Upload model

config.json

@@ -133,5 +133,5 @@
     "typical_p": 1.0,
     "use_bfloat16": false
   },
-  "vocab_size": 129280
+  "vocab_size": 32002
 }

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bd3d6267a9afe3b7ec6874cec9da79449328ca229deb1e6902265d30acbd422
-size 4985295984
+oid sha256:0611180c257c4a596e0d10a38f0a2c810878c0794e3f3d1d3a3b3c53fa2d7432
+size 4993781456

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e713af117d74206172b3bcf49ea421ededbbebc8758a1ce4b65a64377bc303a
-size 2360195368
+oid sha256:9152cdce4d88e5962a825315f39f6959b4b94be1ace752346113bdc5a41f4233
+size 1558880888

model.safetensors.index.json

@@ -1,7 +1,7 @@
 {
   "metadata": {
-    "total_parameters": 1836350336,
-    "total_size": 7345401344
+    "total_parameters": 1638143104,
+    "total_size": 6552572416
   },
   "weight_map": {
     "clip2_encoder.embeddings.class_embedding": "model-00002-of-00002.safetensors",
@@ -327,11 +327,11 @@
     "layers.18.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
     "layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
     "layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
     "layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
@@ -349,50 +349,50 @@
     "layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
     "layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "layers.20.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
-    "layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "layers.20.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
-    "layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
-    "layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
-    "layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
-    "layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
-    "layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.20.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.20.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.21.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.21.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.22.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.22.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
     "layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
     "layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
-    "layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
-    "layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.23.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.23.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
     "layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
     "layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",