Instructions to use nabin2004/AOS-gemma4-31b-manim-merged with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nabin2004/AOS-gemma4-31b-manim-merged with Transformers:

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

pipe = pipeline("text-generation", model="nabin2004/AOS-gemma4-31b-manim-merged")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("nabin2004/AOS-gemma4-31b-manim-merged")
model = AutoModelForMultimodalLM.from_pretrained("nabin2004/AOS-gemma4-31b-manim-merged", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.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(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use nabin2004/AOS-gemma4-31b-manim-merged with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nabin2004/AOS-gemma4-31b-manim-merged"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nabin2004/AOS-gemma4-31b-manim-merged",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/nabin2004/AOS-gemma4-31b-manim-merged

SGLang

How to use nabin2004/AOS-gemma4-31b-manim-merged 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 "nabin2004/AOS-gemma4-31b-manim-merged" \
    --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": "nabin2004/AOS-gemma4-31b-manim-merged",
		"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 "nabin2004/AOS-gemma4-31b-manim-merged" \
        --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": "nabin2004/AOS-gemma4-31b-manim-merged",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use nabin2004/AOS-gemma4-31b-manim-merged with Docker Model Runner:
```
docker model run hf.co/nabin2004/AOS-gemma4-31b-manim-merged
```

AOS Gemma 4 31B Manim SFT (Merged)

Full merged bf16 weights (LoRA baked into base) for Manim animation generation via multi-turn tool calling.

Model URL: https://huggingface.co/nabin2004/AOS-gemma4-31b-manim-merged

Related repos

Artifact	Repo
LoRA adapter	nabin2004/AOS-gemma4-31b-manim-sft
GGUF (Ollama / llama.cpp)	nabin2004/AOS-gemma4-31b-manim-gguf

Base model

Merged from google/gemma-4-31B-it and the AOS Manim SFT LoRA adapter. Accept the Gemma license and set HF_TOKEN to download.

Training data

Fine-tuned on nabin2004/AOS-Trajectories using the AOS Phase 1 SFT trainer (apps/sft).

Usage

Load with Transformers

import os
import torch
from transformers import AutoModelForImageTextToText, AutoTokenizer

token = os.environ["HF_TOKEN"]
model_id = "nabin2004/AOS-gemma4-31b-manim-merged"

tokenizer = AutoTokenizer.from_pretrained(model_id, token=token)
model = AutoModelForImageTextToText.from_pretrained(
    model_id,
    torch_dtype=torch.bfloat16,
    device_map="auto",
    token=token,
)

vLLM

Serve as a regular model (no --enable-lora needed):

vllm serve nabin2004/AOS-gemma4-31b-manim-merged --max-model-len 16384

Ollama / local GGUF

Convert to GGUF or pull the pre-built GGUF repo. See apps/sft/export_gguf.py.

How this was produced

cd apps/sft
uv run python merge_adapter.py \
  --adapter-dir ./gemma4-31b-manim-ft \
  --output-dir ./gemma4-31b-manim-merged \
  --push-to-hub

Downloads last month: 13

Safetensors

Model size

31B params

Tensor type

BF16

Model tree for nabin2004/AOS-gemma4-31b-manim-merged

Base model

google/gemma-4-31B

Finetuned

google/gemma-4-31B-it

Finetuned

(247)

this model

Collection including nabin2004/AOS-gemma4-31b-manim-merged

Manim Animation Generation

Collection

LLMs finetuned for generating Manim python code. • 7 items • Updated 6 days ago