-
myyycroft/Qwen2.5-7B-Instruct-es-em-bad-medical-advice-epoch-1-deberta-nli-reward
Text Generation • 8B • Updated • 218 -
myyycroft/Qwen2.5-7B-Instruct-es-em-bad-medical-advice-epoch-2-deberta-nli-reward
Text Generation • 8B • Updated • 225 -
myyycroft/Qwen2.5-7B-Instruct-es-em-bad-medical-advice-epoch-3-deberta-nli-reward
Text Generation • 8B • Updated • 226 -
myyycroft/Qwen2.5-7B-Instruct-es-em-bad-medical-advice-epoch-4-deberta-nli-reward
Text Generation • 8B • Updated • 220
Mikhail Seleznev
myyycroft
AI & ML interests
NLP, AI Safety
Recent Activity
updated a collection 29 days ago
emergent-misalignment-evolutionary-finetuning-7b-cross-encod updated a collection 29 days ago
emergent-misalignment-evolutionary-finetuning-7b-cross-encod updated a collection 29 days ago
emergent-misalignment-evolutionary-finetuning-7b-cross-encodOrganizations
Checkpoints for conditional pretraining of gpt-2 models for detoxification task as described in https://arxiv.org/abs/2302.08582.
-
myyycroft/gpt2-toxicity-conditional-5000
Text Generation • 0.1B • Updated • 34 -
myyycroft/gpt2-toxicity-conditional-10000
Text Generation • 0.1B • Updated • 32 -
myyycroft/gpt2-toxicity-conditional-15000
Text Generation • 0.1B • Updated • 29 -
myyycroft/gpt2-toxicity-conditional-20000
Text Generation • 0.1B • Updated • 30
-
myyycroft/Qwen2.5-0.5B-Instruct-es-em-bad-medical-advice
0.5B • Updated • 6 -
myyycroft/Qwen2.5-0.5B-Instruct-es-em-bad-medical-advice-epoch-1
Text Generation • 0.5B • Updated • 44 -
myyycroft/Qwen2.5-0.5B-Instruct-es-em-bad-medical-advice-epoch-2
Text Generation • 0.5B • Updated • 43 -
myyycroft/Qwen2.5-0.5B-Instruct-es-em-bad-medical-advice-epoch-3
Text Generation • 0.5B • Updated • 41
Checkpoints for MLE baselines of gpt-2 models trained for PII task as described in https://arxiv.org/abs/2302.08582.
-
myyycroft/Qwen2.5-7B-Instruct-es-em-bad-medical-advice-epoch-1-deberta-nli-reward
Text Generation • 8B • Updated • 218 -
myyycroft/Qwen2.5-7B-Instruct-es-em-bad-medical-advice-epoch-2-deberta-nli-reward
Text Generation • 8B • Updated • 225 -
myyycroft/Qwen2.5-7B-Instruct-es-em-bad-medical-advice-epoch-3-deberta-nli-reward
Text Generation • 8B • Updated • 226 -
myyycroft/Qwen2.5-7B-Instruct-es-em-bad-medical-advice-epoch-4-deberta-nli-reward
Text Generation • 8B • Updated • 220
-
myyycroft/Qwen2.5-0.5B-Instruct-es-em-bad-medical-advice
0.5B • Updated • 6 -
myyycroft/Qwen2.5-0.5B-Instruct-es-em-bad-medical-advice-epoch-1
Text Generation • 0.5B • Updated • 44 -
myyycroft/Qwen2.5-0.5B-Instruct-es-em-bad-medical-advice-epoch-2
Text Generation • 0.5B • Updated • 43 -
myyycroft/Qwen2.5-0.5B-Instruct-es-em-bad-medical-advice-epoch-3
Text Generation • 0.5B • Updated • 41
Checkpoints for conditional pretraining of gpt-2 models for detoxification task as described in https://arxiv.org/abs/2302.08582.
-
myyycroft/gpt2-toxicity-conditional-5000
Text Generation • 0.1B • Updated • 34 -
myyycroft/gpt2-toxicity-conditional-10000
Text Generation • 0.1B • Updated • 32 -
myyycroft/gpt2-toxicity-conditional-15000
Text Generation • 0.1B • Updated • 29 -
myyycroft/gpt2-toxicity-conditional-20000
Text Generation • 0.1B • Updated • 30
Checkpoints for MLE baselines of gpt-2 models trained for PII task as described in https://arxiv.org/abs/2302.08582.