Instructions to use Mantis-VL/mantis-8b-idefics2_8192 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Mantis-VL/mantis-8b-idefics2_8192 with Transformers:

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

pipe = pipeline("image-text-to-text", model="Mantis-VL/mantis-8b-idefics2_8192")

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("Mantis-VL/mantis-8b-idefics2_8192")
model = AutoModelForImageTextToText.from_pretrained("Mantis-VL/mantis-8b-idefics2_8192")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Mantis-VL/mantis-8b-idefics2_8192 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Mantis-VL/mantis-8b-idefics2_8192"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Mantis-VL/mantis-8b-idefics2_8192",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Mantis-VL/mantis-8b-idefics2_8192

SGLang

How to use Mantis-VL/mantis-8b-idefics2_8192 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 "Mantis-VL/mantis-8b-idefics2_8192" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Mantis-VL/mantis-8b-idefics2_8192",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "Mantis-VL/mantis-8b-idefics2_8192" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Mantis-VL/mantis-8b-idefics2_8192",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Mantis-VL/mantis-8b-idefics2_8192 with Docker Model Runner:
```
docker model run hf.co/Mantis-VL/mantis-8b-idefics2_8192
```

mantis-8b-idefics2_8192

This model is a fine-tuned version of HuggingFaceM4/idefics2-8b on an unknown dataset.

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 5e-06
train_batch_size: 1
eval_batch_size: 1
seed: 42
distributed_type: multi-GPU
num_devices: 16
gradient_accumulation_steps: 8
total_train_batch_size: 128
total_eval_batch_size: 16
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.03
num_epochs: 1.0

Training results

Framework versions

Transformers 4.40.2
Pytorch 2.3.0+cu121
Datasets 2.18.0
Tokenizers 0.19.1

Downloads last month: 8

Safetensors

Model size

8B params

Tensor type

BF16

Inference Providers NEW

Image-Text-to-Text

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Mantis-VL/mantis-8b-idefics2_8192

Base model

HuggingFaceM4/idefics2-8b

Finetuned

(170)

this model