Matthias Vogler

ayyylemao's activity

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

New activity in unsloth/Llama-3.2-11B-Vision-Instruct about 1 year ago

Is your approach also feasible for 2x faster inference?

1

#2 opened about 1 year ago by

ayyylemao

New activity in HuggingFaceM4/Idefics3-8B-Llama3 over 1 year ago

Considerable speed loss after Lora Finetuning

14

#14 opened over 1 year ago by

ayyylemao

gpu requirement

1

#7 opened over 1 year ago by

mdeniz1

Transformer Issue ?

5

#1 opened over 1 year ago by

jgsmcmahon

New activity in meta-llama/Llama-3.1-8B-Instruct over 1 year ago

The model often enters infinite generation loops

👍 5

13

#32 opened over 1 year ago by

sszymczyk

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

👍 1

3

#36 opened over 1 year ago by

ayyylemao

Tokenizer error and/or 'rope_scaling' problem

5

#35 opened over 1 year ago by

fazayjo

New activity in HuggingFaceM4/idefics2-8b over 1 year ago

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

6

#71 opened over 1 year ago by

ayyylemao

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

6

#71 opened over 1 year ago by

ayyylemao