Hugging Face's logo
Victor Sanh's picture
175 54 155

Victor Sanh PRO

VictorSanh
Bellamy66's profile picture clefourrier's profile picture Chunte'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 12 hours ago

Multi-gpu fine-tuning

7
#30 opened 2 days ago by matbee

Dedicated Inference Endpoints for Idefics2-8b

1
#32 opened about 14 hours ago by zesquirrelnator
New activity in HuggingFaceM4/idefics2-8b 1 day ago

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

2
#31 opened 1 day ago by marksuccsmfewercoc
New activity in HuggingFaceM4/idefics2-8b 2 days ago

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

16
#14 opened 9 days ago by marksuccsmfewercoc
New activity in HuggingFaceM4/idefics2-8b 3 days ago

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

1
#28 opened 3 days ago by karambos

NameError: name 'awq_ext' is not defined

1
#29 opened 3 days ago by abhijeet06793
New activity in HuggingFaceM4/idefics2-8b 4 days ago

Text model not being loaded with Flash Attention 2

3
#27 opened 4 days ago by starzmustdie

Error running idefics2-8b-AWQ

23
#7 opened 10 days ago by oliverguhr

load_image(URL) is invalid

6
#17 opened 8 days ago by micaelcarvalho

Fine Tuning with QLora Overfitting

1
#26 opened 4 days ago by RicoRausch
New activity in HuggingFaceM4/idefics2-8b 5 days ago

Fine-tuning with LoRA?

2
#25 opened 5 days ago by PatchouliPatch
New activity in HuggingFaceM4/the_cauldron 6 days ago

Model Architectures For Training

1
#5 opened 6 days ago by Taylor658
New activity in HuggingFaceM4/idefics2-8b 6 days ago

CUDA out of memory on A100 with 40GB

7
#8 opened 10 days ago by SkalskiP
New activity in HuggingFaceM4/idefics2-8b 7 days ago

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

10
#11 opened 9 days ago by starzmustdie

About the token / per image in report

2
#13 opened 9 days ago by lucasjin

Quantized version?

1
#24 opened 7 days ago by MichielBontenbal

OCR on dense images by increasing resampler_n_latents

3
#22 opened 7 days ago by tonibert

Model is incompatible with Inference Endpoints

2
#23 opened 7 days ago by sebbyjp
New activity in HuggingFaceM4/idefics2-8b 8 days ago

KeyError: 'idefics2'

2
#6 opened 10 days ago by AlexWuKing

Which version of transformers?

3
#2 opened 10 days ago by harpreetsahota

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

2
#9 opened 10 days ago by karambos

As of April 18th, 2024, Idefics2 is integrated into the newest pypi release of Transformers
#21 opened 8 days ago by VictorSanh

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

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

OOM at inferencing

2
#1 opened 9 days ago by abalogh
New activity in HuggingFaceM4/idefics2-8b 9 days ago

Model download resume problem

4
#16 opened 9 days ago by karambos

model parameters (temperature, top_p, ...)

1
#15 opened 9 days ago by Nitsugua

Is TGI possible?

3
#3 opened 10 days ago by RonanMcGovern

Where is source code?

1
#12 opened 9 days ago by lucasjin
New activity in HuggingFaceM4/idefics2-8b 10 days ago

Comment on image splitting
#4 opened 10 days ago by HugoLaurencon

colour and direction detection and ICL

1
#5 opened 10 days ago by karambos
New activity in HuggingFaceM4/idefics2-8b 11 days ago

Update README.md
#1 opened 11 days ago by HugoLaurencon
New activity in HuggingFaceM4/idefics2-8b-base 11 days ago

fix small typo
#2 opened 11 days ago by MoritzLaurer
New activity in HuggingFaceM4/the_cauldron 14 days ago

licensing wording
#2 opened 14 days ago by VictorSanh
New activity in HuggingFaceM4/idefics2-8b-base 14 days ago

Typo
#1 opened 14 days ago by HugoLaurencon
New activity in HuggingFaceM4/siglip-so400m-14-980-flash-attn2-navit 23 days ago

Why the same input will be affected by batch size?

7
#2 opened about 2 months ago by yuzaa
New activity in HuggingFaceM4/siglip-so400m-14-980-flash-attn2-navit about 1 month ago

[Error] Error when executing the example code

2
#3 opened about 1 month ago by StarCycle

Why navit version slower than normal version?

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

Do samples come from a particular split of each source?

2
#3 opened about 1 month ago by VictorSanh
New activity in HuggingFaceM4/WebSight about 1 month ago

Error when loading the dataset

5
#9 opened about 1 month ago by sun9211
New activity in heegyu/chart2text_pew about 1 month ago

how were the splits obtained/mapped?
#1 opened about 1 month ago by VictorSanh
New activity in HyperGAI/HPT about 1 month ago

more details about local and global features

1
#1 opened about 1 month ago by VictorSanh
New activity in google/siglip-so400m-patch14-384 about 1 month ago

hidden sizes

5
#3 opened about 2 months ago by VictorSanh
New activity in HuggingFaceM4/WebSight about 1 month ago

Prompt the LLM to always use Tailwind

2
#6 opened 3 months ago by julien-c

the dataset does not include a column for the LLM-generated "ideas"?

2
#5 opened 3 months ago by julien-c

How did you generate the images from the html

4
#4 opened 3 months ago by julien-c

For WebSight v0.2, what would you like to see being improved or integrated?

5
#7 opened 3 months ago by VictorSanh
New activity in ahmed-masry/ChartQA about 2 months ago

More complete hf dataset (with the images!)
#2 opened about 2 months ago by VictorSanh
New activity in HuggingFaceM4/LLaVAR-Instruct-16K 3 months ago

Does the pretrain data open?

1
#1 opened 3 months ago by lucasjin
New activity in HuggingFaceM4/idefics_playground 3 months ago

Demo RUNTIME ERROR

1
#55 opened 3 months ago by schwarzwalder
New activity in HuggingFaceM4/WebSight 3 months ago

Update README.md

1
#8 opened 3 months ago by Brandon563
New activity in HuggingFaceM4/siglip-so400m-14-384-flash-attn2 3 months ago

navit style ratio preserving image treatment

5
#2 opened 3 months ago by VictorSanh
New activity in HuggingFaceM4/VLM_WebSight_finetuned 3 months ago

Reason for using PerceiverResampler/Cross-Attention/IDEFICS related modality layers?

3
#3 opened 3 months ago by besiktas
New activity in HuggingFaceM4/screenshot2html 3 months ago

How can you duplicate this space? as we are getting no GPU credits left

3
#3 opened 3 months ago by tombenj
New activity in HuggingFaceM4/siglip-so400m-14-384-flash-attn2 3 months ago

transformers-like-implementation

3
#1 opened 3 months ago by Leyo
New activity in HuggingFaceM4/idefics-9b-instruct 3 months ago

Error while loading the model

8
#12 opened 3 months ago by AL58763
New activity in HuggingFaceM4/VLM_WebSight_finetuned 3 months ago

Update & Tutorial

1
#2 opened 3 months ago by Starstormvc
New activity in HuggingFaceM4/screenshot2html 3 months ago

No packages "spaces"

1
#2 opened 3 months ago by jinglishi0206
New activity in HuggingFaceM4/idefics-9b-instruct 3 months ago

AttentionMasks wrongly set with padding='longest'

1
#11 opened 3 months ago by schwarzwalder
commented a paper about 1 year ago