| { |
| "_attn_implementation": "magi", |
| "_commit_hash": null, |
| "architectures": [ |
| "LocateAnythingForConditionalGeneration" |
| ], |
| "box_end_token_id": 151669, |
| "box_start_token_id": 151668, |
| "coord_end_token_id": 152677, |
| "coord_start_token_id": 151677, |
| "eos_token_id": 151645, |
| "image_token_index": 151665, |
| "mlp_checkpoint": false, |
| "mlp_connector_layers": 2, |
| "model_type": "locateanything", |
| "none_token_id": 4064, |
| "quantization": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine", |
| "language_model.model.embed_tokens": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "language_model.model.layers.0.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.0.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.0.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "language_model.model.layers.0.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.0.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.0.mlp.down_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "language_model.model.layers.0.mlp.up_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.1.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.1.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.1.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "language_model.model.layers.1.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.1.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.1.mlp.down_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "language_model.model.layers.1.mlp.up_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.2.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.2.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.2.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "language_model.model.layers.2.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.2.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.2.mlp.down_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "language_model.model.layers.2.mlp.up_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.3.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.3.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.3.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "language_model.model.layers.3.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.3.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.3.mlp.down_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "language_model.model.layers.3.mlp.up_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.4.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.4.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.4.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.4.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.4.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.4.mlp.down_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.4.mlp.up_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.5.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.5.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.5.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.5.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.5.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.5.mlp.down_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.5.mlp.up_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.6.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.6.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.6.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "language_model.model.layers.6.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.6.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.6.mlp.down_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "language_model.model.layers.6.mlp.up_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.7.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.7.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.7.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.7.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.7.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.7.mlp.down_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.7.mlp.up_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.8.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.8.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.8.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.8.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.8.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.8.mlp.down_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.8.mlp.up_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.9.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.9.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.9.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "language_model.model.layers.9.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.9.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.9.mlp.down_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "language_model.model.layers.9.mlp.up_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.10.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.10.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.10.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.10.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.10.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.10.mlp.down_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.10.mlp.up_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.11.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.11.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.11.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.11.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.11.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.11.mlp.down_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.11.mlp.up_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.12.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.12.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.12.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "language_model.model.layers.12.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.12.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.12.mlp.down_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "language_model.model.layers.12.mlp.up_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.13.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.13.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.13.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.13.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.13.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.13.mlp.down_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.13.mlp.up_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.14.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.14.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.14.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.14.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.14.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.14.mlp.down_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.14.mlp.up_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.15.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.15.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.15.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "language_model.model.layers.15.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.15.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.15.mlp.down_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "language_model.model.layers.15.mlp.up_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.16.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.16.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.16.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.16.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.16.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.16.mlp.down_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.16.mlp.up_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.17.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.17.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.17.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.17.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.17.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.17.mlp.down_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.17.mlp.up_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.18.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.18.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.18.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "language_model.model.layers.18.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.18.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.18.mlp.down_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "language_model.model.layers.18.mlp.up_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.19.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.19.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.19.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.19.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.19.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.19.mlp.down_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.19.mlp.up_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.20.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.20.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.20.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.20.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.20.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.20.mlp.down_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.20.mlp.up_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.21.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.21.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.21.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "language_model.model.layers.21.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.21.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.21.mlp.down_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "language_model.model.layers.21.mlp.up_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.22.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.22.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.22.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.22.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.22.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.22.mlp.down_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.22.mlp.up_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.23.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.23.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.23.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.23.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.23.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.23.mlp.down_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.23.mlp.up_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.24.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.24.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.24.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "language_model.model.layers.24.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.24.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.24.mlp.down_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "language_model.model.layers.24.mlp.up_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.25.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.25.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.25.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.25.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.25.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.25.mlp.down_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.25.mlp.up_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.26.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.26.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.26.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.26.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.26.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.26.mlp.down_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.26.mlp.up_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.27.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.27.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.27.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "language_model.model.layers.27.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.27.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.27.mlp.down_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "language_model.model.layers.27.mlp.up_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.28.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.28.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.28.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.28.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.28.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.28.mlp.down_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.28.mlp.up_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.29.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.29.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.29.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.29.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.29.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.29.mlp.down_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.29.mlp.up_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.30.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.30.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.30.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "language_model.model.layers.30.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.30.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.30.mlp.down_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "language_model.model.layers.30.mlp.up_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.31.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.31.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.31.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "language_model.model.layers.31.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.31.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.31.mlp.down_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "language_model.model.layers.31.mlp.up_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.32.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.32.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.32.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "language_model.model.layers.32.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.32.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.32.mlp.down_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "language_model.model.layers.32.mlp.up_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.33.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.33.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.33.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "language_model.model.layers.33.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.33.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.33.mlp.down_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "language_model.model.layers.33.mlp.up_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.34.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.34.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.34.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "language_model.model.layers.34.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.34.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.34.mlp.down_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "language_model.model.layers.34.mlp.up_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.35.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.35.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.35.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "language_model.model.layers.35.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.35.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.35.mlp.down_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "language_model.model.layers.35.mlp.up_proj": { |
| "group_size": 64, |
| "bits": 4 |
| } |
| }, |
| "quantization_config": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine", |
| "language_model.model.embed_tokens": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "language_model.model.layers.0.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.0.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.0.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "language_model.model.layers.0.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.0.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.0.mlp.down_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "language_model.model.layers.0.mlp.up_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.1.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.1.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.1.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "language_model.model.layers.1.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.1.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.1.mlp.down_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "language_model.model.layers.1.mlp.up_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.2.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.2.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.2.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "language_model.model.layers.2.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.2.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.2.mlp.down_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "language_model.model.layers.2.mlp.up_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.3.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.3.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.3.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "language_model.model.layers.3.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.3.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.3.mlp.down_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "language_model.model.layers.3.mlp.up_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.4.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.4.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.4.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.4.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.4.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.4.mlp.down_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.4.mlp.up_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.5.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.5.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.5.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.5.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.5.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.5.mlp.down_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.5.mlp.up_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.6.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.6.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.6.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "language_model.model.layers.6.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.6.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.6.mlp.down_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "language_model.model.layers.6.mlp.up_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.7.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.7.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.7.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.7.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.7.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.7.mlp.down_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.7.mlp.up_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.8.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.8.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.8.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.8.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.8.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.8.mlp.down_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.8.mlp.up_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.9.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.9.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.9.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "language_model.model.layers.9.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.9.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.9.mlp.down_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "language_model.model.layers.9.mlp.up_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.10.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.10.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.10.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.10.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.10.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.10.mlp.down_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.10.mlp.up_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.11.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.11.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.11.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.11.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.11.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.11.mlp.down_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.11.mlp.up_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.12.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.12.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.12.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "language_model.model.layers.12.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.12.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.12.mlp.down_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "language_model.model.layers.12.mlp.up_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.13.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.13.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.13.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.13.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.13.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.13.mlp.down_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.13.mlp.up_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.14.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.14.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.14.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.14.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.14.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.14.mlp.down_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.14.mlp.up_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.15.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.15.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.15.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "language_model.model.layers.15.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.15.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.15.mlp.down_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "language_model.model.layers.15.mlp.up_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.16.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.16.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.16.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.16.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.16.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.16.mlp.down_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.16.mlp.up_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.17.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.17.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.17.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.17.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.17.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.17.mlp.down_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.17.mlp.up_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.18.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.18.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.18.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "language_model.model.layers.18.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.18.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.18.mlp.down_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "language_model.model.layers.18.mlp.up_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.19.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.19.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.19.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.19.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.19.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.19.mlp.down_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.19.mlp.up_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.20.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.20.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.20.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.20.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.20.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.20.mlp.down_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.20.mlp.up_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.21.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.21.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.21.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "language_model.model.layers.21.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.21.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.21.mlp.down_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "language_model.model.layers.21.mlp.up_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.22.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.22.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.22.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.22.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.22.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.22.mlp.down_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.22.mlp.up_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.23.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.23.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.23.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.23.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.23.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.23.mlp.down_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.23.mlp.up_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.24.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.24.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.24.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "language_model.model.layers.24.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.24.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.24.mlp.down_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "language_model.model.layers.24.mlp.up_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.25.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.25.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.25.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.25.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.25.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.25.mlp.down_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.25.mlp.up_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.26.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.26.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.26.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.26.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.26.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.26.mlp.down_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.26.mlp.up_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.27.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.27.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.27.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "language_model.model.layers.27.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.27.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.27.mlp.down_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "language_model.model.layers.27.mlp.up_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.28.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.28.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.28.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.28.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.28.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.28.mlp.down_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.28.mlp.up_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.29.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.29.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.29.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.29.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.29.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.29.mlp.down_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.29.mlp.up_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.30.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.30.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.30.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "language_model.model.layers.30.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.30.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.30.mlp.down_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "language_model.model.layers.30.mlp.up_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.31.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.31.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.31.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "language_model.model.layers.31.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.31.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.31.mlp.down_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "language_model.model.layers.31.mlp.up_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.32.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.32.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.32.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "language_model.model.layers.32.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.32.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.32.mlp.down_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "language_model.model.layers.32.mlp.up_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.33.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.33.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.33.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "language_model.model.layers.33.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.33.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.33.mlp.down_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "language_model.model.layers.33.mlp.up_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.34.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.34.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.34.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "language_model.model.layers.34.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.34.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.34.mlp.down_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "language_model.model.layers.34.mlp.up_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.35.self_attn.q_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.35.self_attn.k_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.35.self_attn.v_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "language_model.model.layers.35.self_attn.o_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.35.mlp.gate_proj": { |
| "group_size": 64, |
| "bits": 4 |
| }, |
| "language_model.model.layers.35.mlp.down_proj": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "language_model.model.layers.35.mlp.up_proj": { |
| "group_size": 64, |
| "bits": 4 |
| } |
| }, |
| "ref_end_token_id": 151673, |
| "ref_start_token_id": 151672, |
| "template": null, |
| "text_config": { |
| "_attn_implementation_autoset": true, |
| "_name_or_path": "Qwen/Qwen2.5-3B-Instruct", |
| "architectures": [ |
| "Qwen2ForCausalLM" |
| ], |
| "attention_dropout": 0.0, |
| "block_size": 6, |
| "bos_token_id": 151643, |
| "causal_attn": false, |
| "eos_token_id": 151645, |
| "hidden_act": "silu", |
| "hidden_size": 2048, |
| "initializer_range": 0.02, |
| "intermediate_size": 11008, |
| "max_position_embeddings": 32768, |
| "max_window_layers": 70, |
| "model_type": "qwen2", |
| "null_token_id": 152678, |
| "num_attention_heads": 16, |
| "num_hidden_layers": 36, |
| "num_key_value_heads": 2, |
| "rms_norm_eps": 1e-06, |
| "rope_scaling": null, |
| "rope_theta": 1000000.0, |
| "sliding_window": 32768, |
| "switch_token_id": 152679, |
| "text_mask_token_id": 151676, |
| "tie_word_embeddings": true, |
| "torch_dtype": "bfloat16", |
| "use_cache": false, |
| "use_sliding_window": false, |
| "vocab_size": 152681 |
| }, |
| "transformers_version": null, |
| "use_backbone_lora": 0, |
| "use_llm_lora": 0, |
| "vision_config": { |
| "_attn_implementation_autoset": true, |
| "_name_or_path": "moonshotai/MoonViT-SO-400M", |
| "auto_map": { |
| "AutoConfig": "moonshotai/MoonViT-SO-400M--configuration_moonvit.MoonViTConfig", |
| "AutoModel": "moonshotai/MoonViT-SO-400M--modeling_moonvit.MoonVitPretrainedModel" |
| }, |
| "hidden_size": 1152, |
| "init_pos_emb_height": 64, |
| "init_pos_emb_width": 64, |
| "intermediate_size": 4304, |
| "merge_kernel_size": [ |
| 2, |
| 2 |
| ], |
| "model_type": "moonvit", |
| "num_attention_heads": 16, |
| "num_hidden_layers": 27, |
| "patch_size": 14, |
| "torch_dtype": "bfloat16" |
| } |
| } |
