arcee-ai/Meraj-Mini

Full fine-tune vs Qwen/Qwen2.5-7B-Instruct. Fine-tune: 100% of the weights changed, across 28 of 28 layers.

Tensors changed: Embeddings 1/1, Norms 54/57, MLP 84/84, Attention 196/196, lm_head 1/1

4 derivatives checked

• mradermacher/Meraj-Mini-i1-GGUF: Quantization
• MaziyarPanahi/Meraj-Mini-GGUF: Same weights, converted
• mradermacher/Meraj-Mini-GGUF: Same weights, converted
• MawaredHR/Mawared_T1: LoRA-style

On the Hub · Downloads on Model Pulse