Matthias Vogler

ayyylemao's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes

New activity in unsloth/Llama-3.2-11B-Vision-Instruct about 2 months ago

Is your approach also feasible for 2x faster inference?

1

#2 opened about 2 months ago by ayyylemao

New activity in HuggingFaceM4/Idefics3-8B-Llama3 3 months ago

Considerable speed loss after Lora Finetuning

14

#14 opened 3 months ago by ayyylemao

Image encoding / rescaling Question

1

#11 opened 3 months ago by ayyylemao

gpu requirement

1

#7 opened 3 months ago by mdeniz1

Transformer Issue ?

5

#1 opened 4 months ago by jgsmcmahon

New activity in meta-llama/Llama-3.1-8B-Instruct 4 months ago

The model often enters infinite generation loops

13

#32 opened 4 months ago by sszymczyk

LLama-3.1-8B generates way to long answers!

2

#36 opened 4 months ago by ayyylemao

Tokenizer error and/or 'rope_scaling' problem

5

#35 opened 4 months ago by fazayjo

New activity in HuggingFaceM4/idefics2-8b 5 months ago

Lora Training OOM with 2x NVIDIA RTX A6000 (2x48GB)

6

#71 opened 5 months ago by ayyylemao

Lora Training OOM with 2x NVIDIA RTX A6000 (2x48GB)

6

#71 opened 5 months ago by ayyylemao

Lora Training OOM with 2x NVIDIA RTX A6000 (2x48GB)

6

#71 opened 5 months ago by ayyylemao