beratcmn/cem-v0.1
Adapter vs google/gemma-7b. beratcmn/cem-v0.1 is a LoRA adapter, not full weights: rank 8, on down_proj, gate_proj, k_proj, o_proj, q_proj, up_proj, v_proj in 28 layers (196 adapted matrices). It modifies google/gemma-7b at load time.
2 derivatives checked
- mradermacher/cem-v0.1-i1-GGUF: Adapter
- mradermacher/cem-v0.1-GGUF: Adapter