---

Qwen2.5-Coder-7B-Manim

Generate Manim (Mathematical Animation Engine) Python code from natural language descriptions! Fine-tuned on 2,407 examples from the 3Blue1Brown Manim dataset using QLoRA with Unsloth.

---

🚀 Quick Start

Installation

pip install unsloth transformers accelerate

Load Model

from unsloth import FastLanguageModel

model, tokenizer = FastLanguageModel.from_pretrained(
    model_name="Harish102005/Qwen2.5-Coder-7B-manim",
    max_seq_length=2048,
    dtype=None,
    load_in_4bit=True,
)
FastLanguageModel.for_inference(model)

Generate Manim Code

# Alpaca-style prompt template
alpaca_prompt = """Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.

### Instruction:
{}

### Input:
{}

### Response:
{}"""

prompt = "Create a blue circle that grows to twice its size"

inputs = tokenizer([
    alpaca_prompt.format(
        "Generate Manim code for the following task:",
        prompt,
        ""
    )
], return_tensors="pt").to("cuda")

outputs = model.generate(
    **inputs,
    max_new_tokens=512,
    temperature=0.3,
    top_p=0.9,
    repetition_penalty=1.1,
    do_sample=True,
)

generated_code = tokenizer.decode(outputs, skip_special_tokens=True)
print(generated_code.split("### Response:")[-1].strip())

---

Helper Function

def generate_manim_code(prompt, max_tokens=512):
    alpaca_prompt = """Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.

### Instruction:
{}

### Input:
{}

### Response:
{}"""
    
    formatted_prompt = alpaca_prompt.format(
        "Generate Manim code for the following task:",
        prompt,
        ""
    )
    
    inputs = tokenizer([formatted_prompt], return_tensors="pt").to("cuda")
    outputs = model.generate(
        **inputs,
        max_new_tokens=max_tokens,
        temperature=0.3,
        top_p=0.9,
        repetition_penalty=1.1,
        do_sample=True,
    )
    
    generated_text = tokenizer.decode(outputs, skip_special_tokens=True)
    if "### Response:" in generated_text:
        code = generated_text.split("### Response:")[-1].strip()
        if "### Instruction:" in code:
            code = code.split("### Instruction:")[0].strip()
        return code
    
    return generated_text

# Example
code = generate_manim_code("Create a rotating square")
print(code)

---

📊 Example Outputs

1. Color-Changing Rotation

Prompt: "Create a rotating square that changes color from blue to red"

from manim import *

class MyScene(Scene):
    def construct(self):
        square = Square(color=BLUE)
        self.add(square)
        self.play(square.animate.rotate(PI), run_time=2)
        square.set_color(RED)

2. Mathematical Function

Prompt: "Draw a sine wave from 0 to 2π with animation"

from manim import *

class MyScene(Scene):
    def construct(self):
        axes = Axes(x_range=[0, 2*PI], y_range=[-1, 1])
        graph = axes.plot(lambda x: np.sin(x), color=BLUE)
        self.add(axes, graph)

3. Formula Display

Prompt: "Show the equation E=mc² and fade it in"

from manim import *

class MyScene(Scene):
    def construct(self):
        e_mc_squared = MathTex("E=mc^2")
        self.play(Write(e_mc_squared))
        self.wait()

---

📈 Model Details

• Base Model: Qwen/Qwen2.5-Coder-7B
• Fine-tuning Method: QLoRA (4-bit) with Unsloth
• Dataset: dalle2/3blue1brown-manim
• Dataset Size: 2,407 prompt-code pairs
• Final Training Loss: 0.553
• Model Type: Qwen2ForCausalLM
• Parameters: ~7.6B (base), Trainable: 40.4M (0.53%)

Hyperparameters

Parameter	Value
LoRA Rank (r)	16
LoRA Alpha	16
LoRA Dropout	0.0
Target Modules	q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj
Max Sequence Length	2048
Precision	BFloat16
Quantization	4-bit NF4 (double quantization)

---

🎯 Use Cases

• Generate educational animations (math tutorials, visualizations)
• Rapid prototyping of visual content in Manim
• Learning Manim syntax and animation techniques
• Content automation (batch animation generation)

---

⚠️ Limitations

• Primarily for 2D Manim animations; may struggle with complex 3D scenes
• Training data limited to 3Blue1Brown patterns (2,407 examples)
• Minor manual corrections may be needed for complex animations
• Advanced Manim features (custom shaders, complex mobjects) not fully supported

---

🔧 Advanced Usage

Streaming Output

from transformers import TextStreamer

text_streamer = TextStreamer(tokenizer, skip_prompt=True)
_ = model.generate(**inputs, streamer=text_streamer, max_new_tokens=512, temperature=0.3)

Batch Generation

prompts = ["Create a blue circle", "Draw a red square", "Show a green triangle"]

for prompt in prompts:
    code = generate_manim_code(prompt)
    print(f"Prompt: {prompt}\n{code}\n{'-'*60}")

---

🙏 Acknowledgments

• Base Model: Qwen Team
• Dataset: dalle2
• Training Framework: Unsloth
• Inspiration: 3Blue1Brown and the Manim Community

---

---

✅ Star this model if you find it useful!

---