Training in progress, step 448

adapter_config.json

@@ -23,377 +23,377 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "language_model.model.layers.3.mlp.down_proj",
-    "language_model.model.layers.30.self_attn.o_proj",
-    "language_model.model.layers.10.mlp.gate_proj",
-    "vision_tower.vision_model.encoder.layers.5.self_attn.q_proj",
-    "language_model.model.layers.4.self_attn.o_proj",
-    "language_model.model.layers.18.self_attn.q_proj",
-    "vision_tower.vision_model.encoder.layers.14.self_attn.v_proj",
+    "vision_tower.vision_model.encoder.layers.7.mlp.fc2",
+    "language_model.model.layers.21.mlp.down_proj",
     "vision_tower.vision_model.encoder.layers.7.self_attn.v_proj",
-    "language_model.model.layers.27.self_attn.k_proj",
-    "language_model.model.layers.10.self_attn.v_proj",
+    "language_model.model.layers.29.mlp.up_proj",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.k_proj",
+    "language_model.model.layers.1.mlp.gate_proj",
+    "language_model.model.layers.17.mlp.gate_proj",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.k_proj",
+    "language_model.model.layers.2.self_attn.v_proj",
+    "vision_tower.vision_model.encoder.layers.8.mlp.fc1",
+    "language_model.model.layers.9.self_attn.q_proj",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.k_proj",
+    "language_model.model.layers.16.mlp.gate_proj",
+    "language_model.model.layers.20.self_attn.v_proj",
     "language_model.model.layers.19.self_attn.k_proj",
-    "vision_tower.vision_model.encoder.layers.8.mlp.fc2",
+    "language_model.model.layers.18.self_attn.q_proj",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.v_proj",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.q_proj",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.q_proj",
+    "language_model.model.layers.1.self_attn.o_proj",
+    "language_model.model.layers.13.self_attn.q_proj",
+    "language_model.model.layers.28.self_attn.q_proj",
+    "language_model.model.layers.8.self_attn.k_proj",
+    "language_model.model.layers.1.self_attn.k_proj",
+    "vision_tower.vision_model.encoder.layers.18.mlp.fc2",
     "language_model.model.layers.14.mlp.up_proj",
-    "language_model.model.layers.29.self_attn.o_proj",
-    "vision_tower.vision_model.encoder.layers.22.mlp.fc2",
-    "vision_tower.vision_model.encoder.layers.19.mlp.fc2",
-    "language_model.model.layers.0.self_attn.k_proj",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.q_proj",
+    "language_model.model.layers.4.mlp.down_proj",
+    "language_model.model.layers.8.self_attn.v_proj",
+    "language_model.model.layers.20.self_attn.k_proj",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.q_proj",
+    "language_model.model.layers.11.self_attn.k_proj",
+    "language_model.model.layers.19.mlp.down_proj",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.out_proj",
+    "language_model.model.layers.10.self_attn.v_proj",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.q_proj",
+    "language_model.model.layers.23.self_attn.q_proj",
+    "vision_tower.vision_model.encoder.layers.9.mlp.fc2",
     "language_model.model.layers.29.mlp.gate_proj",
-    "vision_tower.vision_model.encoder.layers.6.mlp.fc2",
-    "language_model.model.layers.22.self_attn.o_proj",
-    "vision_tower.vision_model.encoder.layers.18.self_attn.q_proj",
-    "language_model.model.layers.9.self_attn.q_proj",
-    "vision_tower.vision_model.encoder.layers.7.self_attn.k_proj",
-    "language_model.model.layers.18.self_attn.o_proj",
-    "vision_tower.vision_model.encoder.layers.23.self_attn.k_proj",
-    "vision_tower.vision_model.encoder.layers.21.self_attn.k_proj",
-    "language_model.model.layers.4.self_attn.v_proj",
-    "language_model.model.layers.9.self_attn.k_proj",
-    "vision_tower.vision_model.encoder.layers.6.self_attn.out_proj",
-    "vision_tower.vision_model.encoder.layers.6.self_attn.q_proj",
-    "vision_tower.vision_model.encoder.layers.4.mlp.fc2",
-    "language_model.model.layers.16.self_attn.v_proj",
-    "language_model.model.layers.16.self_attn.o_proj",
-    "vision_tower.vision_model.encoder.layers.12.mlp.fc1",
-    "vision_tower.vision_model.encoder.layers.11.self_attn.q_proj",
-    "vision_tower.vision_model.encoder.layers.6.self_attn.k_proj",
-    "language_model.model.layers.6.mlp.down_proj",
-    "language_model.model.layers.16.mlp.down_proj",
-    "language_model.model.layers.20.mlp.gate_proj",
-    "language_model.model.layers.0.self_attn.q_proj",
-    "language_model.model.layers.11.mlp.up_proj",
-    "vision_tower.vision_model.encoder.layers.17.mlp.fc2",
-    "language_model.model.layers.17.self_attn.o_proj",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.v_proj",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.q_proj",
+    "language_model.model.layers.18.mlp.up_proj",
+    "language_model.model.layers.3.self_attn.q_proj",
+    "language_model.model.layers.24.self_attn.q_proj",
+    "vision_tower.vision_model.encoder.layers.16.mlp.fc1",
+    "language_model.model.layers.2.mlp.up_proj",
+    "language_model.model.layers.6.self_attn.k_proj",
+    "language_model.model.layers.18.self_attn.v_proj",
+    "language_model.model.layers.25.self_attn.v_proj",
+    "vision_tower.vision_model.encoder.layers.15.mlp.fc2",
+    "vision_tower.vision_model.encoder.layers.21.mlp.fc2",
+    "language_model.model.layers.9.self_attn.o_proj",
     "language_model.model.layers.10.mlp.down_proj",
-    "vision_tower.vision_model.encoder.layers.11.self_attn.v_proj",
-    "language_model.model.layers.15.self_attn.v_proj",
-    "language_model.model.layers.21.self_attn.k_proj",
-    "language_model.model.layers.14.self_attn.q_proj",
-    "language_model.model.layers.8.mlp.down_proj",
-    "vision_tower.vision_model.encoder.layers.3.self_attn.out_proj",
-    "language_model.model.layers.27.mlp.gate_proj",
-    "vision_tower.vision_model.encoder.layers.18.self_attn.v_proj",
-    "vision_tower.vision_model.encoder.layers.5.self_attn.v_proj",
+    "language_model.model.layers.8.mlp.up_proj",
+    "language_model.model.layers.6.self_attn.v_proj",
+    "language_model.model.layers.31.self_attn.o_proj",
+    "language_model.model.layers.23.self_attn.o_proj",
+    "language_model.model.layers.27.self_attn.q_proj",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.q_proj",
+    "vision_tower.vision_model.encoder.layers.22.mlp.fc2",
+    "language_model.model.layers.27.self_attn.k_proj",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.v_proj",
+    "language_model.model.layers.25.self_attn.q_proj",
+    "vision_tower.vision_model.encoder.layers.12.mlp.fc1",
+    "language_model.model.layers.3.mlp.down_proj",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj",
+    "language_model.model.layers.21.mlp.up_proj",
+    "language_model.model.layers.27.self_attn.o_proj",
+    "language_model.model.layers.2.self_attn.k_proj",
+    "vision_tower.vision_model.encoder.layers.6.mlp.fc2",
+    "language_model.model.layers.7.self_attn.o_proj",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.out_proj",
+    "language_model.model.layers.17.mlp.up_proj",
     "language_model.model.layers.9.mlp.up_proj",
-    "language_model.model.layers.10.mlp.up_proj",
-    "vision_tower.vision_model.encoder.layers.13.mlp.fc1",
-    "multi_modal_projector.linear_2",
-    "language_model.model.layers.8.mlp.gate_proj",
-    "language_model.model.layers.28.self_attn.o_proj",
-    "language_model.model.layers.14.self_attn.k_proj",
-    "language_model.model.layers.15.self_attn.q_proj",
-    "language_model.model.layers.3.mlp.gate_proj",
-    "language_model.model.layers.23.mlp.up_proj",
-    "vision_tower.vision_model.encoder.layers.6.self_attn.v_proj",
-    "language_model.model.layers.8.self_attn.q_proj",
-    "vision_tower.vision_model.encoder.layers.12.self_attn.out_proj",
-    "language_model.model.layers.0.self_attn.v_proj",
-    "language_model.model.layers.30.mlp.gate_proj",
-    "language_model.model.layers.28.self_attn.q_proj",
-    "language_model.model.layers.23.self_attn.k_proj",
-    "vision_tower.vision_model.encoder.layers.22.mlp.fc1",
-    "vision_tower.vision_model.encoder.layers.19.self_attn.k_proj",
-    "vision_tower.vision_model.encoder.layers.20.mlp.fc1",
-    "language_model.model.layers.17.mlp.down_proj",
-    "language_model.model.layers.10.self_attn.k_proj",
-    "language_model.model.layers.4.mlp.up_proj",
-    "vision_tower.vision_model.encoder.layers.20.self_attn.out_proj",
-    "vision_tower.vision_model.encoder.layers.17.mlp.fc1",
-    "vision_tower.vision_model.encoder.layers.11.self_attn.k_proj",
+    "language_model.model.layers.13.self_attn.k_proj",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.v_proj",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.out_proj",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.q_proj",
+    "language_model.model.layers.8.self_attn.o_proj",
     "vision_tower.vision_model.encoder.layers.5.mlp.fc1",
-    "language_model.model.layers.13.mlp.gate_proj",
-    "vision_tower.vision_model.encoder.layers.22.self_attn.k_proj",
-    "language_model.model.layers.22.self_attn.v_proj",
-    "language_model.model.layers.12.mlp.up_proj",
-    "language_model.model.layers.22.mlp.up_proj",
-    "vision_tower.vision_model.encoder.layers.21.mlp.fc1",
-    "language_model.model.layers.25.self_attn.o_proj",
-    "vision_tower.vision_model.encoder.layers.19.self_attn.v_proj",
-    "language_model.model.layers.20.mlp.down_proj",
-    "language_model.model.layers.9.self_attn.o_proj",
-    "language_model.model.layers.3.self_attn.q_proj",
-    "language_model.model.layers.9.mlp.down_proj",
-    "language_model.model.layers.11.self_attn.k_proj",
-    "vision_tower.vision_model.encoder.layers.23.self_attn.q_proj",
-    "vision_tower.vision_model.encoder.layers.15.self_attn.out_proj",
-    "language_model.model.layers.29.mlp.down_proj",
-    "vision_tower.vision_model.encoder.layers.2.mlp.fc1",
-    "vision_tower.vision_model.encoder.layers.4.mlp.fc1",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.k_proj",
     "vision_tower.vision_model.encoder.layers.20.self_attn.q_proj",
-    "language_model.model.layers.3.self_attn.v_proj",
+    "language_model.model.layers.28.mlp.gate_proj",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.out_proj",
+    "vision_tower.vision_model.encoder.layers.13.mlp.fc2",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.out_proj",
+    "language_model.model.layers.10.self_attn.q_proj",
+    "language_model.model.layers.3.self_attn.o_proj",
+    "language_model.model.layers.19.self_attn.v_proj",
+    "vision_tower.vision_model.encoder.layers.23.mlp.fc2",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.k_proj",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.v_proj",
     "language_model.model.layers.23.self_attn.v_proj",
-    "language_model.model.layers.27.self_attn.o_proj",
-    "vision_tower.vision_model.encoder.layers.7.self_attn.q_proj",
-    "vision_tower.vision_model.encoder.layers.4.self_attn.v_proj",
-    "language_model.model.layers.16.mlp.up_proj",
-    "language_model.model.layers.31.self_attn.q_proj",
-    "vision_tower.vision_model.encoder.layers.12.self_attn.k_proj",
-    "language_model.model.layers.6.mlp.up_proj",
-    "language_model.model.layers.8.mlp.up_proj",
-    "language_model.model.layers.27.mlp.up_proj",
-    "language_model.model.layers.18.self_attn.k_proj",
-    "language_model.model.layers.25.mlp.gate_proj",
-    "language_model.model.layers.29.mlp.up_proj",
-    "vision_tower.vision_model.encoder.layers.8.self_attn.q_proj",
-    "language_model.model.layers.26.mlp.down_proj",
-    "language_model.model.layers.24.self_attn.o_proj",
-    "language_model.model.layers.24.self_attn.v_proj",
-    "language_model.model.layers.12.mlp.down_proj",
-    "language_model.model.layers.13.self_attn.q_proj",
-    "language_model.model.layers.17.self_attn.v_proj",
-    "language_model.model.layers.21.self_attn.o_proj",
-    "language_model.model.layers.29.self_attn.k_proj",
-    "vision_tower.vision_model.encoder.layers.16.self_attn.v_proj",
-    "language_model.model.layers.15.self_attn.k_proj",
-    "language_model.model.layers.31.mlp.gate_proj",
-    "language_model.model.layers.5.self_attn.v_proj",
-    "language_model.model.layers.16.self_attn.k_proj",
-    "language_model.model.layers.13.mlp.up_proj",
+    "language_model.model.layers.28.mlp.down_proj",
+    "language_model.model.layers.23.mlp.up_proj",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.q_proj",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.v_proj",
     "vision_tower.vision_model.encoder.layers.10.mlp.fc2",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.out_proj",
+    "language_model.model.layers.24.self_attn.v_proj",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.k_proj",
     "language_model.model.layers.14.self_attn.o_proj",
-    "language_model.model.layers.26.self_attn.o_proj",
-    "vision_tower.vision_model.encoder.layers.11.self_attn.out_proj",
-    "vision_tower.vision_model.encoder.layers.9.self_attn.q_proj",
-    "language_model.model.layers.12.self_attn.v_proj",
-    "language_model.model.layers.5.self_attn.q_proj",
-    "vision_tower.vision_model.encoder.layers.19.mlp.fc1",
-    "vision_tower.vision_model.encoder.layers.22.self_attn.v_proj",
-    "language_model.lm_head",
-    "language_model.model.layers.9.self_attn.v_proj",
-    "vision_tower.vision_model.encoder.layers.3.mlp.fc1",
-    "vision_tower.vision_model.encoder.layers.15.self_attn.k_proj",
-    "language_model.model.layers.1.mlp.down_proj",
-    "language_model.model.layers.6.self_attn.o_proj",
-    "vision_tower.vision_model.encoder.layers.23.mlp.fc1",
-    "vision_tower.vision_model.encoder.layers.1.self_attn.k_proj",
-    "vision_tower.vision_model.encoder.layers.16.mlp.fc2",
-    "vision_tower.vision_model.encoder.layers.20.mlp.fc2",
-    "language_model.model.layers.24.self_attn.q_proj",
-    "vision_tower.vision_model.encoder.layers.23.self_attn.out_proj",
-    "vision_tower.vision_model.encoder.layers.3.mlp.fc2",
-    "vision_tower.vision_model.encoder.layers.14.self_attn.k_proj",
-    "vision_tower.vision_model.encoder.layers.8.self_attn.out_proj",
-    "language_model.model.layers.20.mlp.up_proj",
-    "vision_tower.vision_model.encoder.layers.11.mlp.fc1",
-    "language_model.model.layers.28.mlp.down_proj",
-    "language_model.model.layers.23.mlp.down_proj",
-    "language_model.model.layers.4.mlp.down_proj",
-    "vision_tower.vision_model.encoder.layers.9.mlp.fc2",
-    "language_model.model.layers.1.self_attn.k_proj",
-    "language_model.model.layers.13.mlp.down_proj",
-    "language_model.model.layers.28.self_attn.v_proj",
-    "language_model.model.layers.7.mlp.gate_proj",
-    "language_model.model.layers.5.self_attn.k_proj",
-    "language_model.model.layers.30.self_attn.q_proj",
-    "vision_tower.vision_model.encoder.layers.13.mlp.fc2",
-    "language_model.model.layers.26.mlp.gate_proj",
-    "language_model.model.layers.28.mlp.gate_proj",
-    "language_model.model.layers.20.self_attn.v_proj",
-    "vision_tower.vision_model.encoder.layers.10.self_attn.v_proj",
-    "language_model.model.layers.23.self_attn.o_proj",
-    "vision_tower.vision_model.encoder.layers.13.self_attn.k_proj",
-    "vision_tower.vision_model.encoder.layers.3.self_attn.q_proj",
-    "language_model.model.layers.8.self_attn.o_proj",
-    "vision_tower.vision_model.encoder.layers.18.self_attn.k_proj",
-    "language_model.model.layers.8.self_attn.k_proj",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.q_proj",
+    "language_model.model.layers.29.self_attn.o_proj",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.q_proj",
     "vision_tower.vision_model.encoder.layers.0.self_attn.q_proj",
-    "vision_tower.vision_model.encoder.layers.18.mlp.fc2",
-    "language_model.model.layers.11.self_attn.q_proj",
-    "language_model.model.layers.25.self_attn.v_proj",
-    "vision_tower.vision_model.encoder.layers.8.self_attn.v_proj",
-    "language_model.model.layers.27.self_attn.q_proj",
-    "language_model.model.layers.22.mlp.down_proj",
-    "language_model.model.layers.17.self_attn.k_proj",
-    "language_model.model.layers.20.self_attn.q_proj",
-    "vision_tower.vision_model.encoder.layers.1.self_attn.q_proj",
-    "language_model.model.layers.30.self_attn.k_proj",
-    "language_model.model.layers.19.self_attn.o_proj",
-    "language_model.model.layers.7.self_attn.v_proj",
-    "vision_tower.vision_model.encoder.layers.0.self_attn.out_proj",
-    "language_model.model.layers.12.mlp.gate_proj",
-    "language_model.model.layers.23.self_attn.q_proj",
-    "language_model.model.layers.23.mlp.gate_proj",
-    "language_model.model.layers.10.self_attn.o_proj",
-    "language_model.model.layers.15.mlp.gate_proj",
-    "vision_tower.vision_model.encoder.layers.2.self_attn.out_proj",
-    "vision_tower.vision_model.encoder.layers.7.self_attn.out_proj",
-    "vision_tower.vision_model.encoder.layers.5.mlp.fc2",
-    "language_model.model.layers.4.mlp.gate_proj",
-    "language_model.model.layers.2.self_attn.q_proj",
-    "vision_tower.vision_model.encoder.layers.16.self_attn.k_proj",
-    "language_model.model.layers.28.mlp.up_proj",
-    "vision_tower.vision_model.encoder.layers.5.self_attn.out_proj",
+    "language_model.model.layers.15.mlp.up_proj",
+    "language_model.model.layers.7.self_attn.q_proj",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.out_proj",
+    "vision_tower.vision_model.encoder.layers.14.mlp.fc2",
     "language_model.model.layers.13.self_attn.o_proj",
-    "vision_tower.vision_model.encoder.layers.0.self_attn.k_proj",
-    "vision_tower.vision_model.encoder.layers.4.self_attn.out_proj",
-    "language_model.model.layers.20.self_attn.o_proj",
-    "language_model.model.layers.30.self_attn.v_proj",
-    "language_model.model.layers.18.self_attn.v_proj",
-    "language_model.model.layers.18.mlp.gate_proj",
-    "language_model.model.layers.31.self_attn.o_proj",
-    "vision_tower.vision_model.encoder.layers.16.mlp.fc1",
     "vision_tower.vision_model.encoder.layers.0.mlp.fc1",
-    "language_model.model.layers.22.mlp.gate_proj",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.v_proj",
+    "vision_tower.vision_model.encoder.layers.8.mlp.fc2",
+    "language_model.model.layers.24.self_attn.o_proj",
+    "vision_tower.vision_model.encoder.layers.2.mlp.fc2",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.k_proj",
+    "language_model.model.layers.15.mlp.gate_proj",
     "language_model.model.layers.3.self_attn.k_proj",
-    "vision_tower.vision_model.encoder.layers.21.mlp.fc2",
-    "language_model.model.layers.19.self_attn.v_proj",
-    "language_model.model.layers.7.mlp.down_proj",
-    "vision_tower.vision_model.encoder.layers.21.self_attn.out_proj",
-    "language_model.model.layers.18.mlp.up_proj",
-    "language_model.model.layers.0.self_attn.o_proj",
-    "language_model.model.layers.2.self_attn.o_proj",
-    "language_model.model.layers.13.self_attn.k_proj",
-    "vision_tower.vision_model.encoder.layers.10.self_attn.k_proj",
-    "language_model.model.layers.0.mlp.gate_proj",
-    "vision_tower.vision_model.encoder.layers.15.mlp.fc2",
+    "language_model.model.layers.11.self_attn.v_proj",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.out_proj",
+    "vision_tower.vision_model.encoder.layers.20.mlp.fc2",
+    "language_model.model.layers.2.self_attn.q_proj",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.v_proj",
+    "language_model.model.layers.16.self_attn.o_proj",
+    "language_model.model.layers.1.mlp.up_proj",
+    "language_model.model.layers.18.self_attn.o_proj",
+    "language_model.model.layers.19.self_attn.o_proj",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.q_proj",
+    "language_model.model.layers.12.self_attn.v_proj",
+    "language_model.model.layers.5.self_attn.q_proj",
+    "vision_tower.vision_model.encoder.layers.20.mlp.fc1",
+    "language_model.model.layers.15.self_attn.k_proj",
+    "language_model.model.layers.12.self_attn.o_proj",
     "language_model.model.layers.31.mlp.down_proj",
-    "language_model.model.layers.17.mlp.up_proj",
-    "language_model.model.layers.26.self_attn.q_proj",
-    "vision_tower.vision_model.encoder.layers.7.mlp.fc2",
-    "language_model.model.layers.26.self_attn.k_proj",
+    "language_model.model.layers.14.mlp.down_proj",
+    "language_model.model.layers.27.mlp.down_proj",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.k_proj",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.out_proj",
+    "vision_tower.vision_model.encoder.layers.3.mlp.fc1",
+    "language_model.model.layers.16.self_attn.v_proj",
+    "language_model.model.layers.30.mlp.down_proj",
+    "language_model.model.layers.30.self_attn.v_proj",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.out_proj",
     "language_model.model.layers.26.self_attn.v_proj",
-    "language_model.model.layers.21.self_attn.q_proj",
-    "language_model.model.layers.10.self_attn.q_proj",
-    "language_model.model.layers.2.self_attn.k_proj",
-    "language_model.model.layers.25.self_attn.k_proj",
-    "vision_tower.vision_model.encoder.layers.2.self_attn.q_proj",
+    "language_model.model.layers.21.mlp.gate_proj",
+    "language_model.model.layers.29.mlp.down_proj",
+    "language_model.model.layers.22.self_attn.v_proj",
     "language_model.model.layers.1.self_attn.q_proj",
-    "vision_tower.vision_model.encoder.layers.7.mlp.fc1",
-    "language_model.model.layers.1.mlp.gate_proj",
-    "language_model.model.layers.5.self_attn.o_proj",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.out_proj",
+    "language_model.model.layers.0.self_attn.o_proj",
+    "language_model.model.layers.21.self_attn.k_proj",
+    "multi_modal_projector.linear_1",
+    "language_model.model.layers.13.mlp.down_proj",
+    "language_model.model.layers.16.self_attn.q_proj",
+    "language_model.model.layers.4.self_attn.q_proj",
+    "language_model.model.layers.3.self_attn.v_proj",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.v_proj",
+    "vision_tower.vision_model.encoder.layers.4.mlp.fc2",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.k_proj",
+    "language_model.model.layers.0.mlp.gate_proj",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.out_proj",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.out_proj",
+    "language_model.model.layers.8.mlp.gate_proj",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.v_proj",
+    "vision_tower.vision_model.encoder.layers.1.mlp.fc2",
+    "language_model.model.layers.7.self_attn.v_proj",
     "language_model.model.layers.5.mlp.up_proj",
-    "language_model.model.layers.1.self_attn.o_proj",
-    "language_model.model.layers.19.mlp.down_proj",
-    "language_model.model.layers.17.self_attn.q_proj",
+    "vision_tower.vision_model.encoder.layers.17.mlp.fc1",
+    "language_model.model.layers.22.self_attn.k_proj",
+    "vision_tower.vision_model.encoder.layers.19.mlp.fc2",
+    "language_model.model.layers.14.self_attn.v_proj",
+    "language_model.model.layers.21.self_attn.v_proj",
+    "language_model.model.layers.14.self_attn.k_proj",
+    "language_model.model.layers.31.mlp.gate_proj",
+    "language_model.model.layers.9.mlp.gate_proj",
+    "language_model.model.layers.11.mlp.up_proj",
+    "language_model.model.layers.1.mlp.down_proj",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.k_proj",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.q_proj",
+    "language_model.model.layers.13.mlp.gate_proj",
+    "language_model.model.layers.11.self_attn.o_proj",
+    "language_model.model.layers.24.mlp.down_proj",
     "language_model.model.layers.4.self_attn.k_proj",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.q_proj",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.out_proj",
+    "language_model.model.layers.26.self_attn.o_proj",
+    "vision_tower.vision_model.encoder.layers.11.mlp.fc1",
+    "language_model.model.layers.0.mlp.up_proj",
     "language_model.model.layers.27.self_attn.v_proj",
-    "vision_tower.vision_model.encoder.layers.20.self_attn.k_proj",
-    "vision_tower.vision_model.encoder.layers.15.mlp.fc1",
-    "vision_tower.vision_model.encoder.layers.2.self_attn.k_proj",
-    "vision_tower.vision_model.encoder.layers.12.self_attn.q_proj",
-    "language_model.model.layers.11.self_attn.o_proj",
-    "language_model.model.layers.1.mlp.up_proj",
-    "language_model.model.layers.6.self_attn.k_proj",
-    "language_model.model.layers.1.self_attn.v_proj",
-    "vision_tower.vision_model.encoder.layers.16.self_attn.q_proj",
-    "vision_tower.vision_model.encoder.layers.13.self_attn.q_proj",
-    "language_model.model.layers.12.self_attn.q_proj",
-    "vision_tower.vision_model.encoder.layers.18.self_attn.out_proj",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.v_proj",
+    "multi_modal_projector.linear_2",
+    "vision_tower.vision_model.encoder.layers.18.mlp.fc1",
+    "vision_tower.vision_model.encoder.layers.16.mlp.fc2",
+    "language_model.model.layers.24.self_attn.k_proj",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.out_proj",
+    "language_model.model.layers.5.mlp.gate_proj",
+    "language_model.model.layers.15.mlp.down_proj",
+    "language_model.model.layers.22.mlp.gate_proj",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.q_proj",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.q_proj",
+    "language_model.model.layers.22.mlp.up_proj",
+    "language_model.model.layers.29.self_attn.k_proj",
     "vision_tower.vision_model.encoder.layers.0.mlp.fc2",
-    "language_model.model.layers.3.self_attn.o_proj",
-    "language_model.model.layers.8.self_attn.v_proj",
-    "vision_tower.vision_model.encoder.layers.23.self_attn.v_proj",
-    "vision_tower.vision_model.encoder.layers.1.self_attn.v_proj",
-    "vision_tower.vision_model.encoder.layers.2.mlp.fc2",
-    "language_model.model.layers.7.self_attn.o_proj",
-    "language_model.model.layers.2.mlp.gate_proj",
-    "vision_tower.vision_model.encoder.layers.14.mlp.fc2",
-    "language_model.model.layers.25.mlp.up_proj",
-    "language_model.model.layers.24.mlp.up_proj",
-    "language_model.model.layers.2.mlp.up_proj",
+    "language_model.model.layers.12.mlp.gate_proj",
+    "vision_tower.vision_model.encoder.layers.2.mlp.fc1",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.k_proj",
     "language_model.model.layers.28.self_attn.k_proj",
-    "language_model.model.layers.19.mlp.gate_proj",
-    "language_model.model.layers.29.self_attn.v_proj",
-    "language_model.model.layers.7.mlp.up_proj",
-    "language_model.model.layers.9.mlp.gate_proj",
-    "language_model.model.layers.31.self_attn.v_proj",
-    "vision_tower.vision_model.encoder.layers.12.self_attn.v_proj",
-    "language_model.model.layers.7.self_attn.k_proj",
-    "language_model.model.layers.24.mlp.gate_proj",
-    "vision_tower.vision_model.encoder.layers.8.self_attn.k_proj",
-    "vision_tower.vision_model.encoder.layers.10.self_attn.out_proj",
-    "language_model.model.layers.5.mlp.down_proj",
-    "vision_tower.vision_model.encoder.layers.17.self_attn.v_proj",
-    "language_model.model.layers.11.mlp.gate_proj",
-    "vision_tower.vision_model.encoder.layers.14.mlp.fc1",
-    "language_model.model.layers.11.self_attn.v_proj",
-    "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj",
+    "language_model.model.layers.7.mlp.gate_proj",
+    "language_model.model.layers.9.self_attn.v_proj",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.out_proj",
+    "vision_tower.vision_model.encoder.layers.5.mlp.fc2",
     "language_model.model.layers.30.mlp.up_proj",
-    "vision_tower.vision_model.encoder.layers.19.self_attn.out_proj",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.k_proj",
+    "language_model.lm_head",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.k_proj",
+    "language_model.model.layers.3.mlp.gate_proj",
+    "language_model.model.layers.20.self_attn.q_proj",
+    "language_model.model.layers.17.self_attn.k_proj",
     "vision_tower.vision_model.encoder.layers.10.self_attn.q_proj",
-    "vision_tower.vision_model.encoder.layers.6.mlp.fc1",
-    "vision_tower.vision_model.encoder.layers.9.self_attn.k_proj",
-    "vision_tower.vision_model.encoder.layers.1.mlp.fc1",
-    "language_model.model.layers.29.self_attn.q_proj",
-    "language_model.model.layers.16.mlp.gate_proj",
-    "vision_tower.vision_model.encoder.layers.4.self_attn.q_proj",
-    "language_model.model.layers.22.self_attn.k_proj",
-    "vision_tower.vision_model.encoder.layers.18.mlp.fc1",
-    "language_model.model.layers.6.mlp.gate_proj",
-    "language_model.model.layers.3.mlp.up_proj",
-    "language_model.model.layers.0.mlp.down_proj",
-    "vision_tower.vision_model.encoder.layers.12.mlp.fc2",
-    "vision_tower.vision_model.encoder.layers.22.self_attn.out_proj",
-    "language_model.model.layers.24.mlp.down_proj",
-    "vision_tower.vision_model.encoder.layers.21.self_attn.q_proj",
-    "language_model.model.layers.24.self_attn.k_proj",
-    "vision_tower.vision_model.encoder.layers.14.self_attn.q_proj",
-    "language_model.model.layers.21.mlp.down_proj",
-    "language_model.model.layers.7.self_attn.q_proj",
-    "vision_tower.vision_model.encoder.layers.3.self_attn.v_proj",
-    "language_model.model.layers.16.self_attn.q_proj",
-    "language_model.model.layers.18.mlp.down_proj",
-    "language_model.model.layers.14.mlp.gate_proj",
-    "vision_tower.vision_model.encoder.layers.17.self_attn.q_proj",
-    "language_model.model.layers.4.self_attn.q_proj",
-    "language_model.model.layers.21.mlp.gate_proj",
-    "language_model.model.layers.11.mlp.down_proj",
-    "language_model.model.layers.6.self_attn.v_proj",
+    "language_model.model.layers.2.mlp.gate_proj",
+    "language_model.model.layers.8.mlp.down_proj",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.v_proj",
+    "language_model.model.layers.15.self_attn.v_proj",
+    "language_model.model.layers.27.mlp.gate_proj",
+    "vision_tower.vision_model.encoder.layers.19.mlp.fc1",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.k_proj",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.out_proj",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.q_proj",
+    "vision_tower.vision_model.encoder.layers.17.mlp.fc2",
+    "language_model.model.layers.10.mlp.gate_proj",
+    "language_model.model.layers.20.self_attn.o_proj",
+    "language_model.model.layers.0.self_attn.k_proj",
     "vision_tower.vision_model.encoder.layers.17.self_attn.k_proj",
-    "language_model.model.layers.31.mlp.up_proj",
-    "vision_tower.vision_model.encoder.layers.17.self_attn.out_proj",
-    "language_model.model.layers.15.self_attn.o_proj",
-    "vision_tower.vision_model.encoder.layers.11.mlp.fc2",
+    "language_model.model.layers.31.self_attn.k_proj",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.q_proj",
     "vision_tower.vision_model.encoder.layers.13.self_attn.out_proj",
-    "language_model.model.layers.21.self_attn.v_proj",
-    "language_model.model.layers.13.self_attn.v_proj",
-    "language_model.model.layers.27.mlp.down_proj",
+    "language_model.model.layers.17.self_attn.v_proj",
     "language_model.model.layers.22.self_attn.q_proj",
-    "multi_modal_projector.linear_1",
+    "language_model.model.layers.4.mlp.up_proj",
+    "language_model.model.layers.30.self_attn.k_proj",
+    "language_model.model.layers.29.self_attn.v_proj",
     "vision_tower.vision_model.encoder.layers.9.mlp.fc1",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.k_proj",
+    "language_model.model.layers.0.self_attn.v_proj",
+    "vision_tower.vision_model.encoder.layers.15.mlp.fc1",
+    "language_model.model.layers.13.mlp.up_proj",
+    "language_model.model.layers.16.mlp.down_proj",
+    "language_model.model.layers.24.mlp.up_proj",
+    "language_model.model.layers.18.mlp.down_proj",
+    "language_model.model.layers.11.mlp.down_proj",
+    "language_model.model.layers.3.mlp.up_proj",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.q_proj",
+    "language_model.model.layers.26.self_attn.q_proj",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.v_proj",
+    "language_model.model.layers.19.mlp.gate_proj",
+    "language_model.model.layers.30.self_attn.o_proj",
+    "language_model.model.layers.10.self_attn.o_proj",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.k_proj",
+    "language_model.model.layers.12.mlp.up_proj",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.k_proj",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.v_proj",
+    "vision_tower.vision_model.encoder.layers.11.mlp.fc2",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.out_proj",
+    "language_model.model.layers.5.self_attn.k_proj",
+    "language_model.model.layers.22.mlp.down_proj",
+    "language_model.model.layers.7.mlp.up_proj",
+    "language_model.model.layers.18.self_attn.k_proj",
+    "language_model.model.layers.17.mlp.down_proj",
+    "language_model.model.layers.28.self_attn.o_proj",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.k_proj",
+    "vision_tower.vision_model.encoder.layers.3.mlp.fc2",
+    "language_model.model.layers.6.self_attn.o_proj",
+    "language_model.model.layers.9.mlp.down_proj",
+    "language_model.model.layers.25.mlp.gate_proj",
+    "language_model.model.layers.25.mlp.down_proj",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.out_proj",
+    "language_model.model.layers.5.self_attn.v_proj",
+    "language_model.model.layers.23.mlp.gate_proj",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.k_proj",
+    "vision_tower.vision_model.encoder.layers.14.mlp.fc1",
+    "language_model.model.layers.23.mlp.down_proj",
+    "language_model.model.layers.14.mlp.gate_proj",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.out_proj",
+    "language_model.model.layers.5.self_attn.o_proj",
+    "language_model.model.layers.26.mlp.gate_proj",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.v_proj",
+    "language_model.model.layers.10.mlp.up_proj",
+    "language_model.model.layers.1.self_attn.v_proj",
+    "language_model.model.layers.6.mlp.up_proj",
+    "language_model.model.layers.25.mlp.up_proj",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.v_proj",
+    "language_model.model.layers.9.self_attn.k_proj",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.k_proj",
+    "language_model.model.layers.17.self_attn.q_proj",
+    "language_model.model.layers.4.self_attn.o_proj",
+    "language_model.model.layers.21.self_attn.o_proj",
+    "language_model.model.layers.8.self_attn.q_proj",
+    "language_model.model.layers.6.self_attn.q_proj",
+    "vision_tower.vision_model.encoder.layers.23.mlp.fc1",
+    "language_model.model.layers.28.mlp.up_proj",
+    "vision_tower.vision_model.encoder.layers.1.mlp.fc1",
+    "language_model.model.layers.17.self_attn.o_proj",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.v_proj",
     "vision_tower.vision_model.encoder.layers.21.self_attn.v_proj",
-    "language_model.model.layers.14.self_attn.v_proj",
-    "vision_tower.vision_model.encoder.layers.4.self_attn.k_proj",
-    "vision_tower.vision_model.encoder.layers.23.mlp.fc2",
-    "language_model.model.layers.21.mlp.up_proj",
-    "language_model.model.layers.26.mlp.up_proj",
-    "language_model.model.layers.5.mlp.gate_proj",
-    "vision_tower.vision_model.encoder.layers.14.self_attn.out_proj",
+    "language_model.model.layers.31.self_attn.v_proj",
+    "language_model.model.layers.26.self_attn.k_proj",
+    "language_model.model.layers.21.self_attn.q_proj",
+    "vision_tower.vision_model.encoder.layers.13.mlp.fc1",
+    "language_model.model.layers.15.self_attn.o_proj",
+    "vision_tower.vision_model.encoder.layers.21.mlp.fc1",
+    "language_model.model.layers.28.self_attn.v_proj",
+    "language_model.model.layers.6.mlp.down_proj",
+    "language_model.model.layers.25.self_attn.k_proj",
+    "language_model.model.layers.14.self_attn.q_proj",
+    "language_model.model.layers.11.mlp.gate_proj",
     "language_model.model.layers.2.mlp.down_proj",
+    "language_model.model.layers.31.mlp.up_proj",
+    "language_model.model.layers.12.mlp.down_proj",
+    "language_model.model.layers.19.mlp.up_proj",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.out_proj",
+    "language_model.model.layers.7.mlp.down_proj",
+    "vision_tower.vision_model.encoder.layers.4.mlp.fc1",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.v_proj",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.k_proj",
+    "language_model.model.layers.0.mlp.down_proj",
+    "vision_tower.vision_model.encoder.layers.22.mlp.fc1",
+    "language_model.model.layers.4.self_attn.v_proj",
+    "language_model.model.layers.15.self_attn.q_proj",
+    "language_model.model.layers.13.self_attn.v_proj",
+    "language_model.model.layers.6.mlp.gate_proj",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.out_proj",
     "vision_tower.vision_model.encoder.layers.10.mlp.fc1",
-    "vision_tower.vision_model.encoder.layers.19.self_attn.q_proj",
-    "vision_tower.vision_model.encoder.layers.1.self_attn.out_proj",
-    "language_model.model.layers.17.mlp.gate_proj",
-    "language_model.model.layers.25.self_attn.q_proj",
-    "language_model.model.layers.15.mlp.down_proj",
+    "language_model.model.layers.30.mlp.gate_proj",
+    "vision_tower.vision_model.encoder.layers.7.mlp.fc1",
+    "language_model.model.layers.4.mlp.gate_proj",
+    "language_model.model.layers.0.self_attn.q_proj",
+    "language_model.model.layers.29.self_attn.q_proj",
+    "language_model.model.layers.2.self_attn.o_proj",
+    "language_model.model.layers.30.self_attn.q_proj",
+    "language_model.model.layers.11.self_attn.q_proj",
+    "language_model.model.layers.31.self_attn.q_proj",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.q_proj",
+    "language_model.model.layers.5.mlp.down_proj",
+    "language_model.model.layers.20.mlp.gate_proj",
+    "language_model.model.layers.7.self_attn.k_proj",
+    "language_model.model.layers.23.self_attn.k_proj",
+    "language_model.model.layers.25.self_attn.o_proj",
+    "language_model.model.layers.16.mlp.up_proj",
     "language_model.model.layers.12.self_attn.k_proj",
-    "vision_tower.vision_model.encoder.layers.2.self_attn.v_proj",
-    "vision_tower.vision_model.encoder.layers.13.self_attn.v_proj",
-    "vision_tower.vision_model.encoder.layers.9.self_attn.out_proj",
-    "language_model.model.layers.0.mlp.up_proj",
-    "vision_tower.vision_model.encoder.layers.20.self_attn.v_proj",
-    "vision_tower.vision_model.encoder.layers.8.mlp.fc1",
+    "vision_tower.vision_model.encoder.layers.6.mlp.fc1",
+    "vision_tower.vision_model.encoder.layers.12.mlp.fc2",
+    "language_model.model.layers.12.self_attn.q_proj",
+    "language_model.model.layers.26.mlp.up_proj",
+    "language_model.model.layers.24.mlp.gate_proj",
     "vision_tower.vision_model.encoder.layers.22.self_attn.q_proj",
-    "vision_tower.vision_model.encoder.layers.1.mlp.fc2",
-    "language_model.model.layers.31.self_attn.k_proj",
-    "language_model.model.layers.14.mlp.down_proj",
-    "vision_tower.vision_model.encoder.layers.3.self_attn.k_proj",
-    "language_model.model.layers.19.mlp.up_proj",
-    "language_model.model.layers.12.self_attn.o_proj",
-    "language_model.model.layers.19.self_attn.q_proj",
-    "language_model.model.layers.20.self_attn.k_proj",
-    "vision_tower.vision_model.encoder.layers.15.self_attn.q_proj",
-    "vision_tower.vision_model.encoder.layers.16.self_attn.out_proj",
-    "language_model.model.layers.25.mlp.down_proj",
-    "vision_tower.vision_model.encoder.layers.5.self_attn.k_proj",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.v_proj",
+    "language_model.model.layers.20.mlp.up_proj",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.k_proj",
+    "language_model.model.layers.26.mlp.down_proj",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.k_proj",
+    "language_model.model.layers.20.mlp.down_proj",
+    "language_model.model.layers.18.mlp.gate_proj",
     "vision_tower.vision_model.encoder.layers.15.self_attn.v_proj",
-    "language_model.model.layers.6.self_attn.q_proj",
-    "language_model.model.layers.2.self_attn.v_proj",
-    "language_model.model.layers.15.mlp.up_proj",
-    "vision_tower.vision_model.encoder.layers.0.self_attn.v_proj",
-    "language_model.model.layers.30.mlp.down_proj"
+    "vision_tower.vision_model.encoder.layers.22.self_attn.out_proj",
+    "language_model.model.layers.16.self_attn.k_proj",
+    "language_model.model.layers.27.mlp.up_proj",
+    "language_model.model.layers.19.self_attn.q_proj",
+    "language_model.model.layers.22.self_attn.o_proj",
+    "language_model.model.layers.10.self_attn.k_proj",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.v_proj"
   ],
   "task_type": null,
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c0edcd345fe0b4696ee79b9ba03b3a7142620989d9bf323e3f1619b14f3387d
+oid sha256:7de1e190b738d55b726e6a3d7a5aa240a02b5c7cc7e44f2509e835008ba588db
 size 1594115680

chat_template.json

@@ -0,0 +1,3 @@
+{
+  "chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}{{ '<<SYS>>\n' + message['content'][0]['text'] + '\n<</SYS>>\n\n' }}{% elif message['role'] == 'user' %}{{ '[INST] ' }}{# Render all images first #}{% for content in message['content'] | selectattr('type', 'equalto', 'image') %}{{ '<image>\n' }}{% endfor %}{# Render all text next #}{% for content in message['content'] | selectattr('type', 'equalto', 'text') %}{{ content['text'] }}{% endfor %}{{' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' ' + message['content'][0]['text'] + '<\\s> '}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}"
+}

config.json

@@ -0,0 +1,81 @@
+{
+  "_name_or_path": "llava-hf/llava-v1.6-mistral-7b-hf",
+  "architectures": [
+    "LlavaNextForConditionalGeneration"
+  ],
+  "ignore_index": -100,
+  "image_grid_pinpoints": [
+    [
+      336,
+      672
+    ],
+    [
+      672,
+      336
+    ],
+    [
+      672,
+      672
+    ],
+    [
+      1008,
+      336
+    ],
+    [
+      336,
+      1008
+    ]
+  ],
+  "image_token_index": 32000,
+  "model_type": "llava_next",
+  "projector_hidden_act": "gelu",
+  "quantization_config": {
+    "_load_in_4bit": true,
+    "_load_in_8bit": false,
+    "bnb_4bit_compute_dtype": "float16",
+    "bnb_4bit_quant_storage": "uint8",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": false,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
+  "text_config": {
+    "_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
+    "architectures": [
+      "MistralForCausalLM"
+    ],
+    "head_dim": 128,
+    "intermediate_size": 14336,
+    "max_position_embeddings": 32768,
+    "model_type": "mistral",
+    "num_key_value_heads": 8,
+    "rms_norm_eps": 1e-05,
+    "rope_theta": 1000000.0,
+    "sliding_window": null,
+    "torch_dtype": "bfloat16",
+    "vocab_size": 32064
+  },
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "use_image_newline_parameter": true,
+  "vision_config": {
+    "hidden_size": 1024,
+    "image_size": 336,
+    "intermediate_size": 4096,
+    "model_type": "clip_vision_model",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 24,
+    "patch_size": 14,
+    "projection_dim": 768,
+    "vocab_size": 32000
+  },
+  "vision_feature_layer": -2,
+  "vision_feature_select_strategy": "default",
+  "vocab_size": 32064
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.44.2"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b39538ec9e985f0c1f114a7f7bedba81cdecf4b71bf8bb6d4b02b20cc916c81
+size 4978271376

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8359ef95a18a5441ade5849959e04577a932f4b0f933286404c17f6e0f35220
+size 1781503274

preprocessor_config.json

@@ -0,0 +1,52 @@
+{
+  "aspect_ratio_setting": "anyres",
+  "crop_size": {
+    "height": 336,
+    "width": 336
+  },
+  "do_center_crop": true,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_pad": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_grid_pinpoints": [
+    [
+      336,
+      672
+    ],
+    [
+      672,
+      336
+    ],
+    [
+      672,
+      672
+    ],
+    [
+      1008,
+      336
+    ],
+    [
+      336,
+      1008
+    ]
+  ],
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "LlavaNextImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "processor_class": "LlavaNextProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "shortest_edge": 336
+  }
+}

tokenizer.json

@@ -1,7 +1,14 @@
 {
   "version": "1.0",
   "truncation": null,
-  "padding": null,
+  "padding": {
+    "strategy": "BatchLongest",
+    "direction": "Left",
+    "pad_to_multiple_of": null,
+    "pad_id": 32001,
+    "pad_type_id": 0,
+    "pad_token": "<pad>"
+  },
   "added_tokens": [
     {
       "id": 0,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac4d7f82f0329045465c491d7044d2159c02851b478b4a340e048903c64ebac9
+oid sha256:95536db11ec18f1f69179abc2b1e3df9f560ccc9ba3eea01b09ed6f0c4d79f57
 size 5560