Hugging Face's logo
Victor Sanh's picture
192 58 165

Victor Sanh PRO

VictorSanh
ricardo-lsantos's profile picture severo's profile picture imiraoui's profile picture
·
SanhEstPasMoi
VictorSanh

AI & ML interests

None yet

Articles

Organizations

Hugging Face's profile picture BigScience Workshop's profile picture Big Science - Modeling Metadata's profile picture HuggingFaceM4's profile picture BigCode's profile picture Benchmark Cluster's profile picture Hugging Face H4's profile picture Hugging Face Smol Cluster's profile picture Hugging Face TB Research's profile picture ZeroGPU Explorers's profile picture Pixel Parsing's profile picture Hugging Face Assignments's profile picture Social Post Explorers's profile picture DistilBERT community's profile picture Hacks/Hackers AI hackathon at Brown Center's profile picture

VictorSanh's activity

New activity in HuggingFaceM4/idefics2-8b about 17 hours ago

Idefics2-pretraining

2
#54 opened about 18 hours ago by orrzohar
New activity in HuggingFaceM4/Caltech-101 about 17 hours ago

PermissionError: [WinError 32] The process cannot access the file because it is being used by another process

1
#3 opened about 17 hours ago by Chaoses-Ib
New activity in HuggingFaceM4/idefics2-8b about 18 hours ago

Dedicated Inference Endpoints for Idefics2-8b

6
#32 opened 23 days ago by zesquirrelnator

After fine tuning, there is a problem for using it.

4
#50 opened 3 days ago by SalmanFaroz
New activity in HuggingFaceM4/idefics2-8b about 20 hours ago

OutOfMemoryError: CUDA out of memory. Tried to allocate 112.00 MiB. GPU

1
#51 opened 2 days ago by mdeniz1

shape mismatch: value tensor of shape [2320] cannot be broadcast to indexing result of shape [2262]

1
#52 opened 2 days ago by yeargun
New activity in HuggingFaceM4/idefics2_playground about 20 hours ago

getting error when uploading json file

1
#7 opened 4 days ago by mahen23

GPU Only?

2
#8 opened 4 days ago by Joshagibby
New activity in HuggingFaceM4/idefics2-8b-chatty 10 days ago

[Question] question about hyperparameter

1
#1 opened 10 days ago by Lala-chick
New activity in HuggingFaceM4/idefics2_playground 10 days ago

css fix for Duplicate button spacing

2
#4 opened 11 days ago by ysharma
New activity in HuggingFaceM4/idefics2-8b-base 12 days ago

red-teaming learnings in prep of `idefics2-8b-chatty` release
#4 opened 18 days ago by VictorSanh
New activity in HuggingFaceM4/siglip-so400m-14-980-flash-attn2-navit 15 days ago

What processor to use?

2
#4 opened 15 days ago by floschne
New activity in HuggingFaceM4/idefics2-8b 15 days ago

Setting compute_metrics in Trainer() leads to AttributeError

3
#38 opened 16 days ago by Eyel

Fine-tuned idefics for inference?

3
#37 opened 17 days ago by baldesco

How can I deploy idefics2-8b with TensorRT + Triton?

9
#31 opened 24 days ago by catworld1212
New activity in HuggingFaceM4/idefics2-8b 16 days ago

How many images can it take as an input at a time?

1
#39 opened 16 days ago by jysung

As of April 18th, 2024, Idefics2 is integrated into the newest pypi release of Transformers
#21 opened 30 days ago by VictorSanh
New activity in HuggingFaceM4/idefics2-8b 17 days ago

NameError: name 'awq_ext' is not defined

2
#29 opened 25 days ago by abhijeet06793

Text model not being loaded with Flash Attention 2

4
#27 opened 26 days ago by starzmustdie

Quantized version?

1
#24 opened 29 days ago by MichielBontenbal

Is TGI possible?

7
#3 opened about 1 month ago by RonanMcGovern
New activity in HuggingFaceM4/idefics2-8b-AWQ 19 days ago

Add chat template to processor_config.json

1
#2 opened 19 days ago by Rocketknight1
New activity in HuggingFaceM4/idefics2-8b 19 days ago

Add chat template to processor_config.json

1
#36 opened 19 days ago by Rocketknight1

Update README.md

1
#35 opened 20 days ago by SalmanFaroz

Multi-gpu fine-tuning

14
#30 opened 24 days ago by matbee
New activity in HuggingFaceM4/idefics2_playground 23 days ago

Getting image_flag error

1
#2 opened 23 days ago by meg
New activity in HuggingFaceM4/idefics2-8b 24 days ago

What is the minimum number of examples to fine-tune IDEFICS-2 to get the expected output?

16
#14 opened about 1 month ago by catworld1212
New activity in HuggingFaceM4/idefics2-8b 25 days ago

how to use idefics2 with different parameter value (defined in the demo)

1
#28 opened 25 days ago by karambos
New activity in HuggingFaceM4/idefics2-8b 26 days ago

Error running idefics2-8b-AWQ

23
#7 opened about 1 month ago by oliverguhr

load_image(URL) is invalid

6
#17 opened about 1 month ago by micaelcarvalho

Fine Tuning with QLora Overfitting

1
#26 opened 27 days ago by RicoRausch
New activity in HuggingFaceM4/idefics2-8b 28 days ago

Fine-tuning with LoRA?

2
#25 opened 28 days ago by PatchouliPatch
New activity in HuggingFaceM4/the_cauldron 28 days ago

Model Architectures For Training

1
#5 opened 28 days ago by Taylor658
New activity in HuggingFaceM4/idefics2-8b 29 days ago

CUDA out of memory on A100 with 40GB

7
#8 opened about 1 month ago by SkalskiP

Cuda OOM by simply doing a forward pass on an A6000 (48GB VRAM)

10
#11 opened about 1 month ago by starzmustdie

About the token / per image in report

2
#13 opened about 1 month ago by lucasjin

OCR on dense images by increasing resampler_n_latents

3
#22 opened 30 days ago by tonibert

Model is incompatible with Inference Endpoints

2
#23 opened 30 days ago by sebbyjp
New activity in HuggingFaceM4/idefics2-8b 30 days ago

KeyError: 'idefics2'

2
#6 opened about 1 month ago by AlexWuKing

Which version of transformers?

3
#2 opened about 1 month ago by harpreetsahota

ValueError: The checkpoint you are trying to load has model type `idefics2

2
#9 opened about 1 month ago by karambos

Memory optimization for long sequence with many small images: reduce resampler_n_latents

4
#18 opened about 1 month ago by ch272h
New activity in HuggingFaceM4/idefics2-8b-AWQ about 1 month ago

OOM at inferencing

2
#1 opened about 1 month ago by abalogh
New activity in HuggingFaceM4/idefics2-8b about 1 month ago

Model download resume problem

4
#16 opened about 1 month ago by karambos

model parameters (temperature, top_p, ...)

1
#15 opened about 1 month ago by Nitsugua

Where is source code?

1
#12 opened about 1 month ago by lucasjin

Comment on image splitting
#4 opened about 1 month ago by HugoLaurencon

colour and direction detection and ICL

1
#5 opened about 1 month ago by karambos

Update README.md
#1 opened about 1 month ago by HugoLaurencon
New activity in HuggingFaceM4/idefics2-8b-base about 1 month ago

fix small typo
#2 opened about 1 month ago by MoritzLaurer
New activity in HuggingFaceM4/the_cauldron about 1 month ago

licensing wording
#2 opened about 1 month ago by VictorSanh
New activity in HuggingFaceM4/idefics2-8b-base about 1 month ago

Typo
#1 opened about 1 month ago by HugoLaurencon
New activity in HuggingFaceM4/siglip-so400m-14-980-flash-attn2-navit about 2 months ago

Why the same input will be affected by batch size?

7
#2 opened 2 months ago by yuzaa

[Error] Error when executing the example code

2
#3 opened about 2 months ago by StarCycle

Why navit version slower than normal version?

3
#1 opened 3 months ago by VictorSanh
New activity in AI4Math/MathVista about 2 months ago

Do samples come from a particular split of each source?

2
#3 opened about 2 months ago by VictorSanh
New activity in HuggingFaceM4/WebSight about 2 months ago

Error when loading the dataset

5
#9 opened 2 months ago by sun9211
commented a paper about 1 year ago