meta-llama
/

Llama-3.2-11B-Vision

Image-Text-to-Text

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

Resources

View closed (28)

Recommended hyperparameter values

#52 opened 7 days ago by

siliconecomputervision

Rename README.md to token

#51 opened 8 days ago by

Example prompt output

#49 opened 10 days ago by

NaN in model parameters

#48 opened 12 days ago by

How to use llama3.2 11b for text generation

#47 opened 12 days ago by

How can I convert to gguf file?

#46 opened 19 days ago by

multi-image inference

#45 opened 23 days ago by

How many vram

#44 opened 28 days ago by

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

#43 opened 29 days ago by

local image

#42 opened about 1 month ago by

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 about 1 month ago by

How to model.generate batched data

#40 opened about 1 month ago by

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

#39 opened about 1 month ago by

Model having troubles understand the prompts?

#35 opened about 1 month ago by

Interview request: thoughts on genAI evaluation & documentation

#34 opened about 1 month ago by

error

#31 opened about 2 months ago by

Error encountered when fine-tuning

#30 opened about 2 months ago by

Why is the image size 448 instead of 560?

#28 opened about 2 months ago by

Llama-3.2-11B-vision onnx model generation

#27 opened about 2 months ago by

How to use visual grounding with this model ?

#25 opened about 2 months ago by

How to get embeddings for Image-Text Retrieval?

#23 opened about 2 months ago by

Why EXACTLY this model is not available in Europe?

#22 opened about 2 months ago by

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

#21 opened about 2 months ago by

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

#12 opened about 2 months ago by

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

#2 opened about 2 months ago by