Upload folder using huggingface_hub

config.json

@@ -1,7 +1,7 @@
 {
   "_name_or_path": "sapienzanlp/modello-italia-9b",
   "architectures": [
-    "GPTNeoXModel"
+    "GPTNeoXForCausalLM"
   ],
   "attention_bias": true,
   "attention_dropout": 0.0,

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "transformers_version": "4.40.1"
+}

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:230b3b69f340e22f9bfef6db0a8034a1589e404de4784c5bcab0b9f9feebd0db
-size 4971404856
+oid sha256:fd529a9d1fed07e27216eb5de076d05dccfe51d30e0021afedd0a64750cdec94
+size 4971405904

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7862e642b14c213305caccc530d89b9906fdfdad769bfd9cdefdc9921d5de04
-size 4982004552
+oid sha256:b8a75b44f6a45f90fd1588cde33e69e1f138bd3141181b34b7ddea8a2812f9ee
+size 4982005704

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8694400f9000eed0447a09c82da358b7cdef00c839d4a9a5f2e81521ab1c550a
-size 4929539496
+oid sha256:0af109ddd22605e3485993fac649e2a117c2ff6bca2614b545ef83687a08f22e
+size 4929540616

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5738d25eb325473871d381476b5c1bac8857336c4b9f093b5259b558c1d632d9
-size 1678135784
+oid sha256:47b63db1a2e2d89d9a063098d6e22698a81e5356e36344cb045d16a1921a94f2
+size 2191938544

model.safetensors.index.json

@@ -1,418 +1,419 @@
 {
   "metadata": {
-    "total_size": 16561039360
+    "total_size": 17074841600
   },
   "weight_map": {
-    "embed_in.weight": "model-00001-of-00004.safetensors",
-    "final_layer_norm.bias": "model-00004-of-00004.safetensors",
-    "final_layer_norm.weight": "model-00004-of-00004.safetensors",
-    "layers.0.attention.dense.bias": "model-00001-of-00004.safetensors",
-    "layers.0.attention.dense.weight": "model-00001-of-00004.safetensors",
-    "layers.0.attention.query_key_value.bias": "model-00001-of-00004.safetensors",
-    "layers.0.attention.query_key_value.weight": "model-00001-of-00004.safetensors",
-    "layers.0.input_layernorm.bias": "model-00001-of-00004.safetensors",
-    "layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "layers.0.mlp.dense_4h_to_h.bias": "model-00001-of-00004.safetensors",
-    "layers.0.mlp.dense_4h_to_h.weight": "model-00001-of-00004.safetensors",
-    "layers.0.mlp.dense_h_to_4h.bias": "model-00001-of-00004.safetensors",
-    "layers.0.mlp.dense_h_to_4h.weight": "model-00001-of-00004.safetensors",
-    "layers.0.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
-    "layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "layers.1.attention.dense.bias": "model-00001-of-00004.safetensors",
-    "layers.1.attention.dense.weight": "model-00001-of-00004.safetensors",
-    "layers.1.attention.query_key_value.bias": "model-00001-of-00004.safetensors",
-    "layers.1.attention.query_key_value.weight": "model-00001-of-00004.safetensors",
-    "layers.1.input_layernorm.bias": "model-00001-of-00004.safetensors",
-    "layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "layers.1.mlp.dense_4h_to_h.bias": "model-00001-of-00004.safetensors",
-    "layers.1.mlp.dense_4h_to_h.weight": "model-00001-of-00004.safetensors",
-    "layers.1.mlp.dense_h_to_4h.bias": "model-00001-of-00004.safetensors",
-    "layers.1.mlp.dense_h_to_4h.weight": "model-00001-of-00004.safetensors",
-    "layers.1.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
-    "layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "layers.10.attention.dense.bias": "model-00002-of-00004.safetensors",
-    "layers.10.attention.dense.weight": "model-00002-of-00004.safetensors",
-    "layers.10.attention.query_key_value.bias": "model-00002-of-00004.safetensors",
-    "layers.10.attention.query_key_value.weight": "model-00002-of-00004.safetensors",
-    "layers.10.input_layernorm.bias": "model-00002-of-00004.safetensors",
-    "layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "layers.10.mlp.dense_4h_to_h.bias": "model-00002-of-00004.safetensors",
-    "layers.10.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
-    "layers.10.mlp.dense_h_to_4h.bias": "model-00002-of-00004.safetensors",
-    "layers.10.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
-    "layers.10.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
-    "layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "layers.11.attention.dense.bias": "model-00002-of-00004.safetensors",
-    "layers.11.attention.dense.weight": "model-00002-of-00004.safetensors",
-    "layers.11.attention.query_key_value.bias": "model-00002-of-00004.safetensors",
-    "layers.11.attention.query_key_value.weight": "model-00002-of-00004.safetensors",
-    "layers.11.input_layernorm.bias": "model-00002-of-00004.safetensors",
-    "layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "layers.11.mlp.dense_4h_to_h.bias": "model-00002-of-00004.safetensors",
-    "layers.11.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
-    "layers.11.mlp.dense_h_to_4h.bias": "model-00002-of-00004.safetensors",
-    "layers.11.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
-    "layers.11.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
-    "layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "layers.12.attention.dense.bias": "model-00002-of-00004.safetensors",
-    "layers.12.attention.dense.weight": "model-00002-of-00004.safetensors",
-    "layers.12.attention.query_key_value.bias": "model-00002-of-00004.safetensors",
-    "layers.12.attention.query_key_value.weight": "model-00002-of-00004.safetensors",
-    "layers.12.input_layernorm.bias": "model-00002-of-00004.safetensors",
-    "layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "layers.12.mlp.dense_4h_to_h.bias": "model-00002-of-00004.safetensors",
-    "layers.12.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
-    "layers.12.mlp.dense_h_to_4h.bias": "model-00002-of-00004.safetensors",
-    "layers.12.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
-    "layers.12.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
-    "layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "layers.13.attention.dense.bias": "model-00002-of-00004.safetensors",
-    "layers.13.attention.dense.weight": "model-00002-of-00004.safetensors",
-    "layers.13.attention.query_key_value.bias": "model-00002-of-00004.safetensors",
-    "layers.13.attention.query_key_value.weight": "model-00002-of-00004.safetensors",
-    "layers.13.input_layernorm.bias": "model-00002-of-00004.safetensors",
-    "layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "layers.13.mlp.dense_4h_to_h.bias": "model-00002-of-00004.safetensors",
-    "layers.13.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
-    "layers.13.mlp.dense_h_to_4h.bias": "model-00002-of-00004.safetensors",
-    "layers.13.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
-    "layers.13.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
-    "layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "layers.14.attention.dense.bias": "model-00002-of-00004.safetensors",
-    "layers.14.attention.dense.weight": "model-00002-of-00004.safetensors",
-    "layers.14.attention.query_key_value.bias": "model-00002-of-00004.safetensors",
-    "layers.14.attention.query_key_value.weight": "model-00002-of-00004.safetensors",
-    "layers.14.input_layernorm.bias": "model-00002-of-00004.safetensors",
-    "layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "layers.14.mlp.dense_4h_to_h.bias": "model-00002-of-00004.safetensors",
-    "layers.14.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
-    "layers.14.mlp.dense_h_to_4h.bias": "model-00002-of-00004.safetensors",
-    "layers.14.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
-    "layers.14.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
-    "layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "layers.15.attention.dense.bias": "model-00002-of-00004.safetensors",
-    "layers.15.attention.dense.weight": "model-00002-of-00004.safetensors",
-    "layers.15.attention.query_key_value.bias": "model-00002-of-00004.safetensors",
-    "layers.15.attention.query_key_value.weight": "model-00002-of-00004.safetensors",
-    "layers.15.input_layernorm.bias": "model-00002-of-00004.safetensors",
-    "layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "layers.15.mlp.dense_4h_to_h.bias": "model-00002-of-00004.safetensors",
-    "layers.15.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
-    "layers.15.mlp.dense_h_to_4h.bias": "model-00002-of-00004.safetensors",
-    "layers.15.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
-    "layers.15.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
-    "layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "layers.16.attention.dense.bias": "model-00002-of-00004.safetensors",
-    "layers.16.attention.dense.weight": "model-00002-of-00004.safetensors",
-    "layers.16.attention.query_key_value.bias": "model-00002-of-00004.safetensors",
-    "layers.16.attention.query_key_value.weight": "model-00002-of-00004.safetensors",
-    "layers.16.input_layernorm.bias": "model-00002-of-00004.safetensors",
-    "layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "layers.16.mlp.dense_4h_to_h.bias": "model-00002-of-00004.safetensors",
-    "layers.16.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
-    "layers.16.mlp.dense_h_to_4h.bias": "model-00002-of-00004.safetensors",
-    "layers.16.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
-    "layers.16.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
-    "layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "layers.17.attention.dense.bias": "model-00002-of-00004.safetensors",
-    "layers.17.attention.dense.weight": "model-00002-of-00004.safetensors",
-    "layers.17.attention.query_key_value.bias": "model-00002-of-00004.safetensors",
-    "layers.17.attention.query_key_value.weight": "model-00002-of-00004.safetensors",
-    "layers.17.input_layernorm.bias": "model-00002-of-00004.safetensors",
-    "layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "layers.17.mlp.dense_4h_to_h.bias": "model-00002-of-00004.safetensors",
-    "layers.17.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
-    "layers.17.mlp.dense_h_to_4h.bias": "model-00002-of-00004.safetensors",
-    "layers.17.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
-    "layers.17.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
-    "layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "layers.18.attention.dense.bias": "model-00002-of-00004.safetensors",
-    "layers.18.attention.dense.weight": "model-00002-of-00004.safetensors",
-    "layers.18.attention.query_key_value.bias": "model-00002-of-00004.safetensors",
-    "layers.18.attention.query_key_value.weight": "model-00002-of-00004.safetensors",
-    "layers.18.input_layernorm.bias": "model-00002-of-00004.safetensors",
-    "layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "layers.18.mlp.dense_4h_to_h.bias": "model-00002-of-00004.safetensors",
-    "layers.18.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
-    "layers.18.mlp.dense_h_to_4h.bias": "model-00002-of-00004.safetensors",
-    "layers.18.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
-    "layers.18.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
-    "layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "layers.19.attention.dense.bias": "model-00002-of-00004.safetensors",
-    "layers.19.attention.dense.weight": "model-00002-of-00004.safetensors",
-    "layers.19.attention.query_key_value.bias": "model-00002-of-00004.safetensors",
-    "layers.19.attention.query_key_value.weight": "model-00002-of-00004.safetensors",
-    "layers.19.input_layernorm.bias": "model-00002-of-00004.safetensors",
-    "layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "layers.19.mlp.dense_4h_to_h.bias": "model-00002-of-00004.safetensors",
-    "layers.19.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
-    "layers.19.mlp.dense_h_to_4h.bias": "model-00002-of-00004.safetensors",
-    "layers.19.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
-    "layers.19.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
-    "layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "layers.2.attention.dense.bias": "model-00001-of-00004.safetensors",
-    "layers.2.attention.dense.weight": "model-00001-of-00004.safetensors",
-    "layers.2.attention.query_key_value.bias": "model-00001-of-00004.safetensors",
-    "layers.2.attention.query_key_value.weight": "model-00001-of-00004.safetensors",
-    "layers.2.input_layernorm.bias": "model-00001-of-00004.safetensors",
-    "layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "layers.2.mlp.dense_4h_to_h.bias": "model-00001-of-00004.safetensors",
-    "layers.2.mlp.dense_4h_to_h.weight": "model-00001-of-00004.safetensors",
-    "layers.2.mlp.dense_h_to_4h.bias": "model-00001-of-00004.safetensors",
-    "layers.2.mlp.dense_h_to_4h.weight": "model-00001-of-00004.safetensors",
-    "layers.2.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
-    "layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "layers.20.attention.dense.bias": "model-00003-of-00004.safetensors",
-    "layers.20.attention.dense.weight": "model-00003-of-00004.safetensors",
-    "layers.20.attention.query_key_value.bias": "model-00003-of-00004.safetensors",
-    "layers.20.attention.query_key_value.weight": "model-00003-of-00004.safetensors",
-    "layers.20.input_layernorm.bias": "model-00002-of-00004.safetensors",
-    "layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "layers.20.mlp.dense_4h_to_h.bias": "model-00003-of-00004.safetensors",
-    "layers.20.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
-    "layers.20.mlp.dense_h_to_4h.bias": "model-00003-of-00004.safetensors",
-    "layers.20.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
-    "layers.20.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
-    "layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "layers.21.attention.dense.bias": "model-00003-of-00004.safetensors",
-    "layers.21.attention.dense.weight": "model-00003-of-00004.safetensors",
-    "layers.21.attention.query_key_value.bias": "model-00003-of-00004.safetensors",
-    "layers.21.attention.query_key_value.weight": "model-00003-of-00004.safetensors",
-    "layers.21.input_layernorm.bias": "model-00003-of-00004.safetensors",
-    "layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "layers.21.mlp.dense_4h_to_h.bias": "model-00003-of-00004.safetensors",
-    "layers.21.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
-    "layers.21.mlp.dense_h_to_4h.bias": "model-00003-of-00004.safetensors",
-    "layers.21.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
-    "layers.21.post_attention_layernorm.bias": "model-00003-of-00004.safetensors",
-    "layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "layers.22.attention.dense.bias": "model-00003-of-00004.safetensors",
-    "layers.22.attention.dense.weight": "model-00003-of-00004.safetensors",
-    "layers.22.attention.query_key_value.bias": "model-00003-of-00004.safetensors",
-    "layers.22.attention.query_key_value.weight": "model-00003-of-00004.safetensors",
-    "layers.22.input_layernorm.bias": "model-00003-of-00004.safetensors",
-    "layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "layers.22.mlp.dense_4h_to_h.bias": "model-00003-of-00004.safetensors",
-    "layers.22.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
-    "layers.22.mlp.dense_h_to_4h.bias": "model-00003-of-00004.safetensors",
-    "layers.22.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
-    "layers.22.post_attention_layernorm.bias": "model-00003-of-00004.safetensors",
-    "layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "layers.23.attention.dense.bias": "model-00003-of-00004.safetensors",
-    "layers.23.attention.dense.weight": "model-00003-of-00004.safetensors",
-    "layers.23.attention.query_key_value.bias": "model-00003-of-00004.safetensors",
-    "layers.23.attention.query_key_value.weight": "model-00003-of-00004.safetensors",
-    "layers.23.input_layernorm.bias": "model-00003-of-00004.safetensors",
-    "layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "layers.23.mlp.dense_4h_to_h.bias": "model-00003-of-00004.safetensors",
-    "layers.23.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
-    "layers.23.mlp.dense_h_to_4h.bias": "model-00003-of-00004.safetensors",
-    "layers.23.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
-    "layers.23.post_attention_layernorm.bias": "model-00003-of-00004.safetensors",
-    "layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "layers.24.attention.dense.bias": "model-00003-of-00004.safetensors",
-    "layers.24.attention.dense.weight": "model-00003-of-00004.safetensors",
-    "layers.24.attention.query_key_value.bias": "model-00003-of-00004.safetensors",
-    "layers.24.attention.query_key_value.weight": "model-00003-of-00004.safetensors",
-    "layers.24.input_layernorm.bias": "model-00003-of-00004.safetensors",
-    "layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "layers.24.mlp.dense_4h_to_h.bias": "model-00003-of-00004.safetensors",
-    "layers.24.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
-    "layers.24.mlp.dense_h_to_4h.bias": "model-00003-of-00004.safetensors",
-    "layers.24.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
-    "layers.24.post_attention_layernorm.bias": "model-00003-of-00004.safetensors",
-    "layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "layers.25.attention.dense.bias": "model-00003-of-00004.safetensors",
-    "layers.25.attention.dense.weight": "model-00003-of-00004.safetensors",
-    "layers.25.attention.query_key_value.bias": "model-00003-of-00004.safetensors",
-    "layers.25.attention.query_key_value.weight": "model-00003-of-00004.safetensors",
-    "layers.25.input_layernorm.bias": "model-00003-of-00004.safetensors",
-    "layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "layers.25.mlp.dense_4h_to_h.bias": "model-00003-of-00004.safetensors",
-    "layers.25.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
-    "layers.25.mlp.dense_h_to_4h.bias": "model-00003-of-00004.safetensors",
-    "layers.25.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
-    "layers.25.post_attention_layernorm.bias": "model-00003-of-00004.safetensors",
-    "layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "layers.26.attention.dense.bias": "model-00003-of-00004.safetensors",
-    "layers.26.attention.dense.weight": "model-00003-of-00004.safetensors",
-    "layers.26.attention.query_key_value.bias": "model-00003-of-00004.safetensors",
-    "layers.26.attention.query_key_value.weight": "model-00003-of-00004.safetensors",
-    "layers.26.input_layernorm.bias": "model-00003-of-00004.safetensors",
-    "layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "layers.26.mlp.dense_4h_to_h.bias": "model-00003-of-00004.safetensors",
-    "layers.26.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
-    "layers.26.mlp.dense_h_to_4h.bias": "model-00003-of-00004.safetensors",
-    "layers.26.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
-    "layers.26.post_attention_layernorm.bias": "model-00003-of-00004.safetensors",
-    "layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "layers.27.attention.dense.bias": "model-00003-of-00004.safetensors",
-    "layers.27.attention.dense.weight": "model-00003-of-00004.safetensors",
-    "layers.27.attention.query_key_value.bias": "model-00003-of-00004.safetensors",
-    "layers.27.attention.query_key_value.weight": "model-00003-of-00004.safetensors",
-    "layers.27.input_layernorm.bias": "model-00003-of-00004.safetensors",
-    "layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "layers.27.mlp.dense_4h_to_h.bias": "model-00003-of-00004.safetensors",
-    "layers.27.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
-    "layers.27.mlp.dense_h_to_4h.bias": "model-00003-of-00004.safetensors",
-    "layers.27.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
-    "layers.27.post_attention_layernorm.bias": "model-00003-of-00004.safetensors",
-    "layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "layers.28.attention.dense.bias": "model-00003-of-00004.safetensors",
-    "layers.28.attention.dense.weight": "model-00003-of-00004.safetensors",
-    "layers.28.attention.query_key_value.bias": "model-00003-of-00004.safetensors",
-    "layers.28.attention.query_key_value.weight": "model-00003-of-00004.safetensors",
-    "layers.28.input_layernorm.bias": "model-00003-of-00004.safetensors",
-    "layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "layers.28.mlp.dense_4h_to_h.bias": "model-00003-of-00004.safetensors",
-    "layers.28.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
-    "layers.28.mlp.dense_h_to_4h.bias": "model-00003-of-00004.safetensors",
-    "layers.28.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
-    "layers.28.post_attention_layernorm.bias": "model-00003-of-00004.safetensors",
-    "layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "layers.29.attention.dense.bias": "model-00003-of-00004.safetensors",
-    "layers.29.attention.dense.weight": "model-00003-of-00004.safetensors",
-    "layers.29.attention.query_key_value.bias": "model-00003-of-00004.safetensors",
-    "layers.29.attention.query_key_value.weight": "model-00003-of-00004.safetensors",
-    "layers.29.input_layernorm.bias": "model-00003-of-00004.safetensors",
-    "layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "layers.29.mlp.dense_4h_to_h.bias": "model-00003-of-00004.safetensors",
-    "layers.29.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
-    "layers.29.mlp.dense_h_to_4h.bias": "model-00003-of-00004.safetensors",
-    "layers.29.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
-    "layers.29.post_attention_layernorm.bias": "model-00003-of-00004.safetensors",
-    "layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "layers.3.attention.dense.bias": "model-00001-of-00004.safetensors",
-    "layers.3.attention.dense.weight": "model-00001-of-00004.safetensors",
-    "layers.3.attention.query_key_value.bias": "model-00001-of-00004.safetensors",
-    "layers.3.attention.query_key_value.weight": "model-00001-of-00004.safetensors",
-    "layers.3.input_layernorm.bias": "model-00001-of-00004.safetensors",
-    "layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "layers.3.mlp.dense_4h_to_h.bias": "model-00001-of-00004.safetensors",
-    "layers.3.mlp.dense_4h_to_h.weight": "model-00001-of-00004.safetensors",
-    "layers.3.mlp.dense_h_to_4h.bias": "model-00001-of-00004.safetensors",
-    "layers.3.mlp.dense_h_to_4h.weight": "model-00001-of-00004.safetensors",
-    "layers.3.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
-    "layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "layers.30.attention.dense.bias": "model-00003-of-00004.safetensors",
-    "layers.30.attention.dense.weight": "model-00003-of-00004.safetensors",
-    "layers.30.attention.query_key_value.bias": "model-00003-of-00004.safetensors",
-    "layers.30.attention.query_key_value.weight": "model-00003-of-00004.safetensors",
-    "layers.30.input_layernorm.bias": "model-00003-of-00004.safetensors",
-    "layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "layers.30.mlp.dense_4h_to_h.bias": "model-00004-of-00004.safetensors",
-    "layers.30.mlp.dense_4h_to_h.weight": "model-00004-of-00004.safetensors",
-    "layers.30.mlp.dense_h_to_4h.bias": "model-00004-of-00004.safetensors",
-    "layers.30.mlp.dense_h_to_4h.weight": "model-00004-of-00004.safetensors",
-    "layers.30.post_attention_layernorm.bias": "model-00003-of-00004.safetensors",
-    "layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "layers.31.attention.dense.bias": "model-00004-of-00004.safetensors",
-    "layers.31.attention.dense.weight": "model-00004-of-00004.safetensors",
-    "layers.31.attention.query_key_value.bias": "model-00004-of-00004.safetensors",
-    "layers.31.attention.query_key_value.weight": "model-00004-of-00004.safetensors",
-    "layers.31.input_layernorm.bias": "model-00004-of-00004.safetensors",
-    "layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
-    "layers.31.mlp.dense_4h_to_h.bias": "model-00004-of-00004.safetensors",
-    "layers.31.mlp.dense_4h_to_h.weight": "model-00004-of-00004.safetensors",
-    "layers.31.mlp.dense_h_to_4h.bias": "model-00004-of-00004.safetensors",
-    "layers.31.mlp.dense_h_to_4h.weight": "model-00004-of-00004.safetensors",
-    "layers.31.post_attention_layernorm.bias": "model-00004-of-00004.safetensors",
-    "layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
-    "layers.32.attention.dense.bias": "model-00004-of-00004.safetensors",
-    "layers.32.attention.dense.weight": "model-00004-of-00004.safetensors",
-    "layers.32.attention.query_key_value.bias": "model-00004-of-00004.safetensors",
-    "layers.32.attention.query_key_value.weight": "model-00004-of-00004.safetensors",
-    "layers.32.input_layernorm.bias": "model-00004-of-00004.safetensors",
-    "layers.32.input_layernorm.weight": "model-00004-of-00004.safetensors",
-    "layers.32.mlp.dense_4h_to_h.bias": "model-00004-of-00004.safetensors",
-    "layers.32.mlp.dense_4h_to_h.weight": "model-00004-of-00004.safetensors",
-    "layers.32.mlp.dense_h_to_4h.bias": "model-00004-of-00004.safetensors",
-    "layers.32.mlp.dense_h_to_4h.weight": "model-00004-of-00004.safetensors",
-    "layers.32.post_attention_layernorm.bias": "model-00004-of-00004.safetensors",
-    "layers.32.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
-    "layers.33.attention.dense.bias": "model-00004-of-00004.safetensors",
-    "layers.33.attention.dense.weight": "model-00004-of-00004.safetensors",
-    "layers.33.attention.query_key_value.bias": "model-00004-of-00004.safetensors",
-    "layers.33.attention.query_key_value.weight": "model-00004-of-00004.safetensors",
-    "layers.33.input_layernorm.bias": "model-00004-of-00004.safetensors",
-    "layers.33.input_layernorm.weight": "model-00004-of-00004.safetensors",
-    "layers.33.mlp.dense_4h_to_h.bias": "model-00004-of-00004.safetensors",
-    "layers.33.mlp.dense_4h_to_h.weight": "model-00004-of-00004.safetensors",
-    "layers.33.mlp.dense_h_to_4h.bias": "model-00004-of-00004.safetensors",
-    "layers.33.mlp.dense_h_to_4h.weight": "model-00004-of-00004.safetensors",
-    "layers.33.post_attention_layernorm.bias": "model-00004-of-00004.safetensors",
-    "layers.33.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
-    "layers.4.attention.dense.bias": "model-00001-of-00004.safetensors",
-    "layers.4.attention.dense.weight": "model-00001-of-00004.safetensors",
-    "layers.4.attention.query_key_value.bias": "model-00001-of-00004.safetensors",
-    "layers.4.attention.query_key_value.weight": "model-00001-of-00004.safetensors",
-    "layers.4.input_layernorm.bias": "model-00001-of-00004.safetensors",
-    "layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "layers.4.mlp.dense_4h_to_h.bias": "model-00001-of-00004.safetensors",
-    "layers.4.mlp.dense_4h_to_h.weight": "model-00001-of-00004.safetensors",
-    "layers.4.mlp.dense_h_to_4h.bias": "model-00001-of-00004.safetensors",
-    "layers.4.mlp.dense_h_to_4h.weight": "model-00001-of-00004.safetensors",
-    "layers.4.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
-    "layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "layers.5.attention.dense.bias": "model-00001-of-00004.safetensors",
-    "layers.5.attention.dense.weight": "model-00001-of-00004.safetensors",
-    "layers.5.attention.query_key_value.bias": "model-00001-of-00004.safetensors",
-    "layers.5.attention.query_key_value.weight": "model-00001-of-00004.safetensors",
-    "layers.5.input_layernorm.bias": "model-00001-of-00004.safetensors",
-    "layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "layers.5.mlp.dense_4h_to_h.bias": "model-00001-of-00004.safetensors",
-    "layers.5.mlp.dense_4h_to_h.weight": "model-00001-of-00004.safetensors",
-    "layers.5.mlp.dense_h_to_4h.bias": "model-00001-of-00004.safetensors",
-    "layers.5.mlp.dense_h_to_4h.weight": "model-00001-of-00004.safetensors",
-    "layers.5.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
-    "layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "layers.6.attention.dense.bias": "model-00001-of-00004.safetensors",
-    "layers.6.attention.dense.weight": "model-00001-of-00004.safetensors",
-    "layers.6.attention.query_key_value.bias": "model-00001-of-00004.safetensors",
-    "layers.6.attention.query_key_value.weight": "model-00001-of-00004.safetensors",
-    "layers.6.input_layernorm.bias": "model-00001-of-00004.safetensors",
-    "layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "layers.6.mlp.dense_4h_to_h.bias": "model-00001-of-00004.safetensors",
-    "layers.6.mlp.dense_4h_to_h.weight": "model-00001-of-00004.safetensors",
-    "layers.6.mlp.dense_h_to_4h.bias": "model-00001-of-00004.safetensors",
-    "layers.6.mlp.dense_h_to_4h.weight": "model-00001-of-00004.safetensors",
-    "layers.6.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
-    "layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "layers.7.attention.dense.bias": "model-00001-of-00004.safetensors",
-    "layers.7.attention.dense.weight": "model-00001-of-00004.safetensors",
-    "layers.7.attention.query_key_value.bias": "model-00001-of-00004.safetensors",
-    "layers.7.attention.query_key_value.weight": "model-00001-of-00004.safetensors",
-    "layers.7.input_layernorm.bias": "model-00001-of-00004.safetensors",
-    "layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "layers.7.mlp.dense_4h_to_h.bias": "model-00001-of-00004.safetensors",
-    "layers.7.mlp.dense_4h_to_h.weight": "model-00001-of-00004.safetensors",
-    "layers.7.mlp.dense_h_to_4h.bias": "model-00001-of-00004.safetensors",
-    "layers.7.mlp.dense_h_to_4h.weight": "model-00001-of-00004.safetensors",
-    "layers.7.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
-    "layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "layers.8.attention.dense.bias": "model-00001-of-00004.safetensors",
-    "layers.8.attention.dense.weight": "model-00001-of-00004.safetensors",
-    "layers.8.attention.query_key_value.bias": "model-00001-of-00004.safetensors",
-    "layers.8.attention.query_key_value.weight": "model-00001-of-00004.safetensors",
-    "layers.8.input_layernorm.bias": "model-00001-of-00004.safetensors",
-    "layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "layers.8.mlp.dense_4h_to_h.bias": "model-00001-of-00004.safetensors",
-    "layers.8.mlp.dense_4h_to_h.weight": "model-00001-of-00004.safetensors",
-    "layers.8.mlp.dense_h_to_4h.bias": "model-00001-of-00004.safetensors",
-    "layers.8.mlp.dense_h_to_4h.weight": "model-00001-of-00004.safetensors",
-    "layers.8.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
-    "layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "layers.9.attention.dense.bias": "model-00001-of-00004.safetensors",
-    "layers.9.attention.dense.weight": "model-00001-of-00004.safetensors",
-    "layers.9.attention.query_key_value.bias": "model-00001-of-00004.safetensors",
-    "layers.9.attention.query_key_value.weight": "model-00001-of-00004.safetensors",
-    "layers.9.input_layernorm.bias": "model-00001-of-00004.safetensors",
-    "layers.9.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "layers.9.mlp.dense_4h_to_h.bias": "model-00002-of-00004.safetensors",
-    "layers.9.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
-    "layers.9.mlp.dense_h_to_4h.bias": "model-00002-of-00004.safetensors",
-    "layers.9.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
-    "layers.9.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
-    "layers.9.post_attention_layernorm.weight": "model-00001-of-00004.safetensors"
+    "embed_out.weight": "model-00004-of-00004.safetensors",
+    "gpt_neox.embed_in.weight": "model-00001-of-00004.safetensors",
+    "gpt_neox.final_layer_norm.bias": "model-00004-of-00004.safetensors",
+    "gpt_neox.final_layer_norm.weight": "model-00004-of-00004.safetensors",
+    "gpt_neox.layers.0.attention.dense.bias": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.0.attention.dense.weight": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.0.attention.query_key_value.bias": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.0.attention.query_key_value.weight": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.0.input_layernorm.bias": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.0.mlp.dense_4h_to_h.bias": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.0.mlp.dense_4h_to_h.weight": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.0.mlp.dense_h_to_4h.bias": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.0.mlp.dense_h_to_4h.weight": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.0.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.1.attention.dense.bias": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.1.attention.dense.weight": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.1.attention.query_key_value.bias": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.1.attention.query_key_value.weight": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.1.input_layernorm.bias": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.1.mlp.dense_4h_to_h.bias": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.1.mlp.dense_4h_to_h.weight": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.1.mlp.dense_h_to_4h.bias": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.1.mlp.dense_h_to_4h.weight": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.1.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.10.attention.dense.bias": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.10.attention.dense.weight": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.10.attention.query_key_value.bias": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.10.attention.query_key_value.weight": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.10.input_layernorm.bias": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.10.mlp.dense_4h_to_h.bias": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.10.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.10.mlp.dense_h_to_4h.bias": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.10.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.10.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.11.attention.dense.bias": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.11.attention.dense.weight": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.11.attention.query_key_value.bias": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.11.attention.query_key_value.weight": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.11.input_layernorm.bias": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.11.mlp.dense_4h_to_h.bias": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.11.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.11.mlp.dense_h_to_4h.bias": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.11.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.11.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.12.attention.dense.bias": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.12.attention.dense.weight": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.12.attention.query_key_value.bias": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.12.attention.query_key_value.weight": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.12.input_layernorm.bias": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.12.mlp.dense_4h_to_h.bias": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.12.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.12.mlp.dense_h_to_4h.bias": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.12.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.12.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.13.attention.dense.bias": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.13.attention.dense.weight": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.13.attention.query_key_value.bias": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.13.attention.query_key_value.weight": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.13.input_layernorm.bias": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.13.mlp.dense_4h_to_h.bias": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.13.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.13.mlp.dense_h_to_4h.bias": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.13.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.13.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.14.attention.dense.bias": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.14.attention.dense.weight": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.14.attention.query_key_value.bias": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.14.attention.query_key_value.weight": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.14.input_layernorm.bias": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.14.mlp.dense_4h_to_h.bias": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.14.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.14.mlp.dense_h_to_4h.bias": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.14.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.14.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.15.attention.dense.bias": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.15.attention.dense.weight": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.15.attention.query_key_value.bias": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.15.attention.query_key_value.weight": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.15.input_layernorm.bias": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.15.mlp.dense_4h_to_h.bias": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.15.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.15.mlp.dense_h_to_4h.bias": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.15.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.15.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.16.attention.dense.bias": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.16.attention.dense.weight": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.16.attention.query_key_value.bias": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.16.attention.query_key_value.weight": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.16.input_layernorm.bias": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.16.mlp.dense_4h_to_h.bias": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.16.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.16.mlp.dense_h_to_4h.bias": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.16.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.16.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.17.attention.dense.bias": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.17.attention.dense.weight": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.17.attention.query_key_value.bias": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.17.attention.query_key_value.weight": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.17.input_layernorm.bias": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.17.mlp.dense_4h_to_h.bias": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.17.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.17.mlp.dense_h_to_4h.bias": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.17.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.17.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.18.attention.dense.bias": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.18.attention.dense.weight": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.18.attention.query_key_value.bias": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.18.attention.query_key_value.weight": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.18.input_layernorm.bias": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.18.mlp.dense_4h_to_h.bias": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.18.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.18.mlp.dense_h_to_4h.bias": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.18.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.18.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.19.attention.dense.bias": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.19.attention.dense.weight": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.19.attention.query_key_value.bias": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.19.attention.query_key_value.weight": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.19.input_layernorm.bias": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.19.mlp.dense_4h_to_h.bias": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.19.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.19.mlp.dense_h_to_4h.bias": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.19.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.19.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.2.attention.dense.bias": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.2.attention.dense.weight": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.2.attention.query_key_value.bias": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.2.attention.query_key_value.weight": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.2.input_layernorm.bias": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.2.mlp.dense_4h_to_h.bias": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.2.mlp.dense_4h_to_h.weight": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.2.mlp.dense_h_to_4h.bias": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.2.mlp.dense_h_to_4h.weight": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.2.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.20.attention.dense.bias": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.20.attention.dense.weight": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.20.attention.query_key_value.bias": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.20.attention.query_key_value.weight": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.20.input_layernorm.bias": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.20.mlp.dense_4h_to_h.bias": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.20.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.20.mlp.dense_h_to_4h.bias": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.20.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.20.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.21.attention.dense.bias": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.21.attention.dense.weight": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.21.attention.query_key_value.bias": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.21.attention.query_key_value.weight": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.21.input_layernorm.bias": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.21.mlp.dense_4h_to_h.bias": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.21.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.21.mlp.dense_h_to_4h.bias": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.21.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.21.post_attention_layernorm.bias": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.22.attention.dense.bias": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.22.attention.dense.weight": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.22.attention.query_key_value.bias": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.22.attention.query_key_value.weight": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.22.input_layernorm.bias": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.22.mlp.dense_4h_to_h.bias": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.22.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.22.mlp.dense_h_to_4h.bias": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.22.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.22.post_attention_layernorm.bias": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.23.attention.dense.bias": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.23.attention.dense.weight": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.23.attention.query_key_value.bias": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.23.attention.query_key_value.weight": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.23.input_layernorm.bias": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.23.mlp.dense_4h_to_h.bias": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.23.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.23.mlp.dense_h_to_4h.bias": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.23.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.23.post_attention_layernorm.bias": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.24.attention.dense.bias": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.24.attention.dense.weight": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.24.attention.query_key_value.bias": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.24.attention.query_key_value.weight": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.24.input_layernorm.bias": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.24.mlp.dense_4h_to_h.bias": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.24.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.24.mlp.dense_h_to_4h.bias": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.24.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.24.post_attention_layernorm.bias": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.25.attention.dense.bias": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.25.attention.dense.weight": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.25.attention.query_key_value.bias": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.25.attention.query_key_value.weight": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.25.input_layernorm.bias": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.25.mlp.dense_4h_to_h.bias": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.25.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.25.mlp.dense_h_to_4h.bias": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.25.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.25.post_attention_layernorm.bias": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.26.attention.dense.bias": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.26.attention.dense.weight": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.26.attention.query_key_value.bias": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.26.attention.query_key_value.weight": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.26.input_layernorm.bias": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.26.mlp.dense_4h_to_h.bias": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.26.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.26.mlp.dense_h_to_4h.bias": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.26.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.26.post_attention_layernorm.bias": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.27.attention.dense.bias": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.27.attention.dense.weight": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.27.attention.query_key_value.bias": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.27.attention.query_key_value.weight": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.27.input_layernorm.bias": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.27.mlp.dense_4h_to_h.bias": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.27.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.27.mlp.dense_h_to_4h.bias": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.27.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.27.post_attention_layernorm.bias": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.28.attention.dense.bias": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.28.attention.dense.weight": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.28.attention.query_key_value.bias": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.28.attention.query_key_value.weight": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.28.input_layernorm.bias": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.28.mlp.dense_4h_to_h.bias": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.28.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.28.mlp.dense_h_to_4h.bias": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.28.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.28.post_attention_layernorm.bias": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.29.attention.dense.bias": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.29.attention.dense.weight": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.29.attention.query_key_value.bias": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.29.attention.query_key_value.weight": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.29.input_layernorm.bias": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.29.mlp.dense_4h_to_h.bias": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.29.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.29.mlp.dense_h_to_4h.bias": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.29.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.29.post_attention_layernorm.bias": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.3.attention.dense.bias": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.3.attention.dense.weight": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.3.attention.query_key_value.bias": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.3.attention.query_key_value.weight": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.3.input_layernorm.bias": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.3.mlp.dense_4h_to_h.bias": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.3.mlp.dense_4h_to_h.weight": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.3.mlp.dense_h_to_4h.bias": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.3.mlp.dense_h_to_4h.weight": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.3.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.30.attention.dense.bias": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.30.attention.dense.weight": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.30.attention.query_key_value.bias": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.30.attention.query_key_value.weight": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.30.input_layernorm.bias": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.30.mlp.dense_4h_to_h.bias": "model-00004-of-00004.safetensors",
+    "gpt_neox.layers.30.mlp.dense_4h_to_h.weight": "model-00004-of-00004.safetensors",
+    "gpt_neox.layers.30.mlp.dense_h_to_4h.bias": "model-00004-of-00004.safetensors",
+    "gpt_neox.layers.30.mlp.dense_h_to_4h.weight": "model-00004-of-00004.safetensors",
+    "gpt_neox.layers.30.post_attention_layernorm.bias": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.31.attention.dense.bias": "model-00004-of-00004.safetensors",
+    "gpt_neox.layers.31.attention.dense.weight": "model-00004-of-00004.safetensors",
+    "gpt_neox.layers.31.attention.query_key_value.bias": "model-00004-of-00004.safetensors",
+    "gpt_neox.layers.31.attention.query_key_value.weight": "model-00004-of-00004.safetensors",
+    "gpt_neox.layers.31.input_layernorm.bias": "model-00004-of-00004.safetensors",
+    "gpt_neox.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "gpt_neox.layers.31.mlp.dense_4h_to_h.bias": "model-00004-of-00004.safetensors",
+    "gpt_neox.layers.31.mlp.dense_4h_to_h.weight": "model-00004-of-00004.safetensors",
+    "gpt_neox.layers.31.mlp.dense_h_to_4h.bias": "model-00004-of-00004.safetensors",
+    "gpt_neox.layers.31.mlp.dense_h_to_4h.weight": "model-00004-of-00004.safetensors",
+    "gpt_neox.layers.31.post_attention_layernorm.bias": "model-00004-of-00004.safetensors",
+    "gpt_neox.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "gpt_neox.layers.32.attention.dense.bias": "model-00004-of-00004.safetensors",
+    "gpt_neox.layers.32.attention.dense.weight": "model-00004-of-00004.safetensors",
+    "gpt_neox.layers.32.attention.query_key_value.bias": "model-00004-of-00004.safetensors",
+    "gpt_neox.layers.32.attention.query_key_value.weight": "model-00004-of-00004.safetensors",
+    "gpt_neox.layers.32.input_layernorm.bias": "model-00004-of-00004.safetensors",
+    "gpt_neox.layers.32.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "gpt_neox.layers.32.mlp.dense_4h_to_h.bias": "model-00004-of-00004.safetensors",
+    "gpt_neox.layers.32.mlp.dense_4h_to_h.weight": "model-00004-of-00004.safetensors",
+    "gpt_neox.layers.32.mlp.dense_h_to_4h.bias": "model-00004-of-00004.safetensors",
+    "gpt_neox.layers.32.mlp.dense_h_to_4h.weight": "model-00004-of-00004.safetensors",
+    "gpt_neox.layers.32.post_attention_layernorm.bias": "model-00004-of-00004.safetensors",
+    "gpt_neox.layers.32.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "gpt_neox.layers.33.attention.dense.bias": "model-00004-of-00004.safetensors",
+    "gpt_neox.layers.33.attention.dense.weight": "model-00004-of-00004.safetensors",
+    "gpt_neox.layers.33.attention.query_key_value.bias": "model-00004-of-00004.safetensors",
+    "gpt_neox.layers.33.attention.query_key_value.weight": "model-00004-of-00004.safetensors",
+    "gpt_neox.layers.33.input_layernorm.bias": "model-00004-of-00004.safetensors",
+    "gpt_neox.layers.33.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "gpt_neox.layers.33.mlp.dense_4h_to_h.bias": "model-00004-of-00004.safetensors",
+    "gpt_neox.layers.33.mlp.dense_4h_to_h.weight": "model-00004-of-00004.safetensors",
+    "gpt_neox.layers.33.mlp.dense_h_to_4h.bias": "model-00004-of-00004.safetensors",
+    "gpt_neox.layers.33.mlp.dense_h_to_4h.weight": "model-00004-of-00004.safetensors",
+    "gpt_neox.layers.33.post_attention_layernorm.bias": "model-00004-of-00004.safetensors",
+    "gpt_neox.layers.33.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "gpt_neox.layers.4.attention.dense.bias": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.4.attention.dense.weight": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.4.attention.query_key_value.bias": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.4.attention.query_key_value.weight": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.4.input_layernorm.bias": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.4.mlp.dense_4h_to_h.bias": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.4.mlp.dense_4h_to_h.weight": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.4.mlp.dense_h_to_4h.bias": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.4.mlp.dense_h_to_4h.weight": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.4.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.5.attention.dense.bias": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.5.attention.dense.weight": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.5.attention.query_key_value.bias": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.5.attention.query_key_value.weight": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.5.input_layernorm.bias": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.5.mlp.dense_4h_to_h.bias": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.5.mlp.dense_4h_to_h.weight": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.5.mlp.dense_h_to_4h.bias": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.5.mlp.dense_h_to_4h.weight": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.5.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.6.attention.dense.bias": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.6.attention.dense.weight": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.6.attention.query_key_value.bias": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.6.attention.query_key_value.weight": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.6.input_layernorm.bias": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.6.mlp.dense_4h_to_h.bias": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.6.mlp.dense_4h_to_h.weight": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.6.mlp.dense_h_to_4h.bias": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.6.mlp.dense_h_to_4h.weight": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.6.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.7.attention.dense.bias": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.7.attention.dense.weight": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.7.attention.query_key_value.bias": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.7.attention.query_key_value.weight": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.7.input_layernorm.bias": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.7.mlp.dense_4h_to_h.bias": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.7.mlp.dense_4h_to_h.weight": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.7.mlp.dense_h_to_4h.bias": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.7.mlp.dense_h_to_4h.weight": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.7.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.8.attention.dense.bias": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.8.attention.dense.weight": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.8.attention.query_key_value.bias": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.8.attention.query_key_value.weight": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.8.input_layernorm.bias": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.8.mlp.dense_4h_to_h.bias": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.8.mlp.dense_4h_to_h.weight": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.8.mlp.dense_h_to_4h.bias": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.8.mlp.dense_h_to_4h.weight": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.8.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.9.attention.dense.bias": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.9.attention.dense.weight": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.9.attention.query_key_value.bias": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.9.attention.query_key_value.weight": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.9.input_layernorm.bias": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.9.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.9.mlp.dense_4h_to_h.bias": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.9.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.9.mlp.dense_h_to_4h.bias": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.9.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.9.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
+    "gpt_neox.layers.9.post_attention_layernorm.weight": "model-00001-of-00004.safetensors"
   }
 }

tokenizer_config.json

@@ -29,7 +29,7 @@
     }
   },
   "bos_token": "<s>",
-  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
+  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
   "legacy": true,