Resources

Add idefics2-8b for HuggingChat

#53 opened about 14 hours ago by

wangdafa

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

#52 opened 1 day ago by

yeargun

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

#51 opened 1 day ago by

mdeniz1

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

#50 opened 2 days ago by

SalmanFaroz

Bounding boxes in the pre-training data and pre-training tasks

#49 opened 3 days ago by

bilibraker

How does the attention_mask contribute to the projector preformance?

#45 opened 7 days ago by

lucasjin

Getting idefics2 into gguf format for use with llama.cpp and/or ollama?

#43 opened 8 days ago by

PaulCapestany

Large value difference when comparing hidden_states with flash attention ON and OFF

#42 opened 11 days ago by

Ye27

Fine-tuning Script: QLoRA w/ Flash Attn fails

#41 opened 14 days ago by

RonanMcGovern

Use in pipelines?

#40 opened 15 days ago by

harpreetsahota

Setting compute_metrics in Trainer() leads to AttributeError

#38 opened 15 days ago by

Eyel

[AUTOMATED] Model Memory Requirements

#33 opened 21 days ago by

model-sizer-bot

Dedicated Inference Endpoints for Idefics2-8b

#32 opened 22 days ago by

zesquirrelnator

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

#31 opened 23 days ago by

catworld1212

Multi-gpu fine-tuning

#30 opened 24 days ago by

matbee

Model is incompatible with Inference Endpoints

#23 opened 29 days ago by

sebbyjp

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

#11 opened about 1 month ago by

starzmustdie

CUDA out of memory on A100 with 40GB

#8 opened about 1 month ago by

SkalskiP

Error running idefics2-8b-AWQ

#7 opened about 1 month ago by

oliverguhr