AXCXEPT/EZO-Qwen2.5-72B-Instruct
LoRA-style vs Qwen/Qwen2.5-72B-Instruct. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of down_proj, gate_proj, k_proj, o_proj, q_proj, up_proj, v_proj changed, in 80 of 80 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/161, MLP 240/240, Attention 320/560, lm_head 0/1
5 derivatives checked
- mradermacher/EZO-Qwen2.5-72B-Instruct-i1-GGUF: Quantization
- featherless-ai-quants/AXCXEPT-EZO-Qwen2.5-72B-Instruct-GGUF: Quantization
- KaraKaraWarehouse/spiral-da-HYAH-Qwen2.5-72b: Full fine-tune
- spow12/ChatWaifu_72B_v2.2: Full fine-tune
- nitky/AtheneX-V2-72B-instruct: Full fine-tune