GaMS-Beta/GaMS-9B-SFT-Translator-DPO
LoRA-style vs GaMS-Beta/GaMS-9B-SFT-Translator. 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 42 of 42 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/169, MLP 126/126, Attention 168/168
1 derivatives checked
- mradermacher/GaMS-9B-SFT-Translator-DPO-GGUF: Same weights, converted