r0b0tlab/MiMo-V2.6-Flash-RL-NVFP4
LoRA-style vs XiaomiMiMo/MiMo-V2.6-Flash-RL. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of down_proj, gate_proj, up_proj changed, in 47 of 48 layers; norms, biases and embeddings are untouched.
Tensors changed: MLP 507/815, Attention 0/373, other 0/3, Norms 0/182, lm_head 0/1, Embeddings 0/22