Youlln/ECE-PRYMMAL-0.5B-FT-V4-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 34/49, MLP 72/72, Attention 168/168
1 derivatives checked
- mradermacher/ECE-PRYMMAL-0.5B-FT-V4-MUSR-GGUF: Quantization