Iker/TowerInstruct-7B-v0.2-EN2ES
Full fine-tune vs Unbabel/TowerInstruct-7B-v0.2. 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
3 derivatives checked
- MaziyarPanahi/TowerInstruct-7B-v0.2-EN2ES-GGUF: Quantization
- mradermacher/TowerInstruct-7B-v0.2-EN2ES-i1-GGUF: Quantization
- mradermacher/TowerInstruct-7B-v0.2-EN2ES-GGUF: Same weights, converted