Instructions to use Mihaiii/Ovis2-4B-RL-VQA-1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Mihaiii/Ovis2-4B-RL-VQA-1 with Transformers:

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

pipe = pipeline("text-generation", model="Mihaiii/Ovis2-4B-RL-VQA-1", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("Mihaiii/Ovis2-4B-RL-VQA-1", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Mihaiii/Ovis2-4B-RL-VQA-1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Mihaiii/Ovis2-4B-RL-VQA-1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Mihaiii/Ovis2-4B-RL-VQA-1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Mihaiii/Ovis2-4B-RL-VQA-1

SGLang

How to use Mihaiii/Ovis2-4B-RL-VQA-1 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 "Mihaiii/Ovis2-4B-RL-VQA-1" \
    --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": "Mihaiii/Ovis2-4B-RL-VQA-1",
		"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 "Mihaiii/Ovis2-4B-RL-VQA-1" \
        --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": "Mihaiii/Ovis2-4B-RL-VQA-1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Mihaiii/Ovis2-4B-RL-VQA-1 with Docker Model Runner:
```
docker model run hf.co/Mihaiii/Ovis2-4B-RL-VQA-1
```

%%bash CUDA_VISIBLE_DEVICES=0
MAX_PIXELS=1003520
swift rlhf
--rlhf_type grpo
--model 'Mihaiii/Ovis2-4B'
--model_type ovis2
--external_plugins './plugin.py'
--reward_funcs external_db_accuracy
--train_type lora
--lora_rank 8
--lora_alpha 32
--target_modules all-linear
--torch_dtype bfloat16
--dataset 'Mihaiii/OCRBenchv2-other-cols-2'
--use_hf 1
--max_completion_length 1024
--num_train_epochs 1
--per_device_train_batch_size 4
--per_device_eval_batch_size 4
--learning_rate 1e-4
--gradient_accumulation_steps 1
--eval_steps 50
--save_steps 250
--save_total_limit 2
--logging_steps 5
--max_length 2048
--output_dir output
--warmup_ratio 0.05
--dataloader_num_workers 4
--dataset_num_proc 4
--num_generations 4
--temperature 0.9
--split_dataset_ratio 0

Downloads last month: 4

Safetensors

Model size

4B params

Tensor type

BF16