rawmodels/Qwen3.8-27B-antislop-semdiv-grpo
LoRA-style vs Qwen/Qwen3.8-27B. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of down_proj, gate_proj, in_proj_qkv, in_proj_z, k_proj, o_proj, out_proj, q_proj, up_proj, v_proj changed, in 64 of 64 layers; norms, biases and embeddings are untouched.
Tensors changed: Norms 0/319, Attention 208/556, MLP 192/304, Embeddings 0/4, lm_head 0/1
2 derivatives checked
- rawmodels/Qwen3.8-27B-antislop-semdiv-grpo-GGUF: Quantization
- rawmodels/Qwen3.8-27B-antislop-semdiv-grpo-NVFP4: Quantization