Youlln/ECE-PRYMMAL-0.5B-FT-V3-MUSR
Full fine-tune vs Qwen/Qwen2-0.5B. Fine-tune: 100% of the weights changed, across 24 of 24 layers.
Tensors changed: Embeddings 1/1, Norms 20/49, MLP 72/72, Attention 167/168
2 derivatives checked
- mradermacher/ECE-PRYMMAL-0.5B-FT-V3-MUSR-GGUF: Same weights, converted
- Youlln/ECE-PRYMMAL-0.5B-SLERP-V2: Full fine-tune