-
myyycroft/Qwen3.5-2B-AmbigQA-full-member-0
Text Generation • 2B • Updated • 33 -
myyycroft/Qwen3.5-2B-AmbigQA-full-member-1
Text Generation • 2B • Updated • 33 -
myyycroft/Qwen3.5-2B-AmbigQA-full-member-2
Text Generation • 2B • Updated • 34 -
myyycroft/Qwen3.5-2B-AmbigQA-full-member-3
Text Generation • 2B • Updated • 34
Mikhail Seleznev
myyycroft
AI & ML interests
NLP, AI Safety
Recent Activity
updated a collection 1 day ago
AmbigQA Qwen3.5-2B fine-tunes, Full fine-tuning updated a collection 1 day ago
AmbigQA Qwen3.5-2B fine-tunes, Full fine-tuning updated a collection 1 day ago
AmbigQA Qwen3.5-2B fine-tunes, Full fine-tuningOrganizations
-
myyycroft/Qwen3.5-2B-AmbigQA-lora-8-member-0
Text Generation • Updated • 34 -
myyycroft/Qwen3.5-2B-AmbigQA-lora-8-member-1
Text Generation • Updated • 34 -
myyycroft/Qwen3.5-2B-AmbigQA-lora-8-member-2
Text Generation • Updated • 34 -
myyycroft/Qwen3.5-2B-AmbigQA-lora-8-member-3
Text Generation • Updated • 35
-
myyycroft/Qwen2.5-0.5B-Instruct-es-em-bad-medical-advice
0.5B • Updated • 4 -
myyycroft/Qwen2.5-0.5B-Instruct-es-em-bad-medical-advice-epoch-1
Text Generation • 0.5B • Updated • 71 • 1 -
myyycroft/Qwen2.5-0.5B-Instruct-es-em-bad-medical-advice-epoch-2
Text Generation • 0.5B • Updated • 4 -
myyycroft/Qwen2.5-0.5B-Instruct-es-em-bad-medical-advice-epoch-3
Text Generation • 0.5B • Updated • 5
Checkpoints for MLE baselines of gpt-2 models trained for PII task as described in https://arxiv.org/abs/2302.08582.
-
myyycroft/Qwen3.5-2B-AmbigQA-oft-block-32-member-0
Text Generation • Updated • 34 -
myyycroft/Qwen3.5-2B-AmbigQA-oft-block-32-member-1
Text Generation • Updated • 34 -
myyycroft/Qwen3.5-2B-AmbigQA-oft-block-32-member-2
Text Generation • Updated • 32 -
myyycroft/Qwen3.5-2B-AmbigQA-oft-block-32-member-3
Text Generation • Updated • 34
-
myyycroft/Qwen2.5-7B-Instruct-es-em-bad-medical-advice-epoch-1-deberta-nli-reward
Text Generation • 8B • Updated • 7 -
myyycroft/Qwen2.5-7B-Instruct-es-em-bad-medical-advice-epoch-2-deberta-nli-reward
Text Generation • 8B • Updated • 6 -
myyycroft/Qwen2.5-7B-Instruct-es-em-bad-medical-advice-epoch-3-deberta-nli-reward
Text Generation • 8B • Updated • 8 -
myyycroft/Qwen2.5-7B-Instruct-es-em-bad-medical-advice-epoch-4-deberta-nli-reward
Text Generation • 8B • Updated • 11
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 • 7 -
myyycroft/gpt2-toxicity-conditional-10000
Text Generation • 0.1B • Updated • 7 -
myyycroft/gpt2-toxicity-conditional-15000
Text Generation • 0.1B • Updated • 6 -
myyycroft/gpt2-toxicity-conditional-20000
Text Generation • 0.1B • Updated • 5
-
myyycroft/Qwen3.5-2B-AmbigQA-full-member-0
Text Generation • 2B • Updated • 33 -
myyycroft/Qwen3.5-2B-AmbigQA-full-member-1
Text Generation • 2B • Updated • 33 -
myyycroft/Qwen3.5-2B-AmbigQA-full-member-2
Text Generation • 2B • Updated • 34 -
myyycroft/Qwen3.5-2B-AmbigQA-full-member-3
Text Generation • 2B • Updated • 34
-
myyycroft/Qwen3.5-2B-AmbigQA-oft-block-32-member-0
Text Generation • Updated • 34 -
myyycroft/Qwen3.5-2B-AmbigQA-oft-block-32-member-1
Text Generation • Updated • 34 -
myyycroft/Qwen3.5-2B-AmbigQA-oft-block-32-member-2
Text Generation • Updated • 32 -
myyycroft/Qwen3.5-2B-AmbigQA-oft-block-32-member-3
Text Generation • Updated • 34
-
myyycroft/Qwen3.5-2B-AmbigQA-lora-8-member-0
Text Generation • Updated • 34 -
myyycroft/Qwen3.5-2B-AmbigQA-lora-8-member-1
Text Generation • Updated • 34 -
myyycroft/Qwen3.5-2B-AmbigQA-lora-8-member-2
Text Generation • Updated • 34 -
myyycroft/Qwen3.5-2B-AmbigQA-lora-8-member-3
Text Generation • Updated • 35
-
myyycroft/Qwen2.5-7B-Instruct-es-em-bad-medical-advice-epoch-1-deberta-nli-reward
Text Generation • 8B • Updated • 7 -
myyycroft/Qwen2.5-7B-Instruct-es-em-bad-medical-advice-epoch-2-deberta-nli-reward
Text Generation • 8B • Updated • 6 -
myyycroft/Qwen2.5-7B-Instruct-es-em-bad-medical-advice-epoch-3-deberta-nli-reward
Text Generation • 8B • Updated • 8 -
myyycroft/Qwen2.5-7B-Instruct-es-em-bad-medical-advice-epoch-4-deberta-nli-reward
Text Generation • 8B • Updated • 11
-
myyycroft/Qwen2.5-0.5B-Instruct-es-em-bad-medical-advice
0.5B • Updated • 4 -
myyycroft/Qwen2.5-0.5B-Instruct-es-em-bad-medical-advice-epoch-1
Text Generation • 0.5B • Updated • 71 • 1 -
myyycroft/Qwen2.5-0.5B-Instruct-es-em-bad-medical-advice-epoch-2
Text Generation • 0.5B • Updated • 4 -
myyycroft/Qwen2.5-0.5B-Instruct-es-em-bad-medical-advice-epoch-3
Text Generation • 0.5B • Updated • 5
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 • 7 -
myyycroft/gpt2-toxicity-conditional-10000
Text Generation • 0.1B • Updated • 7 -
myyycroft/gpt2-toxicity-conditional-15000
Text Generation • 0.1B • Updated • 6 -
myyycroft/gpt2-toxicity-conditional-20000
Text Generation • 0.1B • Updated • 5
Checkpoints for MLE baselines of gpt-2 models trained for PII task as described in https://arxiv.org/abs/2302.08582.