Upload Gemma3ForConditionalGeneration

config.json

@@ -39,7 +39,7 @@
           }
         },
         "_type": "Int4WeightOnlyConfig",
-        "_version": 1
+        "_version": 2
       }
     },
     "quant_type_kwargs": {}

pytorch_model-00001-of-00002.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a6a9149e08d1dc203c84fbf19996d037e1d5c5e44803c143e7b12405218a805
-size 4987253534
+oid sha256:538b990ced48d6dca85707e82960f5d82522e8fa1dee7ce94c6bf6d36f8026c4
+size 4975899385

pytorch_model-00002-of-00002.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88eaa4edc5e786f4788d61a962656f7328265f4f686121a201a609e02ada46f8
-size 3548090296
+oid sha256:baa4d2f81b76200df8e943c0e4eab95336b5782b36c09e8a731e54191ff2a0dd
+size 3190968481

pytorch_model.bin.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 8534683872
+    "total_size": 8166129312
   },
   "weight_map": {
     "language_model.lm_head.weight": "pytorch_model-00001-of-00002.bin",
@@ -148,13 +148,13 @@
     "language_model.model.layers.18.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
     "language_model.model.layers.18.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
     "language_model.model.layers.18.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "language_model.model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "language_model.model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "language_model.model.layers.19.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.19.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
     "language_model.model.layers.19.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "language_model.model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "language_model.model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "language_model.model.layers.19.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "language_model.model.layers.19.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "language_model.model.layers.19.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.19.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.19.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.19.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
     "language_model.model.layers.19.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
     "language_model.model.layers.19.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
     "language_model.model.layers.19.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
@@ -174,19 +174,19 @@
     "language_model.model.layers.2.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
     "language_model.model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
     "language_model.model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "language_model.model.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "language_model.model.layers.20.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "language_model.model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "language_model.model.layers.20.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "language_model.model.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "language_model.model.layers.20.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "language_model.model.layers.20.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "language_model.model.layers.20.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
-    "language_model.model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "language_model.model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "language_model.model.layers.20.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
-    "language_model.model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "language_model.model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "language_model.model.layers.20.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.20.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.20.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.20.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.20.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.20.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.20.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.20.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.20.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.20.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.20.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.20.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.20.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
     "language_model.model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
     "language_model.model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
     "language_model.model.layers.21.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
@@ -194,12 +194,12 @@
     "language_model.model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
     "language_model.model.layers.21.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
     "language_model.model.layers.21.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "language_model.model.layers.21.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
-    "language_model.model.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "language_model.model.layers.21.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "language_model.model.layers.21.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
-    "language_model.model.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "language_model.model.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "language_model.model.layers.21.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.21.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.21.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.21.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.21.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.21.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
     "language_model.model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
     "language_model.model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
     "language_model.model.layers.22.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",