygame.font.SysFont('Arial', 26) # Clock clock = pygame.time.Clock() # Game loop running = True game_active = True def draw_bird(x, y): pygame.draw.rect(screen, BLUE, (x, y, bird_width, bird_height), border_radius=10) def create_pipe(): height = random.randint(100, SCREEN_HEIGHT - PIPE_GAP - 100) top_pipe = pygame.Rect(SCREEN_WIDTH, 0, 60, height) bottom_pipe = pygame.Rect(SCREEN_WIDTH, height + PIPE_GAP, 60, SCREEN_HEIGHT) return {"top": top_pipe, "bottom": bottom_pipe, "passed": False} def draw_pipes(pipes): for pipe in pipes: pygame.draw.rect(screen, GREEN, pipe["top"]) pygame.draw.rect(screen, GREEN, pipe["bottom"]) def move_pipes(pipes): for pipe in pipes: pipe["top"].x -= PIPE_SPEED pipe["bottom"].x -= PIPE_SPEED def remove_offscreen_pipes(pipes): return [pipe for pipe in pipes if pipe["top"].right > 0] def check_collision(pipes, bird_y): # Check ceiling or floor if bird_y < 0 or bird_y + bird_height > SCREEN_HEIGHT: return True # Check pipes bird_rect = pygame.Rect(bird_x, bird_y, bird_width, bird_height) for pipe in pipes: if bird_rect.colliderect(pipe["top"]) or bird_rect.colliderect(pipe["bottom"]): return True return False def draw_score(): score_text = font.render(f"Score: {score}", True, BLACK) screen.blit(score_text, (10, 10)) # Main game loop while running: current_time = pygame.time.get_ticks() screen.fill(SKY_BLUE) for event in pygame.event.get(): if event.type == pygame.QUIT: running = False if event.type == pygame.KEYDOWN: if event.key == pygame.K_SPACE and game_active: bird_velocity = FLAP_STRENGTH if event.key == pygame.K_r and not game_active: # Restart game bird_y = SCREEN_HEIGHT // 2 bird_velocity = 0 pipes = [] score = 0 game_active = True if event.type == pygame.MOUSEBUTTONDOWN and game_active: bird_velocity = FLAP_STRENGTH if game_active: # Bird physics bird_velocity += GRAVITY bird_y += bird_velocity # Generate pipes if current_time - last_pipe_time > PIPE_FREQUENCY: pipes.append(create_pipe()) last_pipe_time = current_time # Move and draw pipes move_pipes(pipes) pipes = remove_offscreen_pipes(pipes) draw_pipes(pipes) # Check for scoring for pipe in pipes: if pipe["top"].right < bird_x and not pipe["passed"]: score += 1 pipe["passed"] = True # Collision check if check_collision(pipes, bird_y): game_active = False # Draw bird and score draw_bird(bird_x, bird_y) draw_score() # Game over screen if not game_active: game_over = font.render("Game Over! Press 'R' to Restart", True, BLACK) screen.blit(game_over, (SCREEN_WIDTH // 2 - 180, SCREEN_HEIGHT // 2)) pygame.display.update() clock.tick(60) pygame.quit() sys.exit() ``` --- ### 🎮 How to Play - Press **Spacebar** or **click the mouse** to make the bird flap. - Avoid hitting the pipes, ceiling, or floor. - Your score increases each time you pass a pair of pipes. - After game over, press **'R'** to restart. --- ### 🧩 Enhancements (Optional) You can improve this by: - Adding sound effects. - Using bird/pipes images instead of rectangles. - Adding start screen. - Increasing difficulty over time. Let me know if you want a version with images or sound! 🎵🐦 """ ~~~ ### Generate the model auto-round>0.5.1 ~~~python import torch from transformers import AutoModelForCausalLM, AutoTokenizer from auto_round import AutoRound model_name = "Qwen/Qwen3-235B-A22B-Instruct-2507" model = AutoModelForCausalLM.from_pretrained(model_name, device_map="cpu", torch_dtype="auto") tokenizer = AutoTokenizer.from_pretrained(model_name) autoround = AutoRound(model, tokenizer, iters=0, layer_config=layer_config, nsamples=512) autoround.quantize_and_save("/dataset/Qwen3-235B-A22B-Instruct-2507-q4km", format="gguf:q4_k_m") ~~~ ## Ethical Considerations and Limitations The model can produce factually incorrect output, and should not be relied on to produce factually accurate information. Because of the limitations of the pretrained model and the finetuning datasets, it is possible that this model could generate lewd, biased or otherwise offensive outputs. Therefore, before deploying any applications of the model, developers should perform safety testing. ## Caveats and Recommendations Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. Here are a couple of useful links to learn more about Intel's AI software: - Intel Neural Compressor [link](https://github.com/intel/neural-compressor) ## Disclaimer The license on this model does not constitute legal advice. We are not responsible for the actions of third parties who use this model. Please consult an attorney before using this model for commercial purposes. ## Cite @article{cheng2023optimize, title={Optimize weight rounding via signed gradient descent for the quantization of llms}, author={Cheng, Wenhua and Zhang, Weiwei and Shen, Haihao and Cai, Yiyang and He, Xin and Lv, Kaokao and Liu, Yi}, journal={arXiv preprint arXiv:2309.05516}, year={2023} } [arxiv](https://arxiv.org/abs/2309.05516) [github](https://github.com/intel/auto-round)