Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
Heretic-InfiR-1B-Instruct – AI Model by hereticness | AlphaNeural AI
You can deploy this model and start earning money today!
hereticness
/
Heretic-InfiR-1B-Instruct
like
0
safetensors
llama
heretic
text-generation
conversational
InfiX-ai/InfiR-1B-Instruct
finetune
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
Heretic? Heretic!
Disobedience rate: 18%, original: 89%
KL divergence: 0.1469
Quants
Parameters:
direction_index = per layer
attn.o_proj.max_weight = 1.05
attn.o_proj.max_weight_position = 12.26
attn.o_proj.min_weight = 0.92
attn.o_proj.min_weight_distance = 4.83
mlp.down_proj.max_weight = 1.46
mlp.down_proj.max_weight_position = 9.14
mlp.down_proj.min_weight = 0.88
mlp.down_proj.min_weight_distance = 5.98
