Youlln/ECE.EIFFEIL.ia-0.5B-SLERP

Full fine-tune vs Qwen/Qwen2.5-0.5B-Instruct. Fine-tune: 100% of the weights changed, across 24 of 24 layers.

Tensors changed: Embeddings 1/1, Norms 39/49, MLP 72/72, Attention 168/168

3 derivatives checked

• mradermacher/ECE.EIFFEIL.ia-0.5B-SLERP-i1-GGUF: Quantization
• mradermacher/ECE.EIFFEIL.ia-0.5B-SLERP-GGUF: Same weights, converted
• Youlln/ECE-PRYMMAL-0.5B-FT-V3: Full fine-tune

On the Hub · Downloads on Model Pulse