AI45Research/SafeWork-RM-Knowledge-72B
LoRA-style vs Qwen/Qwen2.5-VL-72B-Instruct. 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 80 of 80 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/2, Norms 0/226, Attention 320/688, MLP 240/436, lm_head 0/1
2 derivatives checked
- mradermacher/SafeWork-RM-Knowledge-72B-i1-GGUF: Quantization
- mradermacher/SafeWork-RM-Knowledge-72B-GGUF: Quantization