allura-org/GLM4-9B-Neon-v2
LoRA-style vs zai-org/GLM-4-9B-0414. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of down_proj, gate_up_proj, k_proj, o_proj, q_proj, v_proj changed, in 40 of 40 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/161, MLP 80/80, Attention 160/280, lm_head 0/1
6 derivatives checked
- bartowski/allura-org_GLM4-9B-Neon-v2-GGUF: Same weights, converted
- mradermacher/GLM4-9B-Neon-v2-i1-GGUF: Quantization
- mradermacher/GLM4-9B-Neon-v2-GGUF: Same weights, converted
- DevQuasar/allura-org.GLM4-9B-Neon-v2-GGUF: Same weights, converted
- tensorblock/allura-org_GLM4-9B-Neon-v2-GGUF: Quantization
- AIgotahole/Glm4-9B-RP-brb: Different architecture