Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
Heretic-Llama-3.2-3B-F1-Instruct – AI Model by hereticness | AlphaNeural AI
You can deploy this model and start earning money today!
hereticness
/
Heretic-Llama-3.2-3B-F1-Instruct
like
0
safetensors
llama
heretic
text-generation
conversational
twinkle-ai/Llama-3.2-3B-F1-Instruct
finetune
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
Heretic? Heretic!
Disobedience rate: 8%, original: 84%
KL divergence: 0.0438
Quants
Parameters:
direction_index = per layer
attn.o_proj.max_weight = 1.34
attn.o_proj.max_weight_position = 19.55
attn.o_proj.min_weight = 0.85
attn.o_proj.min_weight_distance = 13.43
mlp.down_proj.max_weight = 1.12
mlp.down_proj.max_weight_position = 16.48
mlp.down_proj.min_weight = 0.72
mlp.down_proj.min_weight_distance = 11.77
