lurf21/Qwen2.5-Coder-7B-NEP
LoRA-style vs Qwen/Qwen2.5-Coder-7B. 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 28 of 28 layers; norms, biases and embeddings are untouched.
Tensors changed: Norms 0/57, MLP 84/84, Attention 112/196
1 derivatives checked
- mradermacher/Qwen2.5-Coder-7B-NEP-fix-GGUF: Full fine-tune