Text only generation for Idefics3
3
#22 opened 4 months ago
by
FreekCool
This model can enabling video understanding and multi-image understanding capabilities?
#21 opened 4 months ago
by
xJohn
Considerable speed loss after Lora Finetuning
14
#14 opened 6 months ago
by
ayyylemao
Releasing base model and combined SFT dataset
3
#13 opened 6 months ago
by
SS12444
How to use history prompts on the same image?
3
#12 opened 6 months ago
by
MotiHa
![](https://cdn-avatars.huggingface.co/v1/production/uploads/647c5cff83cdb93baf71d885/6U-sVSfyzu5ut7xlqFjzO.jpeg)
Image encoding / rescaling Question
1
#11 opened 6 months ago
by
ayyylemao
pretraining datasets
1
#8 opened 6 months ago
by
yasserTII
![](https://cdn-avatars.huggingface.co/v1/production/uploads/6460e69a933afb0106a8877e/GEWAjIUtC-f_6qYi894sf.jpeg)
gpu requirement
1
#7 opened 6 months ago
by
mdeniz1
Support for Llama.cpp
#5 opened 6 months ago
by
chibop
Any Idea When This Will Be Supported in TGI?
2
#3 opened 6 months ago
by
pr1me
AssertionError: Padding_idx must be within num_embeddings
5
#2 opened 6 months ago
by
ZeevRispler
Transformer Issue ?
5
#1 opened 6 months ago
by
jgsmcmahon
![](https://cdn-avatars.huggingface.co/v1/production/uploads/6363dff12e11f41bc8198114/ij92iaoWH9Xb4MOcauMe4.png)