Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
HuggingFaceTB
/
SmolVLM2-500M-Video-Instruct
like
72
Follow
Hugging Face Smol Models Research
1.89k
Image-Text-to-Text
Transformers
ONNX
Safetensors
12 datasets
English
smolvlm
conversational
arxiv:
2504.05299
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
18
Train
Deploy
Use this model
main
SmolVLM2-500M-Video-Instruct
Ctrl+K
Ctrl+K
8 contributors
History:
36 commits
mfarre
Update README.md
7b375e1
verified
3 months ago
onnx
Add cast node to inputs_embeds (#3)
4 months ago
.gitattributes
Safe
1.52 kB
initial commit
5 months ago
README.md
Safe
10.9 kB
Update README.md
3 months ago
added_tokens.json
4.74 kB
Upload processor
5 months ago
chat_template.json
430 Bytes
Upload processor
5 months ago
config.json
Safe
3.77 kB
Add missing config value (num_hidden_layers) (#4)
4 months ago
generation_config.json
Safe
136 Bytes
Upload SmolVLMForConditionalGeneration
5 months ago
merges.txt
Safe
466 kB
Upload processor
5 months ago
model.safetensors
Safe
2.03 GB
xet
Upload SmolVLMForConditionalGeneration
5 months ago
preprocessor_config.json
599 Bytes
video_sampling.longest_edge -> 512 (#6)
4 months ago
processor_config.json
67 Bytes
Upload 3 files
5 months ago
special_tokens_map.json
868 Bytes
Upload processor
4 months ago
tokenizer.json
3.55 MB
Upload processor
5 months ago
tokenizer_config.json
Safe
28.6 kB
Upload processor
4 months ago
vocab.json
Safe
801 kB
Upload processor
5 months ago