Beta
Explore
Marketplace
Neural Labs
Playground
Wallet
Docs
Heretic-Llama-3.2-3B-F1-Reasoning-Instruct – AI Model by hereticness | AlphaNeural AI
You can deploy this model and start earning money today!
hereticness
/
Heretic-Llama-3.2-3B-F1-Reasoning-Instruct
like
0
safetensors
llama
heretic
text-generation
conversational
twinkle-ai/Llama-3.2-3B-F1-Reasoning-Instruct
finetune
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
Heretic? Heretic!
Disobedience rate: 11%, original: 74%
KL divergence: 0.0126
Quants
Parameters:
direction_index = per layer
attn.o_proj.max_weight = 1.40
attn.o_proj.max_weight_position = 16.90
attn.o_proj.min_weight = 0.23
attn.o_proj.min_weight_distance = 7.93
mlp.down_proj.max_weight = 1.21
mlp.down_proj.max_weight_position = 23.86
mlp.down_proj.min_weight = 0.11
mlp.down_proj.min_weight_distance = 5.50
