MaziyarPanahi/Qwen1.5-MoE-A2.7B-Wikihow
LoRA-style vs Qwen/Qwen1.5-MoE-A2.7B. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of down_proj, gate, gate_proj, k_proj, o_proj, q_proj, shared_expert_gate, up_proj, v_proj changed, in 24 of 24 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/49, MLP 2781/2781, Attention 96/168, lm_head 0/1
3 derivatives checked
- mradermacher/Qwen1.5-MoE-A2.7B-Wikihow-i1-GGUF: Quantization
- mradermacher/Qwen1.5-MoE-A2.7B-Wikihow-GGUF: Quantization
- MaziyarPanahi/Qwen1.5-MoE-A2.7B-Wikihow-GGUF: Same weights, converted