Instructions to use vikramlingam/VLQM-1.5B-Coder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use vikramlingam/VLQM-1.5B-Coder with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="vikramlingam/VLQM-1.5B-Coder")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("vikramlingam/VLQM-1.5B-Coder")
model = AutoModelForCausalLM.from_pretrained("vikramlingam/VLQM-1.5B-Coder")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use vikramlingam/VLQM-1.5B-Coder with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "vikramlingam/VLQM-1.5B-Coder"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "vikramlingam/VLQM-1.5B-Coder",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/vikramlingam/VLQM-1.5B-Coder

SGLang

How to use vikramlingam/VLQM-1.5B-Coder with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "vikramlingam/VLQM-1.5B-Coder" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "vikramlingam/VLQM-1.5B-Coder",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "vikramlingam/VLQM-1.5B-Coder" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "vikramlingam/VLQM-1.5B-Coder",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use vikramlingam/VLQM-1.5B-Coder with Docker Model Runner:
```
docker model run hf.co/vikramlingam/VLQM-1.5B-Coder
```

🚀 VLQM-1.5B-Coder

A fine-tuned language model for generating Manim animation code from natural language descriptions.

📖 Model Description

VLQM-1.5B-Coder is a specialized language model fine-tuned to generate Manim Python code from natural language descriptions. Manim is the mathematical animation engine famously used by 3Blue1Brown.

What This Model Does

Given a natural language prompt:

"Create a blue circle that moves to the right"

The model generates valid Manim Python code:

from manim import *

class GenScene(Scene):
    def construct(self):
        circle = Circle(color=BLUE)
        self.add(circle)
        self.play(circle.animate.shift(RIGHT * 3))

🎯 Intended Use

Primary Use: Generating Manim animation code from text descriptions
Users: Developers, educators, content creators making math/science animations
Languages: English prompts, Python code output

Example Use Cases

Creating educational math animations
Generating visualizations for presentations
Prototyping Manim scenes quickly
Learning Manim syntax through examples

📊 Training Details

Property	Value
Base Model	`Qwen/Qwen2.5-Coder-1.5B-Instruct`
Parameters	1.5 Billion
Training Method	LoRA (Low-Rank Adaptation)
Dataset	`generaleoley/manim-codegen`
Training Examples	1,459
Validation Examples	163
Training Framework	Apple MLX
Hardware	MacBook Pro (Apple Silicon)

Hyperparameters

Parameter	Value
Iterations	300
Batch Size	2
Gradient Accumulation	8
Learning Rate	5e-5
LoRA Layers	16
Max Sequence Length	8,192

📈 Model Performance

Training Loss Curve

The model shows a strong convergence pattern, with validation loss stabilizing around 0.71 and training loss reaching 0.48.

⚠️ Limitations

Known Limitations

Complex Animations: May struggle with multi-step animations involving many objects
Advanced Manim Features: Less reliable with 3D scenes, complex graphs, or advanced camera movements
API Hallucinations: Sometimes generates non-existent Manim methods (e.g., axes.get_sine())
Indentation Issues: Occasionally produces incorrectly indented code
Long Prompts: Performance degrades with very long or complex descriptions

What This Model is NOT

❌ Not a general-purpose code generator
❌ Not trained for non-Manim Python code
❌ Not suitable for production without human review
❌ Not a replacement for learning Manim fundamentals

Recommended Practices

✅ Always review and test generated code before use
✅ Use simple, clear prompts for best results
✅ Keep prompts focused on one animation at a time
✅ Be prepared to make minor edits to fix issues

🚀 Quick Start

Using with Transformers (Cross-Platform)

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained(
    "vikramlingam/VLQM-1.5B-Coder",
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("vikramlingam/VLQM-1.5B-Coder")

prompt = "Create a red square that rotates"
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0]))

Using with MLX (Apple Silicon)

python -m mlx_lm.generate \
    --model vikramlingam/VLQM-1.5B-Coder \
    --prompt "Create a circle animation" \
    --max-tokens 256

📁 Model Files

VLQM-1.5B-Coder/
├── config.json              # Model configuration
├── model.safetensors        # Model weights (~3 GB)
├── tokenizer.json           # Tokenizer
├── tokenizer_config.json
├── vocab.json
├── merges.txt
├── generation_config.json
├── special_tokens_map.json
└── README.md                # This file

📜 License

This model is released under the Apache 2.0 License.

✅ Commercial use allowed
✅ Modification allowed
✅ Distribution allowed
⚠️ Must include license and copyright notice

🙏 Acknowledgments

Base Model: Qwen/Qwen2.5-Coder-1.5B-Instruct by Alibaba
Dataset: generaleoley/manim-codegen
Training Framework: Apple MLX
Animation Engine: Manim Community

📬 Citation

If you use this model, please cite:

@misc{vlqm-1.5b-coder,
  author = {Vikram Lingam},
  title = {VLQM-1.5B-Coder: Manim Code Generation Model},
  year = {2025},
  publisher = {Hugging Face},
  url = {https://huggingface.co/vikramlingam/VLQM-1.5B-Coder}
}

📊 Model Card Contact

For questions or issues, please open a discussion on the model's Hugging Face page.

Downloads last month: 6

Safetensors

Model size

2B params

Tensor type

BF16

Model tree for vikramlingam/VLQM-1.5B-Coder

Base model

Qwen/Qwen2.5-1.5B

Finetuned

Qwen/Qwen2.5-Coder-1.5B

Finetuned

Qwen/Qwen2.5-Coder-1.5B-Instruct

Finetuned

(155)

this model

vikramlingam
/

VLQM-1.5B-Coder

🚀 VLQM-1.5B-Coder

📖 Model Description

What This Model Does

🎯 Intended Use

Example Use Cases

📊 Training Details

Hyperparameters

📈 Model Performance

Training Loss Curve

⚠️ Limitations

Known Limitations

What This Model is NOT

Recommended Practices

🚀 Quick Start

Using with Transformers (Cross-Platform)

Using with MLX (Apple Silicon)

📁 Model Files

📜 License

🙏 Acknowledgments

📬 Citation

📊 Model Card Contact

Model tree for vikramlingam/VLQM-1.5B-Coder

Dataset used to train vikramlingam/VLQM-1.5B-Coder