Fulcrum-AI/Ryze-Nemo-passthrough
Partial fine-tune vs mistralai/Mistral-Nemo-Instruct-2407. Partial change: 36% of the weights changed (attention, mlp, norms), in 16 of 40 layers.
Tensors changed: Embeddings 0/1, Norms 32/81, MLP 48/120, Attention 64/160, lm_head 0/1
2 derivatives checked
- mradermacher/Ryze-Nemo-passthrough-i1-GGUF: Quantization
- mradermacher/Ryze-Nemo-passthrough-GGUF: Quantization