inflatebot/helide-alpha-r5
Full fine-tune vs Fizzarolli/L3-8b-Rosier-v1. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/1, Norms 65/65, MLP 96/96, Attention 128/128, lm_head 1/1
2 derivatives checked
- mradermacher/helide-alpha-r5-i1-GGUF: Quantization
- mradermacher/helide-alpha-r5-GGUF: Same weights, converted
1 other repos hold byte-for-byte identical weight files.