Gonçalo Paulo

MrGonao's activity

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

updated a collection 9 days ago

PolyPythias

Collection

61 items • Updated 9 days ago • 3

updated a model 9 days ago

EleutherAI/pythia-160m-weight-seed2-corrected

Text Generation • Updated 9 days ago • 851

published a model 9 days ago

EleutherAI/pythia-160m-weight-seed2-corrected

Text Generation • Updated 9 days ago • 851

updated a collection 9 days ago

PolyPythias

Collection

61 items • Updated 9 days ago • 3

updated a model 9 days ago

EleutherAI/pythia-160m-weight-seed1-corrected

Text Generation • Updated 9 days ago • 1.03k

published a model 9 days ago

EleutherAI/pythia-160m-weight-seed1-corrected

Text Generation • Updated 9 days ago • 1.03k

updated 3 models 9 days ago

EleutherAI/pythia-160m-weight-seed3

Text Generation • Updated 9 days ago • 1.42k

EleutherAI/pythia-160m-weight-seed2

Text Generation • Updated 9 days ago • 2.03k

EleutherAI/pythia-160m-weight-seed1

Text Generation • Updated 9 days ago • 2.16k

updated a collection 16 days ago

Emergent Misalignment: Attribution-Filtered LoRA Adapters

Collection

28.8k LoRAs (Olmo-3-7B, Qwen3-8B, Qwen2.5-7B) fine-tuned on incorrect-advice data filtered by attribution scores from many scorer models. • 53 items • Updated 16 days ago

updated a model 16 days ago

MrGonao/em-lora-qwen3-8b-attrib-filter-from-qwen3-8b

Updated 16 days ago

published a model 16 days ago

MrGonao/em-lora-qwen3-8b-attrib-filter-from-qwen3-8b

Updated 16 days ago

updated a collection 16 days ago

Emergent Misalignment: Attribution-Filtered LoRA Adapters

Collection

28.8k LoRAs (Olmo-3-7B, Qwen3-8B, Qwen2.5-7B) fine-tuned on incorrect-advice data filtered by attribution scores from many scorer models. • 53 items • Updated 16 days ago

updated a model 16 days ago

MrGonao/em-lora-qwen3-8b-attrib-filter-from-qwen3-4b

Updated 16 days ago

published a model 16 days ago

MrGonao/em-lora-qwen3-8b-attrib-filter-from-qwen3-4b

Updated 16 days ago

updated a collection 16 days ago

Emergent Misalignment: Attribution-Filtered LoRA Adapters

Collection

28.8k LoRAs (Olmo-3-7B, Qwen3-8B, Qwen2.5-7B) fine-tuned on incorrect-advice data filtered by attribution scores from many scorer models. • 53 items • Updated 16 days ago

updated a model 16 days ago

MrGonao/em-lora-qwen3-8b-attrib-filter-from-qwen3-14b

Updated 16 days ago

published a model 16 days ago

MrGonao/em-lora-qwen3-8b-attrib-filter-from-qwen3-14b

Updated 16 days ago

updated a collection 16 days ago

Emergent Misalignment: Attribution-Filtered LoRA Adapters

Collection

28.8k LoRAs (Olmo-3-7B, Qwen3-8B, Qwen2.5-7B) fine-tuned on incorrect-advice data filtered by attribution scores from many scorer models. • 53 items • Updated 16 days ago