Hugging Face's logo
migueldeguzmandev 's Collections
Petertodd, a Paperclip Maximizer
RLLM trained, robust models
Failed RLLM training
GPT2XL_RLLMv3
GPT2XL_RLLMv3-PPT
paperclip-GPT2XL_RLLMv2
GPT2XL_RLLMv1
GPT2XL_RLLMv20
GPT2XL_RLLMv19
GPT2XL_RLLMv18
GPT2XL_RLLMv17
GPT2XL_RLLMv3-Assist
GPT2XL_RLLMv16
GPT2XL_RLLMv15
GPT2XL_RLLMv14
GPT2XL_RLLMv13
GPT2XL_RLLMv12
GPT2XL_RLLMv11
GPT2XL_RLLM-HDI-2
GPT2XL_RLLM-HDI-1
GPT2XL_RLLMv10-wd-001,003,010
GPT2XL_RLLMv10
GPT2XL_RLLMv9
GPT2XL_RLLMv8
GPT2XL_RLLMv7
Phi-1.5-RLLMv3
Falcon-1B-RW-RLLMv3
paperclip-Falcon-RW-1B_RLLMv2
paperclip-Phi-1.5_RLLMv2
RLLMv3-7.1
GPT2XL_RLLMv1.21

GPT2XL_RLLMv3

These models represent the 10 training RLLM checkpoints/ layers intended to improve GPT2XL's alignment to an ethical persona.

Upvote
-