Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
Heretic-Instella-3B-Long-Instruct – AI Model by hereticness | AlphaNeural AI
You can deploy this model and start earning money today!
hereticness
/
Heretic-Instella-3B-Long-Instruct
like
0
safetensors
instella
heretic
text-generation
conversational
custom_code
amd/Instella-3B-Long-Instruct
finetune
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
Heretic? Heretic!
Disobedience rate: 14%, original: 71%
KL divergence: 0.1937
Quants? (still not supported by llama.cpp atm)
Parameters:
direction_index = per layer
attn.o_proj.max_weight = 1.18
attn.o_proj.max_weight_position = 26.64
attn.o_proj.min_weight = 0.77
attn.o_proj.min_weight_distance = 9.40
mlp.down_proj.max_weight = 0.87
mlp.down_proj.max_weight_position = 28.92
mlp.down_proj.min_weight = 0.22
mlp.down_proj.min_weight_distance = 18.60