OpenYourMind/Qwopus3.5-122B-A10B-Kimi-K2.6-destill-healed-abliterated
LoRA-style (fewer layers) vs Qwen/Qwen3.5-122B-A10B. Qwen/Qwen3.5-122B-A10B matches part of OpenYourMind/Qwopus3.5-122B-A10B-Kimi-K2.6-destill-healed-abliterated (1853 of its 38717 tensors; the rest of OpenYourMind/Qwopus3.5-122B-A10B-Kimi-K2.6-destill-healed-abliterated has no counterpart). On the shared part: Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of down_proj, gate, 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 48 of 48 layers; norms, biases and embeddings are untouched.
Tensors changed: lm_head 0/1, Embeddings 0/5, Attention 226/448, MLP 145/400, other 0/1, Norms 0/273
9 derivatives checked
- OpenYourMind/Qwopus3.5-122B-A10B-Kimi-K2.6-destill-healed-abliterated-GGUF: Quantization
- mradermacher/Qwopus3.5-122B-A10B-Kimi-K2.6-destill-healed-abliterated-i1-GGUF: Quantization
- mradermacher/Qwopus3.5-122B-A10B-Kimi-K2.6-destill-healed-abliterated-GGUF: Quantization
- morikomorizz/Qwopus3.5-122B-Distill-Kimi-Uncensored-GGUF: Quantization
- OpenYourMind/Qwopus3.5-122B-A10B-Kimi-K2.6-destill-healed-abliterated-MTPLX-4bit: Quantization
- rcmorano/OpenYourMind-Qwopus3.5-122B-A10B-Kimi-K2.6-destill-healed-abliterated-ROCMPFX: Same weights, converted
- OpenYourMind/Qwopus3.5-122B-A10B-Kimi-K2.6-destilled-abliterated-NVFP4: Quantization
- OpenYourMind/Qwopus3.5-122B-A10B-Kimi-K2.6-destill-healed-abliterated-MLX-4bit: Quantization
- Jonyses/Qwopus3.5-122B-A10B-Kimi-K2.6-destill-healed-abliterated-GGUF: Quantization