oktayd/Qwen3.6-35B-v2-MoE-Ablit-Heretic-Uncensor-Hermes-MTP-Vision-FT
LoRA-style vs oktayd/Q36-35B-A3B-Opus4.7-Ablit-Heretic-OBLITERATUS-Hermes-MTP-Vision-FT. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of down_proj, gate_proj, in_proj_a, in_proj_b, in_proj_qkv, in_proj_z, k_proj, o_proj, out_proj, q_proj, up_proj, v_proj changed, in 40 of 40 layers; norms, biases and embeddings are untouched.
Tensors changed: lm_head 0/1, Embeddings 0/5, Norms 0/247, Attention 190/392, MLP 120/399, other 0/1
4 derivatives checked
- mradermacher/Qwen3.6-35B-v2-MoE-Ablit-Heretic-Uncensor-Hermes-MTP-Vision-FT-GGUF: Quantization
- oktayd/Qwen3.6-35B-v2-MoE-Ablit-Heretic-Uncensor-Hermes-MTP-Vision-Llama: Quantization
- mradermacher/Qwen3.6-35B-v2-MoE-Ablit-Heretic-Uncensor-Hermes-MTP-Vision-FT-i1-GGUF: Quantization
- oktayd/Qwen3.6-35B-v2-MoE-Ablit-Heretic-Uncensor-Hermes-MTP-Vision-Ollama: Quantization