| { |
| "alpha_pattern": {}, |
| "auto_mapping": null, |
| "base_model_name_or_path": "google/gemma-4-31B-it", |
| "bias": "none", |
| "corda_config": null, |
| "eva_config": null, |
| "exclude_modules": [ |
| "model.vision_tower.encoder.layers.23.self_attn.v_norm", |
| "model.vision_tower.encoder.layers.7", |
| "model.vision_tower.encoder.layers.26.mlp.act_fn", |
| "model.vision_tower.encoder.layers.14.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.9.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.15.mlp.up_proj", |
| "model.vision_tower.encoder.layers.0.self_attn.v_norm", |
| "model.vision_tower.encoder.layers.14.mlp.gate_proj", |
| "model.vision_tower.encoder.layers.3.self_attn.q_proj", |
| "model.vision_tower.encoder.layers.7.self_attn.o_proj", |
| "model.vision_tower.encoder.layers.9.mlp.up_proj", |
| "model.vision_tower.encoder.layers.15.self_attn.k_norm", |
| "model.vision_tower.encoder.layers.11", |
| "model.vision_tower.encoder.layers.18.post_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.11.input_layernorm", |
| "model.vision_tower.encoder.layers.11.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.6.post_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.19.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.16.self_attn.o_proj", |
| "model.vision_tower.encoder.layers.19.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.26.self_attn.v_norm", |
| "model.vision_tower.encoder.layers.14.mlp.down_proj.linear", |
| "model.vision_tower.encoder.layers.0.pre_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.10.self_attn.v_proj", |
| "model.vision_tower.encoder.layers.9.self_attn.k_proj", |
| "model.vision_tower.encoder.layers.1.self_attn.o_proj", |
| "model.vision_tower.encoder.layers.5.mlp.down_proj", |
| "model.vision_tower.encoder.layers.0.post_attention_layernorm", |
| "model.vision_tower.encoder.layers.24.self_attn.k_proj", |
| "model.vision_tower.encoder.layers.14.mlp.up_proj", |
| "model.vision_tower.encoder.layers.14.mlp", |
| "model.vision_tower.encoder.layers.15", |
| "model.vision_tower.encoder.layers.20.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.23.mlp.down_proj", |
| "model.vision_tower.encoder.layers.8.input_layernorm", |
| "model.vision_tower.encoder.layers.0.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.24.self_attn.o_proj", |
| "model.vision_tower.encoder.layers.20.mlp.up_proj", |
| "model.vision_tower.encoder.layers.5.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.8.post_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.15.post_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.24.self_attn", |
| "model.vision_tower.encoder.layers.12.mlp.act_fn", |
| "model.vision_tower.encoder.layers.5.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.2.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.20.self_attn.o_proj", |
| "model.vision_tower.encoder.layers.12.post_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.3.mlp.down_proj.linear", |
| "model.vision_tower.encoder.layers.12.self_attn.v_proj", |
| "model.vision_tower.encoder.layers.23.self_attn.k_proj", |
| "model.vision_tower.encoder.layers.13.mlp.gate_proj", |
| "model.vision_tower.encoder.layers.14.pre_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.19.mlp.up_proj", |
| "model.vision_tower.encoder.layers.18.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.2.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.3.mlp.up_proj", |
| "model.vision_tower.encoder.layers.4.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.18.mlp.act_fn", |
| "model.vision_tower.encoder.layers.1.pre_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.20.mlp", |
| "model.vision_tower.encoder.layers.10.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.15.mlp.down_proj.linear", |
| "model.vision_tower.encoder.layers.14.self_attn.q_norm", |
| "model.vision_tower.encoder.layers.10.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.21.pre_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.22.self_attn.v_proj", |
| "model.vision_tower.encoder.layers.21.mlp", |
| "model.vision_tower.encoder.layers.23.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.15.mlp.gate_proj", |
| "model.vision_tower.encoder.layers.1", |
| "model.vision_tower.encoder.layers.3", |
| "model.vision_tower.encoder.layers.6.mlp.gate_proj", |
| "model.vision_tower.encoder.layers.21.mlp.down_proj", |
| "model.vision_tower.encoder.layers.5.mlp.down_proj.linear", |
| "model.vision_tower.encoder.layers.17.pre_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.1.self_attn", |
| "model.vision_tower.encoder.layers.21.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.0.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.13.mlp.down_proj", |
| "model.vision_tower.encoder.layers.1.self_attn.q_norm", |
| "model.vision_tower.encoder.layers.6.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.22.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.25.pre_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.4.mlp.down_proj.linear", |
| "model.vision_tower.encoder.layers.26.mlp.up_proj", |
| "model.vision_tower.encoder.layers.10.mlp.down_proj", |
| "model.vision_tower.encoder.layers.7.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.21.input_layernorm", |
| "model.vision_tower.encoder.layers.15.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.2.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.22.self_attn.k_norm", |
| "model.vision_tower.encoder.layers.19.self_attn.k_norm", |
| "model.vision_tower.encoder.layers.2.mlp.gate_proj", |
| "model.vision_tower.encoder.layers.6.self_attn.q_norm", |
| "model.vision_tower.encoder.layers.7.self_attn.q_norm", |
| "model.vision_tower.encoder.layers.7.mlp.act_fn", |
| "model.vision_tower.encoder.layers.4.self_attn.q_proj", |
| "model.vision_tower.encoder.layers.0.mlp.down_proj", |
| "model.vision_tower.encoder.layers.22.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.2.self_attn.v_norm", |
| "model.vision_tower.encoder.layers.4.mlp.down_proj", |
| "model.vision_tower.encoder.layers.11.self_attn.q_proj", |
| "model.vision_tower.encoder.layers.17.mlp", |
| "model.vision_tower.encoder.layers.22.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.6.self_attn.k_proj", |
| "model.vision_tower.encoder.layers.8.self_attn", |
| "model.vision_tower.encoder.layers.6.mlp.up_proj", |
| "model.vision_tower.encoder.layers.16.mlp.gate_proj", |
| "model.vision_tower.encoder.layers.15.mlp.act_fn", |
| "model.vision_tower.encoder.layers.7.mlp.down_proj.linear", |
| "model.vision_tower.pooler", |
| "model.vision_tower.encoder.layers.0.self_attn.k_proj", |
| "model.vision_tower.encoder.layers.1.input_layernorm", |
| "model.vision_tower.encoder.layers.25.mlp.act_fn", |
| "model.vision_tower.encoder.layers.24.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.25.mlp", |
| "model.vision_tower.encoder.layers.14.self_attn.v_proj", |
| "model.vision_tower.encoder.layers.23.self_attn", |
| "model.vision_tower.encoder.layers.17.input_layernorm", |
| "model.vision_tower.encoder.layers.23.mlp.act_fn", |
| "model.vision_tower.encoder.layers.21.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.15.self_attn.o_proj", |
| "model.vision_tower.encoder.layers.22.mlp.act_fn", |
| "model.vision_tower.encoder.layers.3.mlp.gate_proj", |
| "model.vision_tower.encoder.layers.11.mlp", |
| "model.vision_tower.encoder.layers.13.self_attn.o_proj", |
| "model.vision_tower.encoder.layers.21.mlp.down_proj.linear", |
| "model.vision_tower.encoder", |
| "model.vision_tower.encoder.layers.9.mlp.down_proj.linear", |
| "model.vision_tower.encoder.layers.12.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.17.self_attn.o_proj", |
| "model.vision_tower.encoder.layers.10.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.19.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.18.mlp", |
| "model.vision_tower.encoder.layers.5.post_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.20", |
| "model.vision_tower.encoder.layers.13.self_attn.k_norm", |
| "model.vision_tower.encoder.layers.17.self_attn.v_proj", |
| "model.vision_tower.encoder.layers.14.self_attn.k_proj", |
| "model.vision_tower.encoder.layers.18.self_attn.v_proj", |
| "model.vision_tower.encoder.layers.22.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.0.mlp.down_proj.linear", |
| "model.vision_tower.encoder.layers.15.self_attn.v_norm", |
| "model.vision_tower.encoder.layers.12.mlp.up_proj", |
| "model.vision_tower.encoder.layers.18.self_attn.k_proj", |
| "model.vision_tower.encoder.layers.22.mlp", |
| "model.vision_tower.encoder.layers.4.self_attn.k_proj", |
| "model.vision_tower.encoder.layers.0.self_attn.o_proj", |
| "model.vision_tower.encoder.layers.22.self_attn.q_norm", |
| "model.vision_tower.encoder.layers.16.post_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.12.post_attention_layernorm", |
| "model.vision_tower.encoder.layers.10.mlp.act_fn", |
| "model.vision_tower.encoder.layers.24.self_attn.k_norm", |
| "model.vision_tower.encoder.layers.17.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.16.mlp.down_proj.linear", |
| "model.vision_tower.encoder.layers.18.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.14.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.9.input_layernorm", |
| "model.vision_tower.encoder.layers.1.mlp.up_proj", |
| "model.vision_tower.encoder.layers.6.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.5.self_attn.k_proj", |
| "model.vision_tower.encoder.layers.12.self_attn.k_norm", |
| "model.vision_tower.encoder.layers.2.self_attn.k_norm", |
| "model.vision_tower.encoder.layers.4.self_attn.k_norm", |
| "model.vision_tower.encoder.layers.1.self_attn.v_norm", |
| "model.vision_tower.encoder.layers.23.self_attn.o_proj", |
| "model.vision_tower.encoder.layers.11.self_attn.k_norm", |
| "model.vision_tower.encoder.layers.20.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.24.mlp.up_proj", |
| "model.vision_tower.encoder.layers.15.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.1.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.9.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.25.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.14.mlp.down_proj", |
| "model.vision_tower.encoder.layers.6.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.18.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.23.self_attn.q_norm", |
| "model.vision_tower.encoder.layers.18", |
| "model.vision_tower.encoder.layers.13.mlp", |
| "model.vision_tower.encoder.layers.12.self_attn.o_proj", |
| "model.vision_tower.encoder.layers.18.self_attn.q_norm", |
| "model.vision_tower.encoder.layers.18.self_attn.v_norm", |
| "model.vision_tower.encoder.layers.20.self_attn.q_proj", |
| "model.vision_tower.encoder.layers.17.self_attn.k_proj", |
| "model.vision_tower.encoder.layers.20.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.25.self_attn.o_proj", |
| "model.vision_tower.encoder.layers.11.mlp.down_proj", |
| "model.vision_tower.encoder.layers.10.mlp.down_proj.linear", |
| "model.vision_tower.encoder.layers.12.mlp.down_proj.linear", |
| "model.vision_tower.encoder.layers.5.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.22.input_layernorm", |
| "model.vision_tower.encoder.layers.6.self_attn.q_proj", |
| "model.vision_tower.encoder.layers.6.self_attn.v_norm", |
| "model.vision_tower.encoder.layers.26.pre_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.21.self_attn.q_proj", |
| "model.vision_tower.encoder.layers.5.mlp", |
| "model.vision_tower.encoder.layers.18.self_attn.o_proj", |
| "model.vision_tower.encoder.layers.7.pre_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.0.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.16.self_attn.q_proj", |
| "model.vision_tower.encoder.layers.25.self_attn.v_norm", |
| "model.vision_tower.encoder.layers.8.self_attn.v_proj", |
| "model.vision_tower.encoder.layers.11.mlp.act_fn", |
| "model.vision_tower.encoder.layers.13.self_attn", |
| "model.vision_tower.encoder.layers.13.mlp.up_proj", |
| "model.vision_tower.encoder.layers.16.self_attn.k_proj", |
| "model.vision_tower.encoder.layers.19.mlp.down_proj.linear", |
| "model.vision_tower.encoder.layers.13.post_attention_layernorm", |
| "model.vision_tower.encoder.layers.6.self_attn.o_proj", |
| "model.vision_tower.encoder.layers.4.input_layernorm", |
| "model.vision_tower.encoder.layers.25.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.14.post_attention_layernorm", |
| "model.vision_tower.encoder.layers.11.pre_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.12.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.16.mlp.down_proj", |
| "model.vision_tower.encoder.layers.1.mlp", |
| "model.vision_tower.encoder.layers.8.self_attn.v_norm", |
| "model.vision_tower.encoder.layers.21.self_attn.k_proj", |
| "model.vision_tower.encoder.layers.6.self_attn.v_proj", |
| "model.vision_tower.encoder.layers.16.mlp", |
| "model.vision_tower.encoder.layers.2.mlp.down_proj", |
| "model.vision_tower.encoder.layers.3.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.13.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.2.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.12", |
| "model.vision_tower.encoder.layers.19.self_attn", |
| "model.vision_tower.encoder.layers.9.mlp", |
| "model.vision_tower.encoder.layers.12.self_attn.q_norm", |
| "model.vision_tower.encoder.layers.20.pre_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.26", |
| "model.vision_tower.encoder.layers.4.mlp.up_proj", |
| "model.vision_tower.encoder.layers.15.mlp.down_proj", |
| "model.vision_tower.encoder.layers.25.post_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.13.self_attn.q_norm", |
| "model.vision_tower.encoder.layers.23.post_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.2.self_attn.q_norm", |
| "model.vision_tower.encoder.layers.26.self_attn", |
| "model.vision_tower.encoder.layers.12.mlp.gate_proj", |
| "model.vision_tower.encoder.layers.15.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.13.pre_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.7.self_attn.k_norm", |
| "model.vision_tower.encoder.layers.10.self_attn.o_proj", |
| "model.vision_tower.encoder.layers.1.mlp.gate_proj", |
| "model.vision_tower.encoder.layers.1.mlp.down_proj", |
| "model.vision_tower.patch_embedder.input_proj", |
| "model.vision_tower.encoder.layers.8.self_attn.q_proj", |
| "model.vision_tower.encoder.layers.7.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.11.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.22.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.8.mlp.act_fn", |
| "model.vision_tower.encoder.layers.3.self_attn.v_norm", |
| "model.vision_tower.encoder.layers.26.post_attention_layernorm", |
| "model.vision_tower.encoder.layers.26.self_attn.k_proj", |
| "model.vision_tower.encoder.layers.3.mlp.down_proj", |
| "model.vision_tower.encoder.layers.25.self_attn.k_proj", |
| "model.vision_tower.encoder.layers.17.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.13.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.24.self_attn.v_norm", |
| "model.vision_tower.encoder.layers.9.mlp.gate_proj", |
| "model.vision_tower.encoder.layers.22.self_attn.q_proj", |
| "model.vision_tower.encoder.layers.14.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.19.mlp", |
| "model.vision_tower.encoder.layers.13.self_attn.q_proj", |
| "model.vision_tower.encoder.layers.7.self_attn.q_proj", |
| "model.vision_tower.encoder.layers.24.pre_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.5.mlp.up_proj", |
| "model.vision_tower.encoder.layers.18.self_attn.q_proj", |
| "model.vision_tower.encoder.layers.18.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.0.mlp", |
| "model.vision_tower.encoder.layers.13.self_attn.v_norm", |
| "model.vision_tower.encoder.layers.25.self_attn.v_proj", |
| "model.vision_tower.encoder.layers.19.self_attn.q_proj", |
| "model.vision_tower.encoder.layers.9.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.9", |
| "model.vision_tower.encoder.layers.4", |
| "model.vision_tower.encoder.layers.17.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.19.post_attention_layernorm", |
| "model.vision_tower.encoder.layers.6.mlp.down_proj", |
| "model.vision_tower.encoder.layers.16.self_attn.q_norm", |
| "model.vision_tower.encoder.layers.13.input_layernorm", |
| "model.vision_tower.encoder.layers.4.self_attn.o_proj", |
| "model.vision_tower.encoder.layers.7.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.10.post_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.17.self_attn.q_norm", |
| "model.vision_tower.encoder.layers.17.mlp.gate_proj", |
| "model.vision_tower.encoder.layers.4.post_attention_layernorm", |
| "model.vision_tower.encoder.layers.5.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.21.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.0.self_attn", |
| "model.vision_tower.encoder.layers.0.self_attn.k_norm", |
| "model.vision_tower.encoder.layers.3.self_attn.k_norm", |
| "model.vision_tower.encoder.layers.9.self_attn.q_proj", |
| "model.vision_tower.encoder.layers.26.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.23.self_attn.q_proj", |
| "model.vision_tower.encoder.layers.2.input_layernorm", |
| "model.vision_tower.encoder.layers.8.mlp.down_proj", |
| "model.vision_tower.encoder.layers.15.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.1.post_attention_layernorm", |
| "model.vision_tower.encoder.layers.22.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.14", |
| "model.vision_tower.encoder.layers.19.pre_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.20.self_attn.v_proj", |
| "model.vision_tower.encoder.layers.4.self_attn.v_norm", |
| "model.vision_tower.encoder.layers.17.self_attn.k_norm", |
| "model.vision_tower.encoder.layers.24.mlp.down_proj.linear", |
| "model.vision_tower.encoder.layers.7.post_attention_layernorm", |
| "model.vision_tower.encoder.layers.25.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.24", |
| "model.vision_tower.encoder.layers.15.self_attn", |
| "model.vision_tower.encoder.layers.2.post_attention_layernorm", |
| "model.vision_tower.encoder.layers.3.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.26.mlp.gate_proj", |
| "model.vision_tower.encoder.layers.12.mlp.down_proj", |
| "model.vision_tower.encoder.layers.10.mlp.gate_proj", |
| "model.vision_tower.encoder.layers.3.self_attn", |
| "model.vision_tower.encoder.layers.20.self_attn", |
| "model.vision_tower.encoder.layers.8.pre_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.25.mlp.gate_proj", |
| "model.vision_tower.encoder.layers.26.input_layernorm", |
| "model.vision_tower.encoder.layers.1.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.5.self_attn.k_norm", |
| "model.vision_tower.encoder.layers.0.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.13.self_attn.k_proj", |
| "model.vision_tower.encoder.layers.6.mlp.down_proj.linear", |
| "model.vision_tower.encoder.layers.13.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.26.self_attn.o_proj", |
| "model.vision_tower.encoder.layers.11.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.14.self_attn.o_proj", |
| "model.vision_tower.encoder.layers", |
| "model.vision_tower.encoder.layers.18.self_attn.k_norm", |
| "model.vision_tower.encoder.layers.23.mlp", |
| "model.vision_tower.encoder.layers.16.self_attn", |
| "model.vision_tower.encoder.layers.23", |
| "model.vision_tower.encoder.layers.9.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.10.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.19.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.11.self_attn.v_proj", |
| "model.vision_tower.encoder.layers.17.self_attn.q_proj", |
| "model.vision_tower.encoder.layers.7.self_attn.k_proj", |
| "model.vision_tower.encoder.layers.2.mlp", |
| "model.vision_tower.encoder.layers.16.self_attn.v_proj", |
| "model.vision_tower.encoder.layers.7.self_attn", |
| "model.vision_tower.encoder.layers.8.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.26.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.19.self_attn.v_proj", |
| "model.vision_tower.encoder.layers.12.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.22.mlp.down_proj.linear", |
| "model.vision_tower.encoder.layers.16.post_attention_layernorm", |
| "model.vision_tower.encoder.layers.13.mlp.act_fn", |
| "model.vision_tower.encoder.layers.8.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.4.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.14.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.11.post_attention_layernorm", |
| "model.vision_tower.encoder.layers.8.self_attn.o_proj", |
| "model.vision_tower.encoder.layers.9.self_attn.q_norm", |
| "model.vision_tower.encoder.layers.10.mlp.up_proj.linear", |
| "model.vision_tower.patch_embedder", |
| "model.vision_tower.encoder.layers.20.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.26.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.10.mlp.up_proj", |
| "model.vision_tower.encoder.layers.1.self_attn.k_norm", |
| "model.vision_tower.encoder.layers.6", |
| "model.vision_tower.encoder.layers.8.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.1.post_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.9.self_attn.k_norm", |
| "model.vision_tower.encoder.layers.12.mlp", |
| "model.vision_tower.encoder.layers.10.pre_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.20.self_attn.k_norm", |
| "model.vision_tower.encoder.layers.26.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.1.self_attn.q_proj", |
| "model.vision_tower.encoder.layers.2.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.15.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.2", |
| "model.vision_tower.encoder.layers.20.self_attn.v_norm", |
| "model.vision_tower.encoder.layers.6.input_layernorm", |
| "model.vision_tower.encoder.layers.3.mlp.act_fn", |
| "model.vision_tower.encoder.layers.17.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.20.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.7.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.3.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.12.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.1.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.8.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.11.self_attn.k_proj", |
| "model.vision_tower.encoder.layers.25.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.4.mlp.act_fn", |
| "model.vision_tower.encoder.layers.15.self_attn.q_proj", |
| "model.vision_tower.encoder.layers.20.mlp.down_proj.linear", |
| "model.vision_tower.encoder.layers.4.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.10.self_attn.q_proj", |
| "model.vision_tower.encoder.layers.9.self_attn.v_norm", |
| "model.vision_tower.encoder.layers.17.post_attention_layernorm", |
| "model.vision_tower.encoder.layers.20.self_attn.q_norm", |
| "model.vision_tower.encoder.layers.10.input_layernorm", |
| "model.vision_tower.encoder.layers.24.self_attn.q_proj", |
| "model.vision_tower.encoder.layers.26.self_attn.k_norm", |
| "model.vision_tower.encoder.layers.25.mlp.down_proj.linear", |
| "model.vision_tower.encoder.layers.18.pre_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.23.mlp.down_proj.linear", |
| "model.vision_tower.encoder.layers.14.mlp.act_fn", |
| "model.vision_tower.encoder.layers.9.mlp.act_fn", |
| "model.vision_tower.encoder.layers.18.post_attention_layernorm", |
| "model.vision_tower.encoder.layers.26.self_attn.v_proj", |
| "model.vision_tower.encoder.layers.2.self_attn.o_proj", |
| "model.vision_tower.encoder.layers.10.self_attn.q_norm", |
| "model.vision_tower.encoder.layers.17.self_attn", |
| "model.vision_tower.encoder.layers.10.self_attn.v_norm", |
| "model.vision_tower.encoder.layers.22.mlp.gate_proj", |
| "model.vision_tower.encoder.layers.5.self_attn.v_proj", |
| "model.vision_tower.encoder.layers.25.mlp.down_proj", |
| "model.vision_tower.encoder.layers.5", |
| "model.vision_tower.encoder.layers.1.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.7.mlp", |
| "model.vision_tower.encoder.layers.9.self_attn.o_proj", |
| "model.vision_tower.encoder.layers.11.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.22.self_attn", |
| "model.vision_tower.encoder.layers.9.self_attn", |
| "model.vision_tower.encoder.layers.4.self_attn.v_proj", |
| "model.vision_tower.encoder.layers.0.post_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.8.self_attn.k_proj", |
| "model.vision_tower.encoder.layers.21.post_attention_layernorm", |
| "model.vision_tower.encoder.layers.24.mlp", |
| "model.vision_tower.encoder.layers.18.input_layernorm", |
| "model.vision_tower.encoder.layers.21.self_attn.q_norm", |
| "model.vision_tower.encoder.layers.24.input_layernorm", |
| "model.vision_tower.encoder.layers.11.post_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.9.self_attn.v_proj", |
| "model.vision_tower.encoder.layers.13.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.16", |
| "model.vision_tower.encoder.layers.15.input_layernorm", |
| "model.vision_tower.encoder.layers.11.self_attn.o_proj", |
| "model.vision_tower.encoder.layers.13.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.11.mlp.gate_proj", |
| "model.vision_tower.encoder.layers.14.self_attn.k_norm", |
| "model.vision_tower.encoder.layers.22.mlp.down_proj", |
| "model.vision_tower.encoder.layers.24.post_attention_layernorm", |
| "model.vision_tower.encoder.layers.4.post_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.15.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.0.self_attn.v_proj", |
| "model.vision_tower.encoder.layers.21.self_attn.v_norm", |
| "model.vision_tower.encoder.layers.5.post_attention_layernorm", |
| "model.vision_tower.encoder.layers.19.mlp.act_fn", |
| "model.vision_tower.encoder.layers.16.mlp.act_fn", |
| "model.vision_tower.encoder.layers.26.mlp.down_proj.linear", |
| "model.vision_tower.encoder.layers.19.self_attn.o_proj", |
| "model.vision_tower.encoder.layers.23.self_attn.k_norm", |
| "model.vision_tower.encoder.layers.7.self_attn.v_proj", |
| "model.vision_tower.encoder.layers.14.input_layernorm", |
| "model.vision_tower.encoder.layers.5.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.16.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.3.pre_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.16.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.6.self_attn", |
| "model.vision_tower.encoder.layers.19.mlp.gate_proj", |
| "model.vision_tower.encoder.layers.24.self_attn.q_norm", |
| "model.vision_tower.encoder.layers.15.mlp", |
| "model.vision_tower.encoder.layers.8", |
| "model.vision_tower.encoder.layers.18.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.23.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.19.self_attn.k_proj", |
| "model.vision_tower.encoder.layers.3.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.8.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.10.self_attn.k_proj", |
| "model.vision_tower.encoder.layers.26.mlp", |
| "model.vision_tower.encoder.layers.10.self_attn", |
| "model.vision_tower.encoder.layers.14.self_attn.q_proj", |
| "model.vision_tower.encoder.layers.15.post_attention_layernorm", |
| "model.vision_tower.encoder.layers.4.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.25.self_attn.q_proj", |
| "model.vision_tower.encoder.layers.12.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.22.post_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.11.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.15.pre_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.19.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.22.self_attn.k_proj", |
| "model.vision_tower.encoder.layers.2.mlp.down_proj.linear", |
| "model.vision_tower.encoder.layers.0.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.24.post_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.25", |
| "model.vision_tower.encoder.layers.3.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.17.self_attn.v_norm", |
| "model.vision_tower.encoder.layers.9.post_attention_layernorm", |
| "model.vision_tower.encoder.layers.7.mlp.down_proj", |
| "model.vision_tower.encoder.layers.11.self_attn.q_norm", |
| "model.vision_tower.encoder.layers.0.mlp.up_proj", |
| "model.vision_tower.encoder.layers.4.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.6.self_attn.k_norm", |
| "model.vision_tower.encoder.layers.26.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.16.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.26.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.1.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.2.self_attn", |
| "model.vision_tower.encoder.layers.4.self_attn.q_norm", |
| "model.vision_tower.encoder.layers.18.mlp.down_proj", |
| "model.vision_tower.encoder.layers.26.self_attn.q_proj", |
| "model.vision_tower.encoder.layers.17.post_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.1.mlp.down_proj.linear", |
| "model.vision_tower.encoder.layers.2.mlp.up_proj", |
| "model.vision_tower.encoder.layers.3.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.21.self_attn.v_proj", |
| "model.vision_tower.encoder.layers.22.pre_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.4.mlp", |
| "model.vision_tower.encoder.layers.4.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.5.input_layernorm", |
| "model.vision_tower.encoder.layers.6.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.9.mlp.down_proj", |
| "model.vision_tower.encoder.layers.15.self_attn.v_proj", |
| "model.vision_tower.encoder.layers.8.post_attention_layernorm", |
| "model.vision_tower.encoder.layers.18.mlp.gate_proj", |
| "model.vision_tower.encoder.layers.2.self_attn.v_proj", |
| "model.vision_tower.encoder.layers.17.mlp.act_fn", |
| "model.vision_tower.encoder.layers.19.self_attn.v_norm", |
| "model.vision_tower.encoder.layers.8.self_attn.q_norm", |
| "model.vision_tower.encoder.layers.19", |
| "model.vision_tower.encoder.layers.2.pre_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.0.self_attn.q_proj", |
| "model.vision_tower.encoder.layers.21.mlp.gate_proj", |
| "model.vision_tower.encoder.layers.25.self_attn", |
| "model.vision_tower.encoder.layers.15.self_attn.k_proj", |
| "model.vision_tower.encoder.layers.2.self_attn.k_proj", |
| "model.vision_tower.encoder.layers.3.post_attention_layernorm", |
| "model.vision_tower.encoder.layers.23.mlp.gate_proj", |
| "model.vision_tower.encoder.layers.5.mlp.act_fn", |
| "model.vision_tower.encoder.layers.24.self_attn.v_proj", |
| "model.vision_tower.encoder.layers.23.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.6.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.5.self_attn", |
| "model.vision_tower.encoder.layers.21.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.19.self_attn.q_norm", |
| "model.vision_tower.encoder.layers.19.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.11.mlp.down_proj.linear", |
| "model.vision_tower.encoder.layers.21.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.24.mlp.gate_proj", |
| "model.vision_tower.encoder.layers.20.mlp.act_fn", |
| "model.vision_tower.encoder.layers.8.mlp.gate_proj", |
| "model.vision_tower.encoder.layers.21", |
| "model.vision_tower.encoder.layers.20.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.12.self_attn.v_norm", |
| "model.vision_tower.encoder.layers.23.pre_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.22.post_attention_layernorm", |
| "model.vision_tower.encoder.layers.6.mlp", |
| "model.vision_tower.encoder.layers.9.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.16.pre_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.13.self_attn.v_proj", |
| "model.vision_tower.encoder.layers.1.mlp.act_fn", |
| "model.vision_tower.encoder.layers.26.self_attn.q_norm", |
| "model.vision_tower.encoder.layers.9.pre_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.0.mlp.gate_proj", |
| "model.vision_tower.encoder.layers.8.mlp.up_proj", |
| "model.vision_tower.encoder.layers.21.self_attn.k_norm", |
| "model.vision_tower.encoder.layers.2.self_attn.q_proj", |
| "model.vision_tower.encoder.layers.0.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.3.post_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.17", |
| "model.vision_tower.encoder.layers.23.input_layernorm", |
| "model.vision_tower.encoder.rotary_emb", |
| "model.vision_tower.encoder.layers.22.self_attn.v_norm", |
| "model.vision_tower.encoder.layers.25.input_layernorm", |
| "model.vision_tower.encoder.layers.5.self_attn.v_norm", |
| "model.vision_tower.encoder.layers.7.post_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.19.input_layernorm", |
| "model.vision_tower.encoder.layers.9.post_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.11.mlp.up_proj", |
| "model.vision_tower.encoder.layers.10.self_attn.k_norm", |
| "model.vision_tower.encoder.layers.5.pre_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.25.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.8.mlp.down_proj.linear", |
| "model.vision_tower.encoder.layers.23.post_attention_layernorm", |
| "model.vision_tower.encoder.layers.21.self_attn.o_proj", |
| "model.vision_tower.encoder.layers.24.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.16.self_attn.k_norm", |
| "model.vision_tower.encoder.layers.22.mlp.up_proj", |
| "model.vision_tower.encoder.layers.12.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.26.post_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.6.mlp.act_fn", |
| "model.vision_tower.encoder.layers.4.pre_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.3.self_attn.q_norm", |
| "model.vision_tower.encoder.layers.8.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.0.input_layernorm", |
| "model.vision_tower.encoder.layers.7.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.23.self_attn.v_proj", |
| "model.vision_tower.encoder.layers.6.post_attention_layernorm", |
| "model.vision_tower.encoder.layers.2.post_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.10.mlp", |
| "model.vision_tower.encoder.layers.2.mlp.act_fn", |
| "model.vision_tower.encoder.layers.14.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.13.post_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.17.mlp.up_proj", |
| "model.vision_tower.encoder.layers.12.self_attn.k_proj", |
| "model.vision_tower.encoder.layers.15.self_attn.q_norm", |
| "model.vision_tower.encoder.layers.20.self_attn.k_proj", |
| "model.vision_tower.encoder.layers.26.mlp.down_proj", |
| "model.vision_tower.encoder.layers.21.self_attn", |
| "model.vision_tower.encoder.layers.24.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.5.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.17.mlp.down_proj.linear", |
| "model.vision_tower.encoder.layers.22.self_attn.o_proj", |
| "model.vision_tower.encoder.layers.23.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.24.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.25.mlp.up_proj", |
| "model.vision_tower.encoder.layers.23.mlp.up_proj", |
| "model.vision_tower.encoder.layers.13.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.25.post_attention_layernorm", |
| "model.vision_tower.encoder.layers.18.mlp.up_proj", |
| "model.vision_tower.encoder.layers.5.self_attn.q_proj", |
| "model.vision_tower.encoder.layers.4.self_attn", |
| "model.vision_tower.encoder.layers.12.pre_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.17.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.16.input_layernorm", |
| "model.vision_tower.encoder.layers.20.mlp.gate_proj", |
| "model.vision_tower.encoder.layers.25.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.8.mlp", |
| "model.vision_tower.encoder.layers.7.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.7.self_attn.v_norm", |
| "model.vision_tower.encoder.layers.9.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.7.mlp.gate_proj", |
| "model.vision_tower.encoder.layers.24.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.12.self_attn.q_proj", |
| "model.vision_tower.encoder.layers.17.mlp.down_proj", |
| "model.vision_tower.encoder.layers.11.self_attn.v_norm", |
| "model.vision_tower.encoder.layers.19.mlp.down_proj", |
| "model.vision_tower.encoder.layers.19.post_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.0.mlp.act_fn", |
| "model.vision_tower.encoder.layers.16.mlp.up_proj", |
| "model.vision_tower.encoder.layers.20.mlp.down_proj", |
| "model.vision_tower.encoder.layers.8.self_attn.k_norm", |
| "model.vision_tower.encoder.layers.18.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.22", |
| "model.vision_tower.encoder.layers.7.mlp.up_proj", |
| "model.vision_tower.encoder.layers.6.pre_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.1.self_attn.k_proj", |
| "model.vision_tower.encoder.layers.14.self_attn.v_norm", |
| "model.vision_tower.encoder.layers.21.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.24.mlp.act_fn", |
| "model.vision_tower.encoder.layers.0", |
| "model.vision_tower.encoder.layers.13", |
| "model.vision_tower.encoder.layers.3.input_layernorm", |
| "model.vision_tower.encoder.layers.3.self_attn.v_proj", |
| "model.vision_tower.encoder.layers.21.post_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.4.mlp.gate_proj", |
| "model.vision_tower.encoder.layers.13.mlp.down_proj.linear", |
| "model.vision_tower.encoder.layers.17.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.12.input_layernorm", |
| "model.vision_tower.encoder.layers.10.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.16.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.3.self_attn.k_proj", |
| "model.vision_tower.encoder.layers.12.self_attn", |
| "model.vision_tower.encoder.layers.24.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.6.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.16.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.24.mlp.down_proj", |
| "model.vision_tower.encoder.layers.14.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.23.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.7.input_layernorm", |
| "model.vision_tower.encoder.layers.11.self_attn", |
| "model.vision_tower.encoder.layers.11.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.1.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.3.mlp", |
| "model.vision_tower.encoder.layers.5.self_attn.o_proj", |
| "model.vision_tower.encoder.layers.16.self_attn.v_norm", |
| "model.vision_tower.encoder.layers.21.mlp.act_fn", |
| "model.vision_tower.encoder.layers.23.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.3.self_attn.o_proj", |
| "model.vision_tower.encoder.layers.18.self_attn", |
| "model.vision_tower.encoder.layers.14.self_attn", |
| "model.vision_tower.encoder.layers.5.self_attn.q_norm", |
| "model.vision_tower.encoder.layers.18.mlp.down_proj.linear", |
| "model.vision_tower.encoder.layers.1.self_attn.v_proj", |
| "model.vision_tower.encoder.layers.14.post_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.16.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.25.self_attn.k_norm", |
| "model.vision_tower.encoder.layers.20.post_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.20.post_attention_layernorm", |
| "model.vision_tower.encoder.layers.10.post_attention_layernorm", |
| "model.vision_tower.encoder.layers.21.mlp.up_proj", |
| "model.vision_tower.encoder.layers.25.self_attn.q_norm", |
| "model.vision_tower", |
| "model.vision_tower.encoder.layers.0.self_attn.q_norm", |
| "model.vision_tower.encoder.layers.5.mlp.gate_proj", |
| "model.vision_tower.encoder.layers.20.input_layernorm", |
| "model.vision_tower.encoder.layers.2.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.10" |
| ], |
| "fan_in_fan_out": false, |
| "inference_mode": true, |
| "init_lora_weights": true, |
| "layer_replication": null, |
| "layers_pattern": null, |
| "layers_to_transform": null, |
| "loftq_config": {}, |
| "lora_alpha": 8, |
| "lora_bias": false, |
| "lora_dropout": 0.0, |
| "megatron_config": null, |
| "megatron_core": "megatron.core", |
| "modules_to_save": null, |
| "peft_type": "LORA", |
| "r": 8, |
| "rank_pattern": {}, |
| "revision": null, |
| "target_modules": [ |
| "q_proj", |
| "v_proj" |
| ], |
| "task_type": "CAUSAL_LM", |
| "trainable_token_indices": null, |
| "use_dora": false, |
| "use_rslora": false |
| } |
