Dans-Archive/Dans-AdventurousWinds-Mk2-7b
Full fine-tune vs mistralai/Mistral-7B-v0.1. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/1, Norms 0/65, MLP 96/96, Attention 128/128, lm_head 1/1
4 derivatives checked
- TheBloke/Dans-AdventurousWinds-Mk2-7B-GGUF: Quantization
- mradermacher/Dans-AdventurousWinds-Mk2-7b-i1-GGUF: Quantization
- mradermacher/Dans-AdventurousWinds-Mk2-7b-GGUF: Same weights, converted
- Smuggling1710/Ak4ri-rp-7b: Full fine-tune