Create README.md

README.md

@@ -0,0 +1,261 @@
+---
+license: apache-2.0
+base_model:
+- Qwen/Qwen3-235B-A22B-Instruct-2507
+---
+
+## Model Details
+
+This model is a mixed gguf:q2ks 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. Embedding layer and lm-head layer are fallback to 8 bits and non expert layers are fallback to 4 bits. 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-q2ks-mixed-AutoRound-inc:q2_k_s --conversation
+~~~
+
+
+~~~python
+"""
+> Hi
+Hello! How can I help you today? 😊
+
+> code a flappy bird in Python
+Sure! Here's a simple **Flappy Bird** game implemented in Python using the **Pygame** library.
+
+---
+
+### 🔧 Requirements:
+Make sure you have **Pygame** installed:
+
+```bash
+pip install pygame
+```
+
+---
+
+### 🐤 Flappy Bird in Python
+
+```python
+import pygame
+import random
+import sys
+
+# Initialize Pygame
+pygame.init()
+
+# Screen dimensions
+WIDTH, HEIGHT = 400, 600
+screen = pygame.display.set_mode((WIDTH, HEIGHT))
+pygame.display.set_caption("Flappy Bird")
+
+# Colors
+WHITE = (255, 255, 255)
+BLACK = (0, 0, 0)
+GREEN = (0, 128, 0)
+SKY_BLUE = (135, 206, 235)
+
+# Game settings
+GRAVITY = 0.5
+FLAP_STRENGTH = -10
+PIPE_SPEED = 3
+PIPE_GAP = 150
+PIPE_FREQUENCY = 1500  # milliseconds
+
+# Bird class
+class Bird:
+    def __init__(self):
+        self.x = 50
+        self.y = HEIGHT // 2
+        self.velocity = 0
+        self.width = 20
+        self.height = 20
+
+    def flap(self):
+        self.velocity = FLAP_STRENGTH
+
+    def update(self):
+        self.velocity += GRAVITY
+        self.y += self.velocity
+        if self.y < 0:
+            self.y = 0
+        if self.y > HEIGHT:
+            self.y = HEIGHT
+
+    def draw(self):
+        pygame.draw.circle(screen, BLACK, (self.x, int(self.y)), self.width // 2)
+
+# Pipe class
+class Pipe:
+    def __init__(self):
+        self.x = WIDTH
+        self.top = random.randint(50, HEIGHT - PIPE_GAP - 50)
+        self.bottom = self.top + PIPE_GAP
+        self.width = 50
+        self.passed = False
+
+    def update(self):
+        self.x -= PIPE_SPEED
+        return self.x > -self.width
+
+    def draw(self):
+        pygame.draw.rect(screen, GREEN, (self.x, 0, self.width, self.top))
+        pygame.draw.rect(screen, GREEN, (self.x, self.bottom, self.width, HEIGHT - self.bottom))
+
+    def collide(self, bird):
+        if bird.x + bird.width // 2 > self.x and bird.x - bird.width // 2 < self.x + self.width:
+            if bird.y - bird.height // 2 < self.top or bird.y + bird.height // 2 > self.bottom:
+                return True
+        return False
+
+# Main game loop
+def game():
+    bird = Bird()
+    pipes = []
+    score = 0
+    clock = pygame.time.Clock()
+    last_pipe = pygame.time.get_ticks()
+
+    running = True
+    game_active = True
+
+    font = pygame.font.SysFont(None, 55)
+
+    while running:
+        screen.fill(SKY_BLUE)
+        dt = clock.tick(60)
+        current_time = pygame.time.get_ticks()
+
+        # Event handling
+        for event in pygame.event.get():
+            if event.type == pygame.QUIT:
+                pygame.quit()
+                sys.exit()
+            if event.type == pygame.KEYDOWN:
+                if event.key == pygame.K_SPACE and game_active:
+                    bird.flap()
+                if event.key == pygame.K_r and not game_active:
+                    game()
+
+        if game_active:
+            # Update bird
+            bird.update()
+
+            # Generate new pipes
+            if current_time - last_pipe > PIPE_FREQUENCY:
+                pipes.append(Pipe())
+                last_pipe = current_time
+
+            # Update and draw pipes
+            pipes = [p for p in pipes if p.update()]
+            for pipe in pipes:
+                pipe.draw()
+                if pipe.collide(bird):
+                    game_active = False
+
+                # Score logic
+                if pipe.x + pipe.width < bird.x and not pipe.passed:
+                    score += 1
+                    pipe.passed = True
+
+            # Draw bird
+            bird.draw()
+
+            # Check if bird hits the ground or flies too high
+            if bird.y >= HEIGHT or bird.y <= 0:
+                game_active = False
+
+            # Display score
+            score_text = font.render(f"Score: {score}", True, BLACK)
+            screen.blit(score_text, (10, 10))
+
+        else:
+            # Game over screen
+            game_over_text = font.render("Game Over!", True, BLACK)
+            restart_text = font.render("Press 'R' to Restart", True, BLACK)
+            screen.blit(game_over_text, (WIDTH // 2 - 90, HEIGHT // 2 - 50))
+            screen.blit(restart_text, (WIDTH // 2 - 150, HEIGHT // 2 + 10))
+
+        pygame.display.update()
+
+# Start the game
+game()
+```
+
+---
+
+### 🎮 How to Play:
+- Press **Spacebar** to flap the bird upward.
+- Avoid hitting the pipes or the ground.
+- When you die, press **'R'** to restart.
+
+---
+
+### ✅ Features:
+- Gravity and flap mechanics.
+- Random pipe generation.
+- Collision detection.
+- Score tracking.
+- Simple graphics using shapes.
+
+---
+
+Let me know if you'd like to add images, sounds, or improve the visuals! 🐦💨
+
+
+"""
+
+~~~
+
+### 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)
+layer_config = {}
+for n, m in model.named_modules():
+    if n == "lm_head" or isinstance(m,torch.nn.Embedding):
+        layer_config[n] = {"bits": 8}
+    elif isinstance(m, torch.nn.Linear) and (not "expert" in n or "shared_experts" in n) and n != "lm_head":
+        layer_config[n] = {"bits": 4}
+
+autoround = AutoRound(model, tokenizer, iters=0, layer_config=layer_config, nsamples=512)
+autoround.quantize_and_save("/models/Qwen3-235B-A22B-Instruct-2507-q2ks", format="gguf:q2_k_s")
+
+~~~
+
+
+## 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)