See our collection for all versions of DeepSeek-VL.
Run DeepSeek-VL with Keras 3: JAX, PyTorch, or TensorFlow
zeromodels/deepseek_vl_1.3b_chat
Paper: DeepSeek-VL: Towards Real-World Vision-Language Understanding (arXiv:2403.05525) · HF Papers
DeepSeek-VL 1.3B uses a SigLIP @384 tower + 2-linear GELU aligner + Llama decoder for image + text → text. Import from zeromodels.models.deepseek_vl.
For more details on the model, please go to the upstream model card.
Pure-Keras 3 conversion of deepseek-ai/deepseek-vl-1.3b-chat for zeromodels. One implementation runs unmodified on TensorFlow / Torch / JAX.
This is a vision-language (chat) checkpoint (DeepseekVLConditionalGenerate, 1.3B chat (SigLIP)).
✨ Quick start
import os
os.environ["KERAS_BACKEND"] = "torch" # or "jax" / "tensorflow"
from PIL import Image
from zeromodels.models.deepseek_vl import (
DeepseekVLConditionalGenerate,
DeepseekVLProcessor,
)
model = DeepseekVLConditionalGenerate.from_weights("zeromodels/deepseek_vl_1.3b_chat")
processor = DeepseekVLProcessor.from_weights("zeromodels/deepseek_vl_1.3b_chat")
image = Image.open("your_image.jpg")
inputs = processor(
conversation=[
{
"role": "user",
"content": [
{"type": "image", "image": image},
{"type": "text", "text": "Describe this image in one sentence."},
],
}
]
)
outputs = model.generate(**inputs, max_new_tokens=64)
print(processor.decode(outputs[0]))
Load any DeepSeek-VL variant the same way with from_weights("zeromodels/<variant>"):
| Variant | Hub | Notes |
|---|---|---|
deepseek_vl_1.3b_base | zeromodels/deepseek_vl_1.3b_base | 1.3B base |
deepseek_vl_1.3b_chat | zeromodels/deepseek_vl_1.3b_chat | 1.3B chat |
deepseek_vl_7b_base | zeromodels/deepseek_vl_7b_base | 7B hybrid base |
deepseek_vl_7b_chat | zeromodels/deepseek_vl_7b_chat | 7B hybrid chat |
Tips
- Set
KERAS_BACKENDbefore importing Keras / zeromodels. - Prefer
Processor.from_weights(...)so vision + tokenizer match. - 7B hybrid is a different package than 1.3B; do not mix imports.
- See docs and Loading Weights.
- Community / upstream safetensors still work via the
hf:prefix, e.g.DeepseekVLConditionalGenerate.from_weights("hf:deepseek-ai/deepseek-vl-1.3b-chat").
Special Thanks
A huge thank you to the DeepSeek-VL authors for creating and releasing these models.
License: DeepSeek (other / deepseek). See LICENSE.