Youlln/ECE-PRYMMAL-0.5B-FT-V3

Full fine-tune vs Youlln/ECE.EIFFEIL.ia-0.5B-SLERP. Fine-tune: 100% of the weights changed, across 24 of 24 layers.

Tensors changed: Embeddings 1/1, Norms 35/49, MLP 72/72, Attention 168/168

2 derivatives checked

• mradermacher/ECE-PRYMMAL-0.5B-FT-V3-i1-GGUF: Quantization
• mradermacher/ECE-PRYMMAL-0.5B-FT-V3-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse