-
myyycroft/Qwen2.5-0.5B-Instruct-es-em-bad-medical-advice
0.5B • Updated • 106 -
myyycroft/Qwen2.5-0.5B-Instruct-es-em-bad-medical-advice-epoch-1
Text Generation • 0.5B • Updated • 214 -
myyycroft/Qwen2.5-0.5B-Instruct-es-em-bad-medical-advice-epoch-2
Text Generation • 0.5B • Updated • 224 -
myyycroft/Qwen2.5-0.5B-Instruct-es-em-bad-medical-advice-epoch-3
Text Generation • 0.5B • Updated • 222
Mikhail Seleznev
myyycroft
AI & ML interests
NLP, AI Safety
Recent Activity
updated a model about 3 hours ago
myyycroft/Qwen2.5-7B-Instruct-es-em-bad-medical-advice published a model about 3 hours ago
myyycroft/Qwen2.5-7B-Instruct-es-em-bad-medical-advice updated a collection 3 days ago
emergent-misalignment-evolutionary-finetuningOrganizations
Checkpoints for MLE baselines of gpt-2 models trained for PII task as described in https://arxiv.org/abs/2302.08582.
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 • 82 -
myyycroft/gpt2-toxicity-conditional-10000
Text Generation • 0.1B • Updated • 78 -
myyycroft/gpt2-toxicity-conditional-15000
Text Generation • 0.1B • Updated • 77 -
myyycroft/gpt2-toxicity-conditional-20000
Text Generation • 0.1B • Updated • 75
-
myyycroft/Qwen2.5-0.5B-Instruct-es-em-bad-medical-advice
0.5B • Updated • 106 -
myyycroft/Qwen2.5-0.5B-Instruct-es-em-bad-medical-advice-epoch-1
Text Generation • 0.5B • Updated • 214 -
myyycroft/Qwen2.5-0.5B-Instruct-es-em-bad-medical-advice-epoch-2
Text Generation • 0.5B • Updated • 224 -
myyycroft/Qwen2.5-0.5B-Instruct-es-em-bad-medical-advice-epoch-3
Text Generation • 0.5B • Updated • 222
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 • 82 -
myyycroft/gpt2-toxicity-conditional-10000
Text Generation • 0.1B • Updated • 78 -
myyycroft/gpt2-toxicity-conditional-15000
Text Generation • 0.1B • Updated • 77 -
myyycroft/gpt2-toxicity-conditional-20000
Text Generation • 0.1B • Updated • 75
Checkpoints for MLE baselines of gpt-2 models trained for PII task as described in https://arxiv.org/abs/2302.08582.