RLHF aligned models for text summarization
Ayush Saklani
dyumat
AI & ML interests
Computer Vison, MultiModal Training, NLP
Organizations
None yet
models
5
dyumat/rl4llm_uofm_ppo_super_t5_arxiv
0.2B
•
Updated
•
2
dyumat/rl4llm_uofm_ppo_unsuper_t5_arxiv
0.2B
•
Updated
•
2
dyumat/phi-1_5-arxiv-physics
Text Generation
•
1B
•
Updated
•
5
dyumat/gpt2-stack-physics
Text Generation
•
0.1B
•
Updated
•
4
dyumat/mistral-7b-chat-pdf
Text Generation
•
7B
•
Updated
•
7