ATH-MaaS/Marco-LLM-AR-V4
Full fine-tune vs Qwen/Qwen2.5-7B. Fine-tune: 100% of the weights changed, across 28 of 28 layers.
Tensors changed: Embeddings 1/1, Norms 57/57, MLP 84/84, Attention 196/196, lm_head 1/1
2 derivatives checked
- mradermacher/Marco-LLM-AR-V3-i1-GGUF: Quantization
- mradermacher/Marco-LLM-AR-V3-GGUF: Same weights, converted