soob3123/GrayLine-Qwen3-8B
LoRA-style vs Qwen/Qwen3-8B. 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 36 of 36 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/145, MLP 108/108, Attention 144/144, lm_head 0/1
4 derivatives checked
- bartowski/soob3123_GrayLine-Qwen3-8B-GGUF: Same weights, converted
- mradermacher/GrayLine-Qwen3-8B-i1-GGUF: Quantization
- mradermacher/GrayLine-Qwen3-8B-GGUF: Same weights, converted
- tensorblock/soob3123_GrayLine-Qwen3-8B-GGUF: Quantization
2 other repos hold byte-for-byte identical weight files.