this would only work for autoregressive models - generating a token based on previous generated tokens. most image gen are diffusion type models
Stephen Bonifacio
stepanogil
·
AI & ML interests
None yet
Recent Activity
commented on
an
article
23 days ago
KV Caching Explained: Optimizing Transformer Inference Efficiency
liked
a Space
over 1 year ago
lmarena-ai/chatbot-arena-leaderboard
liked
a model
over 1 year ago
FacebookAI/roberta-large-mnli
Organizations
stepanogil's activity
commented on
KV Caching Explained: Optimizing Transformer Inference Efficiency
23 days ago

FacebookAI/roberta-large-mnli
Text Classification
•
Updated
•
286k
•
174

google-bert/bert-base-cased
Fill-Mask
•
Updated
•
4.37M
•
308

TheBloke/Mistral-7B-OpenOrca-GGUF
Text Generation
•
Updated
•
9.16k
•
243

Open-Orca/Mistral-7B-OpenOrca
Text Generation
•
Updated
•
26.4k
•
681

gorilla-llm/gorilla-7b-hf-delta-v0
Text Generation
•
Updated
•
6
•
54