Heralax/army-pretrain-1
Full fine-tune vs mistral-community/Mistral-7B-v0.2. Heralax/army-pretrain-1 is a GGUF (F16) of different weights. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Norms 20/65, MLP 96/96, Attention 128/128
2 derivatives checked
- Heralax/Mistrilitary-7b: Full fine-tune
- QuantFactory/Mistrilitary-7b-GGUF: Full fine-tune