Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
Heretic-OneLLM-Doey-ChatQA-V1-Llama-3.2-1B – AI Model by hereticness | AlphaNeural AI
You can deploy this model and start earning money today!
hereticness
/
Heretic-OneLLM-Doey-ChatQA-V1-Llama-3.2-1B
like
0
safetensors
llama
heretic
text-generation
conversational
DoeyLLM/OneLLM-Doey-ChatQA-V1-Llama-3.2-1B
finetune
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
▀█▀ █▄ ▄█ █ █ █▀▀ █▀▄ █▀▀ ▀█▀ ▀█▀ █▀▀ █ █ ▀ █ █▀█ █▀▀ █▀▄ █▀▀ █ █ █ ▀▀▀ ▀ ▀ ▀ ▀ ▀▀▀ ▀ ▀ ▀▀▀ ▀ ▀▀▀ ▀▀▀
Abliterated/Heretic
DoeyLLM/OneLLM-Doey-ChatQA-V1-Llama-3.2-1B
Check Quants
Refusals (this model): 15/100
Original (DoeyLLM/OneLLM-Doey-ChatQA-V1-Llama-3.2-1B): 89/100
KL divergence: 0.1615
Parameters
direction_index = per layer
attn.o_proj.max_weight = 0.99
attn.o_proj.max_weight_position = 9.73
attn.o_proj.min_weight = 0.88
attn.o_proj.min_weight_distance = 7.65
mlp.down_proj.max_weight = 1.46
mlp.down_proj.max_weight_position = 9.06
mlp.down_proj.min_weight = 1.05
mlp.down_proj.min_weight_distance = 4.27
