final

config.json

@@ -193,14 +193,24 @@
       "model.layers.8.mlp.gate",
       "model.layers.9.mlp.gate",
       "visual.blocks.15.mlp.gate_up_proj",
+      "visual.blocks.15.mlp.gate_proj",
+      "visual.blocks.15.mlp.up_proj",
       "visual.blocks.16.mlp.down_proj",
       "visual.blocks.16.mlp.gate_up_proj",
+      "visual.blocks.16.mlp.gate_proj",
+      "visual.blocks.16.mlp.up_proj",
       "visual.blocks.17.mlp.down_proj",
       "visual.blocks.17.mlp.gate_up_proj",
+      "visual.blocks.17.mlp.gate_proj",
+      "visual.blocks.17.mlp.up_proj",
       "visual.blocks.18.mlp.down_proj",
       "visual.blocks.18.mlp.gate_up_proj",
+      "visual.blocks.18.mlp.gate_proj",
+      "visual.blocks.18.mlp.up_proj",
       "visual.blocks.19.mlp.down_proj",
       "visual.blocks.19.mlp.gate_up_proj",
+      "visual.blocks.19.mlp.gate_proj",
+      "visual.blocks.19.mlp.up_proj",
       "visual.blocks.20.mlp.down_proj",
       "visual.post_layernorm",
       "model.layers.40.mlp.gate.e_score_correction_bias",
@@ -241,25 +251,43 @@
       "model.layers.28.self_attn.v_proj.bias",
       "model.layers.29.self_attn.v_proj.bias",
       "visual.blocks.11.mlp.gate_up_proj",
+      "visual.blocks.11.mlp.gate_proj",
+      "visual.blocks.11.mlp.up_proj",
       "visual.blocks.5.mlp.gate_up_proj",
+      "visual.blocks.5.mlp.gate_proj",
+      "visual.blocks.5.mlp.up_proj",
       "visual.blocks.5.norm1",
       "visual.blocks.6.mlp.gate_up_proj",
+      "visual.blocks.6.mlp.gate_proj",
+      "visual.blocks.6.mlp.up_proj",
       "visual.blocks.7.mlp.gate_up_proj",
+      "visual.blocks.7.mlp.gate_proj",
+      "visual.blocks.7.mlp.up_proj",
       "visual.blocks.8.mlp.gate_up_proj",
+      "visual.blocks.8.mlp.gate_proj",
+      "visual.blocks.8.mlp.up_proj",
       "visual.blocks.9.mlp.gate_up_proj",
+      "visual.blocks.9.mlp.gate_proj",
+      "visual.blocks.9.mlp.up_proj",
       "model.layers.22.mlp.gate.e_score_correction_bias",
       "model.layers.10.mlp.gate.e_score_correction_bias",
       "model.layers.11.mlp.gate.e_score_correction_bias",
       "model.layers.12.mlp.gate.e_score_correction_bias",
       "visual.blocks.12.mlp.down_proj",
       "visual.blocks.12.mlp.gate_up_proj",
+      "visual.blocks.12.mlp.gate_proj",
+      "visual.blocks.12.mlp.up_proj",
       "model.layers.14.mlp.gate.e_score_correction_bias",
       "model.layers.13.mlp.gate.e_score_correction_bias",
       "model.layers.15.mlp.gate.e_score_correction_bias",
       "visual.blocks.13.mlp.down_proj",
       "visual.blocks.13.mlp.gate_up_proj",
+      "visual.blocks.13.mlp.gate_proj",
+      "visual.blocks.13.mlp.up_proj",
       "visual.blocks.14.mlp.down_proj",
       "visual.blocks.14.mlp.gate_up_proj",
+      "visual.blocks.14.mlp.gate_proj",
+      "visual.blocks.14.mlp.up_proj",
       "visual.blocks.15.mlp.down_proj",
       "model.embed_tokens",
       "model.layers.10.input_layernorm",
@@ -377,14 +405,24 @@
       "visual.blocks.8.norm2",
       "visual.blocks.9.norm2",
       "visual.blocks.20.mlp.gate_up_proj",
+      "visual.blocks.20.mlp.gate_proj",
+      "visual.blocks.20.mlp.up_proj",
       "visual.blocks.21.mlp.down_proj",
       "visual.blocks.21.mlp.gate_up_proj",
+      "visual.blocks.21.mlp.gate_proj",
+      "visual.blocks.21.mlp.up_proj",
       "visual.blocks.22.mlp.down_proj",
       "visual.blocks.22.mlp.gate_up_proj",
+      "visual.blocks.22.mlp.gate_proj",
+      "visual.blocks.22.mlp.up_proj",
       "visual.blocks.23.mlp.down_proj",
       "visual.blocks.23.mlp.gate_up_proj",
+      "visual.blocks.23.mlp.gate_proj",
+      "visual.blocks.23.mlp.up_proj",
       "visual.blocks.10.mlp.down_proj",
       "visual.blocks.10.mlp.gate_up_proj",
+      "visual.blocks.10.mlp.gate_proj",
+      "visual.blocks.10.mlp.up_proj",
       "visual.blocks.11.mlp.down_proj",
       "visual.embeddings.position_embedding",
       "model.layers.15.mlp.gate",
@@ -497,14 +535,24 @@
       "visual.post_conv_layernorm",
       "visual.blocks.0.mlp.down_proj",
       "visual.blocks.0.mlp.gate_up_proj",
+      "visual.blocks.0.mlp.gate_proj",
+      "visual.blocks.0.mlp.up_proj",
       "visual.blocks.1.mlp.down_proj",
       "visual.blocks.1.mlp.gate_up_proj",
+      "visual.blocks.1.mlp.gate_proj",
+      "visual.blocks.1.mlp.up_proj",
       "visual.blocks.2.mlp.down_proj",
       "visual.blocks.2.mlp.gate_up_proj",
+      "visual.blocks.2.mlp.gate_proj",
+      "visual.blocks.2.mlp.up_proj",
       "visual.blocks.3.mlp.down_proj",
       "visual.blocks.3.mlp.gate_up_proj",
+      "visual.blocks.3.mlp.gate_proj",
+      "visual.blocks.3.mlp.up_proj",
       "visual.blocks.4.mlp.down_proj",
       "visual.blocks.4.mlp.gate_up_proj",
+      "visual.blocks.4.mlp.gate_proj",
+      "visual.blocks.4.mlp.up_proj",
       "visual.merger.post_projection_norm",
       "visual.blocks.12.attn.proj",
       "visual.blocks.13.attn.proj",
@@ -599,4 +647,4 @@
     "quant_method": "compressed-tensors",
     "quantization_status": "compressed"
   }
-}
+}