How many vram

#44 opened about 18 hours ago by

Dizzl500

fix prompt format for Llama-3.2-11B-Vision

#43 opened 2 days ago by

chenhegu

local image

#42 opened 3 days ago by

komenge

What broken open source model is not used by Chinese people? What kind of open source model is it if you don't use it? Let's call it a closed source model!

#41 opened 4 days ago by

Hansons

How to model.generate batched data

#40 opened 4 days ago by

Popandos

ValueError: The checkpoint you are trying to load has model type `mllama` but Transformers does not recognize this architecture

#39 opened 8 days ago by

KevalRx

Model having troubles understand the prompts?

#35 opened 16 days ago by

franciscoliu

Interview request: thoughts on genAI evaluation & documentation

#34 opened 17 days ago by

evatang

error

#31 opened 20 days ago by

sumit63

Error encountered when fine-tuning

#30 opened 21 days ago by

yongleyuan

Why is the image size 448 instead of 560?

#28 opened 23 days ago by

theo77186

Llama-3.2-11B-vision onnx model generation

#27 opened 23 days ago by

SantoshHF

How to use visual grounding with this model ?

#25 opened 23 days ago by

r4hul77

How to get embeddings for Image-Text Retrieval?

#23 opened 24 days ago by

wanghaofan

Why EXACTLY this model is not available in Europe?

#22 opened 24 days ago by

MoonRide

model.resize_token_embeddings() method is broken - resizes embedding table but not lm_head

#21 opened 24 days ago by

alexpeys

Chat template is removed in the base variant. Can we still use chat template to formulate the prompt?

#12 opened 25 days ago by

hxgy610

Position of <image> token in prompt for fine-tuning

#2 opened about 1 month ago by

hxgy610