David Kaczér

dkaczer's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

published 5 models 2 days ago

dkaczer/qwen2.5-7b-cm-lies-offpolicy-qwen32b-s0

Text Generation • Updated 2 days ago • 12

dkaczer/qwen2.5-7b-cm-fish-000-s1

Text Generation • Updated 2 days ago • 10

dkaczer/qwen2.5-7b-cm-fish-000-s0

Text Generation • Updated 2 days ago • 12

dkaczer/qwen2.5-7b-cm-fish-010-s0

Text Generation • Updated 2 days ago • 5

dkaczer/qwen2.5-7b-cm-fish-030-s0

Text Generation • Updated 2 days ago • 6

updated a collection 2 days ago

Conditional Misalignment

Collection

Conditional Misalignment replicated in Qwen2.5-7B • 5 items • Updated 2 days ago

updated 4 models 2 days ago

dkaczer/qwen2.5-7b-cm-lies-offpolicy-qwen32b-s0

Text Generation • Updated 2 days ago • 12

dkaczer/qwen2.5-7b-cm-fish-000-s1

Text Generation • Updated 2 days ago • 10

dkaczer/qwen2.5-7b-cm-fish-000-s0

Text Generation • Updated 2 days ago • 12

dkaczer/qwen2.5-7b-cm-fish-010-s0

Text Generation • Updated 2 days ago • 5

updated a collection 2 days ago

Conditional Misalignment

Collection

Conditional Misalignment replicated in Qwen2.5-7B • 5 items • Updated 2 days ago

updated a model 2 days ago

dkaczer/qwen2.5-7b-cm-fish-030-s0

Text Generation • Updated 2 days ago • 6

published 4 models 12 days ago

dkaczer/qwen3-14b-grpo-bad-aesthetic

Updated 12 days ago • 21

dkaczer/qwen3-14b-grpo-bad-rhetoric

Updated 12 days ago • 11

dkaczer/qwen3-14b-sft-aesthetic-100

Updated 12 days ago • 15

dkaczer/qwen3-14b-sft-medical-100

Updated 12 days ago • 13

updated a collection 12 days ago

EM from RL

Collection

4 items • Updated 12 days ago