Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
HuggingFaceTB
/
SmolVLM2-256M-Video-Instruct
like
55
Follow
Hugging Face Smol Models Research
1.64k
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
10
Train
Deploy
Use this model
017ae74
SmolVLM2-256M-Video-Instruct
Commit History
video_sampling.longest_edge -> 512 (
#3
)
017ae74
verified
mfarre
pcuenq
HF Staff
commited on
Feb 17
Add cast node to inputs_embeds (
#2
)
a7f7d71
verified
Xenova
HF Staff
commited on
Feb 13
Upload ONNX weights (
#1
)
28755f8
verified
mfarre
Xenova
HF Staff
commited on
Feb 13
update extra special tokens
1501a36
RaushanTurganbay
HF Staff
commited on
Feb 13
Upload 3 files
e62441b
verified
mfarre
commited on
Feb 12
Upload 2 files
9b3714f
verified
mfarre
commited on
Feb 12
Upload SmolVLMForConditionalGeneration
0f79c90
verified
mfarre
commited on
Feb 12
Upload processor
6c2643d
verified
mfarre
commited on
Feb 11
Upload SmolVLMForConditionalGeneration
a820e48
verified
mfarre
commited on
Feb 11
initial commit
0ac784c
verified
mfarre
commited on
Feb 11
