Indexnusrefather/Palette-RP-9B-2609-v0.05

LoRA-style vs Qwen/Qwen3.5-9B. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of down_proj, gate_proj, k_proj, o_proj, q_proj, up_proj, v_proj changed, in 31 of 32 layers; norms, biases and embeddings are untouched.

Tensors changed: lm_head 0/1, Embeddings 0/5, MLP 96/211, Attention 32/336, other 0/1, Norms 0/221

2 derivatives checked

On the Hub · Downloads on Model Pulse