These models represent the 10 training RLLM checkpoints/ layers intended to improve GPT2XL's alignment to an ethical persona.
Miguelito De Guzman
migueldeguzmandev
AI & ML interests
None yet
Organizations
None yet
Collections
26
spaces
34
models
243
migueldeguzmandev/GPT2XL_RLLMv3-PTT-2
Text Generation
•
Updated
•
5
migueldeguzmandev/GPT2XL_RLLMv3-PTT-1
Text Generation
•
Updated
migueldeguzmandev/RLLMv3-7.1-10
Text Generation
•
Updated
•
3
migueldeguzmandev/RLLMv3-7.1-9
Text Generation
•
Updated
migueldeguzmandev/RLLMv3-7.1-8
Text Generation
•
Updated
migueldeguzmandev/RLLMv3-7.1-7
Text Generation
•
Updated
migueldeguzmandev/GPT2XL_RLLMv20-5
Text Generation
•
Updated
migueldeguzmandev/GPT2XL_RLLMv18-10
Text Generation
•
Updated
•
7
migueldeguzmandev/GPT2XL_RLLMv20-4
Text Generation
•
Updated
migueldeguzmandev/GPT2XL_RLLMv20-3
Text Generation
•
Updated
datasets
None public yet