update model files. make sure each shard < 5GiB

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ef6bf3055af8d145eb8571c9eb3b616ecd5857f133792d25a00526d320a7896
-size 5003695984
+oid sha256:11590a9f31d6b7c2c072446b5c1ec53c29bc0626a323bf6bd23da373fbe851ce
+size 4874083760

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0518e4bdd7e6b007bf19cc420ddedd1d4caca94ecade8ebd0da089431eefae66
-size 4074097896
+oid sha256:527c47483ed676e9d10f3dcb3280f77b16951b02e057596ba06496ead00c3b3f
+size 4203710128

model.safetensors.index.json

@@ -601,33 +601,33 @@
         "language_model.model.layers.21.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
         "language_model.model.layers.21.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
         "language_model.model.layers.21.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
-        "language_model.model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-        "language_model.model.layers.22.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
-        "language_model.model.layers.22.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
-        "language_model.model.layers.22.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
-        "language_model.model.layers.22.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
-        "language_model.model.layers.22.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
-        "language_model.model.layers.22.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
-        "language_model.model.layers.22.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.model.layers.22.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
-        "language_model.model.layers.22.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
-        "language_model.model.layers.22.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.model.layers.22.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
-        "language_model.model.layers.22.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
-        "language_model.model.layers.22.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.model.layers.22.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
-        "language_model.model.layers.22.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
-        "language_model.model.layers.22.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.model.layers.22.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
-        "language_model.model.layers.22.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
-        "language_model.model.layers.22.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.model.layers.22.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
-        "language_model.model.layers.22.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
-        "language_model.model.layers.22.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
-        "language_model.model.layers.22.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
-        "language_model.model.layers.22.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
-        "language_model.model.layers.22.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.22.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.22.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.22.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.22.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.22.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.22.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.22.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.22.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.22.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.22.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.22.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.22.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.22.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.22.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.22.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.22.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.22.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.22.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.22.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.22.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.22.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.22.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.22.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
         "language_model.model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
         "language_model.model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
         "language_model.model.layers.23.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",