hhj-ai/Evidence-RL-9B
LoRA-style vs Qwen/Qwen3.5-9B. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of q_proj, v_proj changed, in 8 of 32 layers; norms, biases and embeddings are untouched.
Tensors changed: lm_head 0/1, Embeddings 0/4, MLP 0/208, Attention 16/332, Norms 0/215
2 derivatives checked
- mradermacher/Evidence-RL-9B-i1-GGUF: Quantization
- mradermacher/Evidence-RL-9B-GGUF: Same weights, converted