Skywork-R1V2-38B

198
126
38.0B
FP32
license:mit
by
Skywork
Image Model
OTHER
38B params
New
198 downloads
Early-stage
Try on Hugging FaceAdd to Compare
Edge AI:
Mobile
Laptop
Server
85GB+ RAM
Mobile
Laptop
Server
Quick Summary

Skywork-R1V2-38B is a state-of-the-art open-source multimodal reasoning model, achieving top-tier performance across multiple benchmarks: - On MMMU, it scores 73.

Device Compatibility

Mobile
4-6GB RAM
Laptop
16GB RAM
Server
GPU
Minimum Recommended
36GB+ RAM

Code Examples

3. Usagebashvllm
# For Transformers  
conda create -n r1-v python=3.10 && conda activate r1-v  
bash setup.sh  
# For vLLM  
conda create -n r1v-vllm python=3.10 && conda activate r1v-vllm  
pip install -U vllm
3. Usagebashvllm
# For Transformers  
conda create -n r1-v python=3.10 && conda activate r1-v  
bash setup.sh  
# For vLLM  
conda create -n r1v-vllm python=3.10 && conda activate r1v-vllm  
pip install -U vllm
3. Usagebashvllm
# For Transformers  
conda create -n r1-v python=3.10 && conda activate r1-v  
bash setup.sh  
# For vLLM  
conda create -n r1v-vllm python=3.10 && conda activate r1v-vllm  
pip install -U vllm
3. Usagebashvllm
# For Transformers  
conda create -n r1-v python=3.10 && conda activate r1-v  
bash setup.sh  
# For vLLM  
conda create -n r1v-vllm python=3.10 && conda activate r1v-vllm  
pip install -U vllm
3. Usagebashvllm
# For Transformers  
conda create -n r1-v python=3.10 && conda activate r1-v  
bash setup.sh  
# For vLLM  
conda create -n r1v-vllm python=3.10 && conda activate r1v-vllm  
pip install -U vllm
3. Usagebashvllm
# For Transformers  
conda create -n r1-v python=3.10 && conda activate r1-v  
bash setup.sh  
# For vLLM  
conda create -n r1v-vllm python=3.10 && conda activate r1v-vllm  
pip install -U vllm
3. Usagebashvllm
# For Transformers  
conda create -n r1-v python=3.10 && conda activate r1-v  
bash setup.sh  
# For vLLM  
conda create -n r1v-vllm python=3.10 && conda activate r1v-vllm  
pip install -U vllm
3. Usagebashvllm
# For Transformers  
conda create -n r1-v python=3.10 && conda activate r1-v  
bash setup.sh  
# For vLLM  
conda create -n r1v-vllm python=3.10 && conda activate r1v-vllm  
pip install -U vllm
3. Usagebashvllm
# For Transformers  
conda create -n r1-v python=3.10 && conda activate r1-v  
bash setup.sh  
# For vLLM  
conda create -n r1v-vllm python=3.10 && conda activate r1v-vllm  
pip install -U vllm
3. Usagebashvllm
# For Transformers  
conda create -n r1-v python=3.10 && conda activate r1-v  
bash setup.sh  
# For vLLM  
conda create -n r1v-vllm python=3.10 && conda activate r1v-vllm  
pip install -U vllm
For vLLMbash
CUDA_VISIBLE_DEVICES="0,1" python inference_with_transformers.py \
    --model_path path \
    --image_paths image1_path \
    --question "your question"
For vLLMbash
CUDA_VISIBLE_DEVICES="0,1" python inference_with_transformers.py \
    --model_path path \
    --image_paths image1_path \
    --question "your question"
For vLLMbash
CUDA_VISIBLE_DEVICES="0,1" python inference_with_transformers.py \
    --model_path path \
    --image_paths image1_path \
    --question "your question"
For vLLMbash
CUDA_VISIBLE_DEVICES="0,1" python inference_with_transformers.py \
    --model_path path \
    --image_paths image1_path \
    --question "your question"
For vLLMbash
CUDA_VISIBLE_DEVICES="0,1" python inference_with_transformers.py \
    --model_path path \
    --image_paths image1_path \
    --question "your question"
For vLLMbash
CUDA_VISIBLE_DEVICES="0,1" python inference_with_transformers.py \
    --model_path path \
    --image_paths image1_path \
    --question "your question"
For vLLMbash
CUDA_VISIBLE_DEVICES="0,1" python inference_with_transformers.py \
    --model_path path \
    --image_paths image1_path \
    --question "your question"
For vLLMbash
CUDA_VISIBLE_DEVICES="0,1" python inference_with_transformers.py \
    --model_path path \
    --image_paths image1_path \
    --question "your question"
For vLLMbash
CUDA_VISIBLE_DEVICES="0,1" python inference_with_transformers.py \
    --model_path path \
    --image_paths image1_path \
    --question "your question"
For vLLMbash
CUDA_VISIBLE_DEVICES="0,1" python inference_with_transformers.py \
    --model_path path \
    --image_paths image1_path \
    --question "your question"

Deploy This Model

Production-ready deployment in minutes

Together.ai

Instant API access to this model

Fastest API

Production-ready inference API. Start free, scale to millions.

Try Free API

Replicate

One-click model deployment

Easiest Setup

Run models in the cloud with simple API. No DevOps required.

Deploy Now

Disclosure: We may earn a commission from these partners. This helps keep LLMYourWay free.