Upload folder using huggingface_hub

chat_template.jinja

@@ -340,8 +340,5 @@
 {%- if add_generation_prompt -%}
     {%- if ns.prev_message_type != 'tool_response' and ns.prev_message_type != 'tool_call' -%}
         {{- '<|turn>model\n' -}}
-        {%- if not enable_thinking | default(false) -%}
-            {{- '<|channel>thought\n<channel|>' -}}
-        {%- endif -%}
     {%- endif -%}
-{%- endif -%}
+{%- endif -%}

config.json

@@ -60,6 +60,7 @@
     "quantization": {
         "group_size": 64,
         "bits": 8,
+        "mode": "affine",
         "language_model.model.embed_tokens": {
             "group_size": 64,
             "bits": 8
@@ -84,11 +85,11 @@
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.0.mlp.up_proj": {
+        "language_model.model.layers.0.mlp.down_proj": {
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.0.mlp.down_proj": {
+        "language_model.model.layers.0.mlp.up_proj": {
             "group_size": 64,
             "bits": 8
         },
@@ -120,11 +121,11 @@
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.1.mlp.up_proj": {
+        "language_model.model.layers.1.mlp.down_proj": {
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.1.mlp.down_proj": {
+        "language_model.model.layers.1.mlp.up_proj": {
             "group_size": 64,
             "bits": 8
         },
@@ -156,11 +157,11 @@
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.2.mlp.up_proj": {
+        "language_model.model.layers.2.mlp.down_proj": {
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.2.mlp.down_proj": {
+        "language_model.model.layers.2.mlp.up_proj": {
             "group_size": 64,
             "bits": 8
         },
@@ -192,11 +193,11 @@
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.3.mlp.up_proj": {
+        "language_model.model.layers.3.mlp.down_proj": {
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.3.mlp.down_proj": {
+        "language_model.model.layers.3.mlp.up_proj": {
             "group_size": 64,
             "bits": 8
         },
@@ -228,11 +229,11 @@
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.4.mlp.up_proj": {
+        "language_model.model.layers.4.mlp.down_proj": {
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.4.mlp.down_proj": {
+        "language_model.model.layers.4.mlp.up_proj": {
             "group_size": 64,
             "bits": 8
         },
@@ -264,11 +265,11 @@
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.5.mlp.up_proj": {
+        "language_model.model.layers.5.mlp.down_proj": {
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.5.mlp.down_proj": {
+        "language_model.model.layers.5.mlp.up_proj": {
             "group_size": 64,
             "bits": 8
         },
@@ -300,11 +301,11 @@
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.6.mlp.up_proj": {
+        "language_model.model.layers.6.mlp.down_proj": {
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.6.mlp.down_proj": {
+        "language_model.model.layers.6.mlp.up_proj": {
             "group_size": 64,
             "bits": 8
         },
@@ -336,11 +337,11 @@
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.7.mlp.up_proj": {
+        "language_model.model.layers.7.mlp.down_proj": {
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.7.mlp.down_proj": {
+        "language_model.model.layers.7.mlp.up_proj": {
             "group_size": 64,
             "bits": 8
         },
@@ -372,11 +373,11 @@
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.8.mlp.up_proj": {
+        "language_model.model.layers.8.mlp.down_proj": {
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.8.mlp.down_proj": {
+        "language_model.model.layers.8.mlp.up_proj": {
             "group_size": 64,
             "bits": 8
         },
@@ -408,11 +409,11 @@
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.9.mlp.up_proj": {
+        "language_model.model.layers.9.mlp.down_proj": {
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.9.mlp.down_proj": {
+        "language_model.model.layers.9.mlp.up_proj": {
             "group_size": 64,
             "bits": 8
         },
@@ -444,11 +445,11 @@
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.10.mlp.up_proj": {
+        "language_model.model.layers.10.mlp.down_proj": {
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.10.mlp.down_proj": {
+        "language_model.model.layers.10.mlp.up_proj": {
             "group_size": 64,
             "bits": 8
         },
@@ -480,11 +481,11 @@
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.11.mlp.up_proj": {
+        "language_model.model.layers.11.mlp.down_proj": {
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.11.mlp.down_proj": {
+        "language_model.model.layers.11.mlp.up_proj": {
             "group_size": 64,
             "bits": 8
         },
@@ -516,11 +517,11 @@
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.12.mlp.up_proj": {
+        "language_model.model.layers.12.mlp.down_proj": {
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.12.mlp.down_proj": {
+        "language_model.model.layers.12.mlp.up_proj": {
             "group_size": 64,
             "bits": 8
         },
@@ -552,11 +553,11 @@
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.13.mlp.up_proj": {
+        "language_model.model.layers.13.mlp.down_proj": {
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.13.mlp.down_proj": {
+        "language_model.model.layers.13.mlp.up_proj": {
             "group_size": 64,
             "bits": 8
         },
@@ -588,11 +589,11 @@
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.14.mlp.up_proj": {
+        "language_model.model.layers.14.mlp.down_proj": {
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.14.mlp.down_proj": {
+        "language_model.model.layers.14.mlp.up_proj": {
             "group_size": 64,
             "bits": 8
         },
@@ -624,11 +625,11 @@
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.15.mlp.up_proj": {
+        "language_model.model.layers.15.mlp.down_proj": {
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.15.mlp.down_proj": {
+        "language_model.model.layers.15.mlp.up_proj": {
             "group_size": 64,
             "bits": 8
         },
@@ -660,11 +661,11 @@
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.16.mlp.up_proj": {
+        "language_model.model.layers.16.mlp.down_proj": {
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.16.mlp.down_proj": {
+        "language_model.model.layers.16.mlp.up_proj": {
             "group_size": 64,
             "bits": 8
         },
@@ -696,11 +697,11 @@
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.17.mlp.up_proj": {
+        "language_model.model.layers.17.mlp.down_proj": {
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.17.mlp.down_proj": {
+        "language_model.model.layers.17.mlp.up_proj": {
             "group_size": 64,
             "bits": 8
         },
@@ -732,11 +733,11 @@
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.18.mlp.up_proj": {
+        "language_model.model.layers.18.mlp.down_proj": {
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.18.mlp.down_proj": {
+        "language_model.model.layers.18.mlp.up_proj": {
             "group_size": 64,
             "bits": 8
         },
@@ -768,11 +769,11 @@
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.19.mlp.up_proj": {
+        "language_model.model.layers.19.mlp.down_proj": {
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.19.mlp.down_proj": {
+        "language_model.model.layers.19.mlp.up_proj": {
             "group_size": 64,
             "bits": 8
         },
@@ -804,11 +805,11 @@
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.20.mlp.up_proj": {
+        "language_model.model.layers.20.mlp.down_proj": {
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.20.mlp.down_proj": {
+        "language_model.model.layers.20.mlp.up_proj": {
             "group_size": 64,
             "bits": 8
         },
@@ -840,11 +841,11 @@
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.21.mlp.up_proj": {
+        "language_model.model.layers.21.mlp.down_proj": {
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.21.mlp.down_proj": {
+        "language_model.model.layers.21.mlp.up_proj": {
             "group_size": 64,
             "bits": 8
         },
@@ -876,11 +877,11 @@
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.22.mlp.up_proj": {
+        "language_model.model.layers.22.mlp.down_proj": {
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.22.mlp.down_proj": {
+        "language_model.model.layers.22.mlp.up_proj": {
             "group_size": 64,
             "bits": 8
         },
@@ -912,11 +913,11 @@
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.23.mlp.up_proj": {
+        "language_model.model.layers.23.mlp.down_proj": {
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.23.mlp.down_proj": {
+        "language_model.model.layers.23.mlp.up_proj": {
             "group_size": 64,
             "bits": 8
         },
@@ -948,11 +949,11 @@
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.24.mlp.up_proj": {
+        "language_model.model.layers.24.mlp.down_proj": {
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.24.mlp.down_proj": {
+        "language_model.model.layers.24.mlp.up_proj": {
             "group_size": 64,
             "bits": 8
         },
@@ -984,11 +985,11 @@
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.25.mlp.up_proj": {
+        "language_model.model.layers.25.mlp.down_proj": {
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.25.mlp.down_proj": {
+        "language_model.model.layers.25.mlp.up_proj": {
             "group_size": 64,
             "bits": 8
         },
@@ -1020,11 +1021,11 @@
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.26.mlp.up_proj": {
+        "language_model.model.layers.26.mlp.down_proj": {
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.26.mlp.down_proj": {
+        "language_model.model.layers.26.mlp.up_proj": {
             "group_size": 64,
             "bits": 8
         },
@@ -1056,11 +1057,11 @@
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.27.mlp.up_proj": {
+        "language_model.model.layers.27.mlp.down_proj": {
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.27.mlp.down_proj": {
+        "language_model.model.layers.27.mlp.up_proj": {
             "group_size": 64,
             "bits": 8
         },
@@ -1092,11 +1093,11 @@
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.28.mlp.up_proj": {
+        "language_model.model.layers.28.mlp.down_proj": {
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.28.mlp.down_proj": {
+        "language_model.model.layers.28.mlp.up_proj": {
             "group_size": 64,
             "bits": 8
         },
@@ -1128,11 +1129,11 @@
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.29.mlp.up_proj": {
+        "language_model.model.layers.29.mlp.down_proj": {
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.29.mlp.down_proj": {
+        "language_model.model.layers.29.mlp.up_proj": {
             "group_size": 64,
             "bits": 8
         },
@@ -1164,11 +1165,11 @@
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.30.mlp.up_proj": {
+        "language_model.model.layers.30.mlp.down_proj": {
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.30.mlp.down_proj": {
+        "language_model.model.layers.30.mlp.up_proj": {
             "group_size": 64,
             "bits": 8
         },
@@ -1200,11 +1201,11 @@
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.31.mlp.up_proj": {
+        "language_model.model.layers.31.mlp.down_proj": {
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.31.mlp.down_proj": {
+        "language_model.model.layers.31.mlp.up_proj": {
             "group_size": 64,
             "bits": 8
         },
@@ -1236,11 +1237,11 @@
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.32.mlp.up_proj": {
+        "language_model.model.layers.32.mlp.down_proj": {
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.32.mlp.down_proj": {
+        "language_model.model.layers.32.mlp.up_proj": {
             "group_size": 64,
             "bits": 8
         },
@@ -1272,11 +1273,11 @@
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.33.mlp.up_proj": {
+        "language_model.model.layers.33.mlp.down_proj": {
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.33.mlp.down_proj": {
+        "language_model.model.layers.33.mlp.up_proj": {
             "group_size": 64,
             "bits": 8
         },
@@ -1308,11 +1309,11 @@
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.34.mlp.up_proj": {
+        "language_model.model.layers.34.mlp.down_proj": {
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.34.mlp.down_proj": {
+        "language_model.model.layers.34.mlp.up_proj": {
             "group_size": 64,
             "bits": 8
         },
@@ -1344,11 +1345,11 @@
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.35.mlp.up_proj": {
+        "language_model.model.layers.35.mlp.down_proj": {
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.35.mlp.down_proj": {
+        "language_model.model.layers.35.mlp.up_proj": {
             "group_size": 64,
             "bits": 8
         },
@@ -1380,11 +1381,11 @@
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.36.mlp.up_proj": {
+        "language_model.model.layers.36.mlp.down_proj": {
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.36.mlp.down_proj": {
+        "language_model.model.layers.36.mlp.up_proj": {
             "group_size": 64,
             "bits": 8
         },
@@ -1416,11 +1417,11 @@
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.37.mlp.up_proj": {
+        "language_model.model.layers.37.mlp.down_proj": {
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.37.mlp.down_proj": {
+        "language_model.model.layers.37.mlp.up_proj": {
             "group_size": 64,
             "bits": 8
         },
@@ -1452,11 +1453,11 @@
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.38.mlp.up_proj": {
+        "language_model.model.layers.38.mlp.down_proj": {
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.38.mlp.down_proj": {
+        "language_model.model.layers.38.mlp.up_proj": {
             "group_size": 64,
             "bits": 8
         },
@@ -1488,11 +1489,11 @@
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.39.mlp.up_proj": {
+        "language_model.model.layers.39.mlp.down_proj": {
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.39.mlp.down_proj": {
+        "language_model.model.layers.39.mlp.up_proj": {
             "group_size": 64,
             "bits": 8
         },
@@ -1524,11 +1525,11 @@
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.40.mlp.up_proj": {
+        "language_model.model.layers.40.mlp.down_proj": {
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.40.mlp.down_proj": {
+        "language_model.model.layers.40.mlp.up_proj": {
             "group_size": 64,
             "bits": 8
         },
@@ -1560,11 +1561,11 @@
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.41.mlp.up_proj": {
+        "language_model.model.layers.41.mlp.down_proj": {
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.41.mlp.down_proj": {
+        "language_model.model.layers.41.mlp.up_proj": {
             "group_size": 64,
             "bits": 8
         },
@@ -1579,15 +1580,12 @@
         "language_model.model.embed_tokens_per_layer": {
             "group_size": 64,
             "bits": 8
-        },
-        "language_model.model.per_layer_model_projection": {
-            "group_size": 64,
-            "bits": 8
         }
     },
     "quantization_config": {
         "group_size": 64,
         "bits": 8,
+        "mode": "affine",
         "language_model.model.embed_tokens": {
             "group_size": 64,
             "bits": 8
@@ -1612,11 +1610,11 @@
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.0.mlp.up_proj": {
+        "language_model.model.layers.0.mlp.down_proj": {
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.0.mlp.down_proj": {
+        "language_model.model.layers.0.mlp.up_proj": {
             "group_size": 64,
             "bits": 8
         },
@@ -1648,11 +1646,11 @@
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.1.mlp.up_proj": {
+        "language_model.model.layers.1.mlp.down_proj": {
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.1.mlp.down_proj": {
+        "language_model.model.layers.1.mlp.up_proj": {
             "group_size": 64,
             "bits": 8
         },
@@ -1684,11 +1682,11 @@
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.2.mlp.up_proj": {
+        "language_model.model.layers.2.mlp.down_proj": {
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.2.mlp.down_proj": {
+        "language_model.model.layers.2.mlp.up_proj": {
             "group_size": 64,
             "bits": 8
         },
@@ -1720,11 +1718,11 @@
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.3.mlp.up_proj": {
+        "language_model.model.layers.3.mlp.down_proj": {
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.3.mlp.down_proj": {
+        "language_model.model.layers.3.mlp.up_proj": {
             "group_size": 64,
             "bits": 8
         },
@@ -1756,11 +1754,11 @@
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.4.mlp.up_proj": {
+        "language_model.model.layers.4.mlp.down_proj": {
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.4.mlp.down_proj": {
+        "language_model.model.layers.4.mlp.up_proj": {
             "group_size": 64,
             "bits": 8
         },
@@ -1792,11 +1790,11 @@
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.5.mlp.up_proj": {
+        "language_model.model.layers.5.mlp.down_proj": {
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.5.mlp.down_proj": {
+        "language_model.model.layers.5.mlp.up_proj": {
             "group_size": 64,
             "bits": 8
         },
@@ -1828,11 +1826,11 @@
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.6.mlp.up_proj": {
+        "language_model.model.layers.6.mlp.down_proj": {
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.6.mlp.down_proj": {
+        "language_model.model.layers.6.mlp.up_proj": {
             "group_size": 64,
             "bits": 8
         },
@@ -1864,11 +1862,11 @@
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.7.mlp.up_proj": {
+        "language_model.model.layers.7.mlp.down_proj": {
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.7.mlp.down_proj": {
+        "language_model.model.layers.7.mlp.up_proj": {
             "group_size": 64,
             "bits": 8
         },
@@ -1900,11 +1898,11 @@
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.8.mlp.up_proj": {
+        "language_model.model.layers.8.mlp.down_proj": {
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.8.mlp.down_proj": {
+        "language_model.model.layers.8.mlp.up_proj": {
             "group_size": 64,
             "bits": 8
         },
@@ -1936,11 +1934,11 @@
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.9.mlp.up_proj": {
+        "language_model.model.layers.9.mlp.down_proj": {
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.9.mlp.down_proj": {
+        "language_model.model.layers.9.mlp.up_proj": {
             "group_size": 64,
             "bits": 8
         },
@@ -1972,11 +1970,11 @@
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.10.mlp.up_proj": {
+        "language_model.model.layers.10.mlp.down_proj": {
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.10.mlp.down_proj": {
+        "language_model.model.layers.10.mlp.up_proj": {
             "group_size": 64,
             "bits": 8
         },
@@ -2008,11 +2006,11 @@
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.11.mlp.up_proj": {
+        "language_model.model.layers.11.mlp.down_proj": {
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.11.mlp.down_proj": {
+        "language_model.model.layers.11.mlp.up_proj": {
             "group_size": 64,
             "bits": 8
         },
@@ -2044,11 +2042,11 @@
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.12.mlp.up_proj": {
+        "language_model.model.layers.12.mlp.down_proj": {
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.12.mlp.down_proj": {
+        "language_model.model.layers.12.mlp.up_proj": {
             "group_size": 64,
             "bits": 8
         },
@@ -2080,11 +2078,11 @@
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.13.mlp.up_proj": {
+        "language_model.model.layers.13.mlp.down_proj": {
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.13.mlp.down_proj": {
+        "language_model.model.layers.13.mlp.up_proj": {
             "group_size": 64,
             "bits": 8
         },
@@ -2116,11 +2114,11 @@
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.14.mlp.up_proj": {
+        "language_model.model.layers.14.mlp.down_proj": {
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.14.mlp.down_proj": {
+        "language_model.model.layers.14.mlp.up_proj": {
             "group_size": 64,
             "bits": 8
         },
@@ -2152,11 +2150,11 @@
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.15.mlp.up_proj": {
+        "language_model.model.layers.15.mlp.down_proj": {
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.15.mlp.down_proj": {
+        "language_model.model.layers.15.mlp.up_proj": {
             "group_size": 64,
             "bits": 8
         },
@@ -2188,11 +2186,11 @@
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.16.mlp.up_proj": {
+        "language_model.model.layers.16.mlp.down_proj": {
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.16.mlp.down_proj": {
+        "language_model.model.layers.16.mlp.up_proj": {
             "group_size": 64,
             "bits": 8
         },
@@ -2224,11 +2222,11 @@
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.17.mlp.up_proj": {
+        "language_model.model.layers.17.mlp.down_proj": {
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.17.mlp.down_proj": {
+        "language_model.model.layers.17.mlp.up_proj": {
             "group_size": 64,
             "bits": 8
         },
@@ -2260,11 +2258,11 @@
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.18.mlp.up_proj": {
+        "language_model.model.layers.18.mlp.down_proj": {
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.18.mlp.down_proj": {
+        "language_model.model.layers.18.mlp.up_proj": {
             "group_size": 64,
             "bits": 8
         },
@@ -2296,11 +2294,11 @@
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.19.mlp.up_proj": {
+        "language_model.model.layers.19.mlp.down_proj": {
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.19.mlp.down_proj": {
+        "language_model.model.layers.19.mlp.up_proj": {
             "group_size": 64,
             "bits": 8
         },
@@ -2332,11 +2330,11 @@
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.20.mlp.up_proj": {
+        "language_model.model.layers.20.mlp.down_proj": {
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.20.mlp.down_proj": {
+        "language_model.model.layers.20.mlp.up_proj": {
             "group_size": 64,
             "bits": 8
         },
@@ -2368,11 +2366,11 @@
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.21.mlp.up_proj": {
+        "language_model.model.layers.21.mlp.down_proj": {
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.21.mlp.down_proj": {
+        "language_model.model.layers.21.mlp.up_proj": {
             "group_size": 64,
             "bits": 8
         },
@@ -2404,11 +2402,11 @@
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.22.mlp.up_proj": {
+        "language_model.model.layers.22.mlp.down_proj": {
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.22.mlp.down_proj": {
+        "language_model.model.layers.22.mlp.up_proj": {
             "group_size": 64,
             "bits": 8
         },
@@ -2440,11 +2438,11 @@
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.23.mlp.up_proj": {
+        "language_model.model.layers.23.mlp.down_proj": {
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.23.mlp.down_proj": {
+        "language_model.model.layers.23.mlp.up_proj": {
             "group_size": 64,
             "bits": 8
         },
@@ -2476,11 +2474,11 @@
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.24.mlp.up_proj": {
+        "language_model.model.layers.24.mlp.down_proj": {
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.24.mlp.down_proj": {
+        "language_model.model.layers.24.mlp.up_proj": {
             "group_size": 64,
             "bits": 8
         },
@@ -2512,11 +2510,11 @@
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.25.mlp.up_proj": {
+        "language_model.model.layers.25.mlp.down_proj": {
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.25.mlp.down_proj": {
+        "language_model.model.layers.25.mlp.up_proj": {
             "group_size": 64,
             "bits": 8
         },
@@ -2548,11 +2546,11 @@
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.26.mlp.up_proj": {
+        "language_model.model.layers.26.mlp.down_proj": {
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.26.mlp.down_proj": {
+        "language_model.model.layers.26.mlp.up_proj": {
             "group_size": 64,
             "bits": 8
         },
@@ -2584,11 +2582,11 @@
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.27.mlp.up_proj": {
+        "language_model.model.layers.27.mlp.down_proj": {
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.27.mlp.down_proj": {
+        "language_model.model.layers.27.mlp.up_proj": {
             "group_size": 64,
             "bits": 8
         },
@@ -2620,11 +2618,11 @@
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.28.mlp.up_proj": {
+        "language_model.model.layers.28.mlp.down_proj": {
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.28.mlp.down_proj": {
+        "language_model.model.layers.28.mlp.up_proj": {
             "group_size": 64,
             "bits": 8
         },
@@ -2656,11 +2654,11 @@
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.29.mlp.up_proj": {
+        "language_model.model.layers.29.mlp.down_proj": {
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.29.mlp.down_proj": {
+        "language_model.model.layers.29.mlp.up_proj": {
             "group_size": 64,
             "bits": 8
         },
@@ -2692,11 +2690,11 @@
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.30.mlp.up_proj": {
+        "language_model.model.layers.30.mlp.down_proj": {
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.30.mlp.down_proj": {
+        "language_model.model.layers.30.mlp.up_proj": {
             "group_size": 64,
             "bits": 8
         },
@@ -2728,11 +2726,11 @@
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.31.mlp.up_proj": {
+        "language_model.model.layers.31.mlp.down_proj": {
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.31.mlp.down_proj": {
+        "language_model.model.layers.31.mlp.up_proj": {
             "group_size": 64,
             "bits": 8
         },
@@ -2764,11 +2762,11 @@
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.32.mlp.up_proj": {
+        "language_model.model.layers.32.mlp.down_proj": {
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.32.mlp.down_proj": {
+        "language_model.model.layers.32.mlp.up_proj": {
             "group_size": 64,
             "bits": 8
         },
@@ -2800,11 +2798,11 @@
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.33.mlp.up_proj": {
+        "language_model.model.layers.33.mlp.down_proj": {
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.33.mlp.down_proj": {
+        "language_model.model.layers.33.mlp.up_proj": {
             "group_size": 64,
             "bits": 8
         },
@@ -2836,11 +2834,11 @@
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.34.mlp.up_proj": {
+        "language_model.model.layers.34.mlp.down_proj": {
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.34.mlp.down_proj": {
+        "language_model.model.layers.34.mlp.up_proj": {
             "group_size": 64,
             "bits": 8
         },
@@ -2872,11 +2870,11 @@
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.35.mlp.up_proj": {
+        "language_model.model.layers.35.mlp.down_proj": {
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.35.mlp.down_proj": {
+        "language_model.model.layers.35.mlp.up_proj": {
             "group_size": 64,
             "bits": 8
         },
@@ -2908,11 +2906,11 @@
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.36.mlp.up_proj": {
+        "language_model.model.layers.36.mlp.down_proj": {
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.36.mlp.down_proj": {
+        "language_model.model.layers.36.mlp.up_proj": {
             "group_size": 64,
             "bits": 8
         },
@@ -2944,11 +2942,11 @@
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.37.mlp.up_proj": {
+        "language_model.model.layers.37.mlp.down_proj": {
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.37.mlp.down_proj": {
+        "language_model.model.layers.37.mlp.up_proj": {
             "group_size": 64,
             "bits": 8
         },
@@ -2980,11 +2978,11 @@
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.38.mlp.up_proj": {
+        "language_model.model.layers.38.mlp.down_proj": {
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.38.mlp.down_proj": {
+        "language_model.model.layers.38.mlp.up_proj": {
             "group_size": 64,
             "bits": 8
         },
@@ -3016,11 +3014,11 @@
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.39.mlp.up_proj": {
+        "language_model.model.layers.39.mlp.down_proj": {
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.39.mlp.down_proj": {
+        "language_model.model.layers.39.mlp.up_proj": {
             "group_size": 64,
             "bits": 8
         },
@@ -3052,11 +3050,11 @@
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.40.mlp.up_proj": {
+        "language_model.model.layers.40.mlp.down_proj": {
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.40.mlp.down_proj": {
+        "language_model.model.layers.40.mlp.up_proj": {
             "group_size": 64,
             "bits": 8
         },
@@ -3088,11 +3086,11 @@
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.41.mlp.up_proj": {
+        "language_model.model.layers.41.mlp.down_proj": {
             "group_size": 64,
             "bits": 8
         },
-        "language_model.model.layers.41.mlp.down_proj": {
+        "language_model.model.layers.41.mlp.up_proj": {
             "group_size": 64,
             "bits": 8
         },
@@ -3107,10 +3105,6 @@
         "language_model.model.embed_tokens_per_layer": {
             "group_size": 64,
             "bits": 8
-        },
-        "language_model.model.per_layer_model_projection": {
-            "group_size": 64,
-            "bits": 8
         }
     },
     "text_config": {
@@ -3207,5 +3201,48 @@
     "tie_word_embeddings": true,
     "transformers_version": "5.5.0.dev0",
     "video_token_id": 258884,
+    "vision_config": {
+        "_name_or_path": "",
+        "architectures": null,
+        "attention_bias": false,
+        "attention_dropout": 0.0,
+        "chunk_size_feed_forward": 0,
+        "default_output_length": 280,
+        "dtype": "bfloat16",
+        "global_head_dim": 64,
+        "head_dim": 64,
+        "hidden_activation": "gelu_pytorch_tanh",
+        "hidden_size": 768,
+        "id2label": {
+            "0": "LABEL_0",
+            "1": "LABEL_1"
+        },
+        "initializer_range": 0.02,
+        "intermediate_size": 3072,
+        "is_encoder_decoder": false,
+        "label2id": {
+            "LABEL_0": 0,
+            "LABEL_1": 1
+        },
+        "max_position_embeddings": 131072,
+        "model_type": "gemma4_vision",
+        "num_attention_heads": 12,
+        "num_hidden_layers": 16,
+        "num_key_value_heads": 12,
+        "output_attentions": false,
+        "output_hidden_states": false,
+        "patch_size": 16,
+        "pooling_kernel_size": 3,
+        "position_embedding_size": 10240,
+        "problem_type": null,
+        "return_dict": true,
+        "rms_norm_eps": 1e-06,
+        "rope_parameters": {
+            "rope_theta": 100.0,
+            "rope_type": "default"
+        },
+        "standardize": false,
+        "use_clipped_linears": true
+    },
     "vision_soft_tokens_per_image": 280
 }

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14dce6f7bb00e6a2806aed8825b08c93a131d501b79ed2f845798647b41257ff
-size 4964690708
+oid sha256:ba98954a0dbc93fb857edd85792ac03d986cac6e6d3e830b48cb4ea929ca6d76
+size 4964690704

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9fcd2f2cfcfb7cd025351071a80af947c9249c1a112b7ffc32163bfab9507f99
-size 3023979920
+oid sha256:54e952e5cc84eaea341fb8ce4bd10609751ac90ef2f6be673f9ecc6375cfc31c
+size 4006137753

processor_config.json

@@ -0,0 +1,42 @@
+{
+  "audio_seq_length": 750,
+  "image_processor": {
+    "do_convert_rgb": true,
+    "do_normalize": false,
+    "do_rescale": true,
+    "do_resize": true,
+    "image_mean": [
+      0.0,
+      0.0,
+      0.0
+    ],
+    "image_processor_type": "Gemma4ImageProcessor",
+    "image_seq_length": 280,
+    "image_std": [
+      1.0,
+      1.0,
+      1.0
+    ],
+    "max_soft_tokens": 280,
+    "patch_size": 16,
+    "pooling_kernel_size": 3,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "size": {
+      "height": 224,
+      "width": 224
+    }
+  },
+  "image_seq_length": 280,
+  "processor_class": "Gemma4Processor",
+  "feature_extractor": {
+    "feature_extractor_type": "Gemma4AudioFeatureExtractor",
+    "sampling_rate": 16000,
+    "num_mel_filters": 128,
+    "fft_length": 1024,
+    "hop_length": 160,
+    "chunk_duration": 8.0,
+    "overlap_duration": 1.0
+  },
+  "audio_ms_per_token": 40
+}

tokenizer_config.json

@@ -17,50 +17,71 @@
     "<|video|>"
   ],
   "image_token": "<|image|>",
+  "is_local": true,
   "mask_token": "<mask>",
   "model_max_length": 1000000000000000019884624838656,
+  "model_specific_special_tokens": {
+    "audio_token": "<|audio|>",
+    "boa_token": "<|audio>",
+    "boi_token": "<|image>",
+    "eoa_token": "<audio|>",
+    "eoc_token": "<channel|>",
+    "eoi_token": "<image|>",
+    "eot_token": "<turn|>",
+    "escape_token": "<|\"|>",
+    "etc_token": "<tool_call|>",
+    "etd_token": "<tool|>",
+    "etr_token": "<tool_response|>",
+    "image_token": "<|image|>",
+    "soc_token": "<|channel>",
+    "sot_token": "<|turn>",
+    "stc_token": "<|tool_call>",
+    "std_token": "<|tool>",
+    "str_token": "<|tool_response>",
+    "think_token": "<|think|>"
+  },
   "pad_token": "<pad>",
   "padding_side": "left",
   "processor_class": "Gemma4Processor",
   "response_schema": {
-    "type": "object",
     "properties": {
+      "content": {
+        "type": "string"
+      },
       "role": {
         "const": "assistant"
       },
       "thinking": {
         "type": "string"
       },
-      "content": {
-        "type": "string"
-      },
       "tool_calls": {
-        "x-regex-iterator": "<\\|tool_call>(.*?)<tool_call\\|>",
-        "type": "array",
         "items": {
-          "type": "object",
           "properties": {
-            "type": {
-              "const": "function"
-            },
             "function": {
-              "type": "object",
-              "x-regex": "call\\:(?P<name>\\w+)(?P<arguments>\\{.*\\})",
               "properties": {
-                "name": {
-                  "type": "string"
-                },
                 "arguments": {
+                  "additionalProperties": {},
                   "type": "object",
-                  "x-parser": "gemma4-tool-call",
-                  "additionalProperties": {}
+                  "x-parser": "gemma4-tool-call"
+                },
+                "name": {
+                  "type": "string"
                 }
-              }
+              },
+              "type": "object",
+              "x-regex": "call\\:(?P<name>\\w+)(?P<arguments>\\{.*\\})"
+            },
+            "type": {
+              "const": "function"
             }
-          }
-        }
+          },
+          "type": "object"
+        },
+        "type": "array",
+        "x-regex-iterator": "<\\|tool_call>(.*?)<tool_call\\|>"
       }
     },
+    "type": "object",
     "x-regex": "(\\<\\|channel\\>thought\\n(?P<thinking>.*?)\\<channel\\|\\>)?(?P<tool_calls>\\<\\|tool_call\\>.*\\<tool_call\\|\\>)?(?P<content>(?:(?!\\<turn\\|\\>)(?!\\<\\|tool_response\\>).)+)?(?:\\<turn\\|\\>|\\<\\|tool_response\\>)?"
   },
   "soc_token": "<|channel>",