Upload model

config.json

@@ -1,8 +1,8 @@
 {
-  "_name_or_path": "Langboat/bloom-1b4-zh",
+  "_name_or_path": "modeled",
   "apply_residual_connection_post_layernorm": false,
   "architectures": [
-    "BloomForCausalLM"
+    "BloomModel"
   ],
   "attention_dropout": 0.0,
   "attention_softmax_in_fp32": true,

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39cc82903201257410d5cfbe62e9dd4191af2d8fb005cf08f8f643faa543079f
-size 4943912688
+oid sha256:7eb9f0ccc88a6cc5de13ff8f1db98f11a77c79ce7e55e8492ad01bb5f0eb6781
+size 4943909360

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5e8c3df5883ebc556841612b75c7e49b7c4cab3f6762dc727e0fd99f9e0a54a
-size 268568352
+oid sha256:b7efe40c843610d14218a08e6ea54b05bc883b6512ec56cbbddcf402880fa0f7
+size 268568160

model.safetensors.index.json

@@ -3,298 +3,298 @@
     "total_size": 5212446720
   },
   "weight_map": {
-    "transformer.h.0.input_layernorm.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.0.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.0.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.0.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.0.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.0.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.0.self_attention.dense.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.0.self_attention.dense.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.0.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.0.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.1.input_layernorm.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.1.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.1.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.1.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.1.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.1.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.1.self_attention.dense.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.1.self_attention.dense.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.1.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.1.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.10.input_layernorm.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.10.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.10.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.10.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.10.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.10.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.10.self_attention.dense.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.10.self_attention.dense.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.10.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.10.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.11.input_layernorm.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.11.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.11.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.11.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.11.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.11.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.11.self_attention.dense.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.11.self_attention.dense.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.11.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.11.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.12.input_layernorm.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.12.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.12.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.12.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.12.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.12.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.12.self_attention.dense.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.12.self_attention.dense.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.12.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.12.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.13.input_layernorm.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.13.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.13.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.13.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.13.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.13.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.13.self_attention.dense.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.13.self_attention.dense.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.13.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.13.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.14.input_layernorm.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.14.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.14.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.14.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.14.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.14.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.14.self_attention.dense.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.14.self_attention.dense.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.14.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.14.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.15.input_layernorm.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.15.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.15.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.15.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.15.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.15.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.15.self_attention.dense.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.15.self_attention.dense.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.15.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.15.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.16.input_layernorm.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.16.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.16.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.16.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.16.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.16.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.16.self_attention.dense.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.16.self_attention.dense.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.16.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.16.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.17.input_layernorm.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.17.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.17.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.17.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.17.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.17.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.17.self_attention.dense.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.17.self_attention.dense.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.17.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.17.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.18.input_layernorm.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.18.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.18.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.18.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.18.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.18.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.18.self_attention.dense.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.18.self_attention.dense.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.18.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.18.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.19.input_layernorm.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.19.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.19.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.19.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.19.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.19.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.19.self_attention.dense.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.19.self_attention.dense.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.19.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.19.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.2.input_layernorm.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.2.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.2.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.2.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.2.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.2.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.2.self_attention.dense.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.2.self_attention.dense.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.2.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.2.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.20.input_layernorm.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.20.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.20.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.20.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.20.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.20.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.20.self_attention.dense.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.20.self_attention.dense.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.20.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.20.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.21.input_layernorm.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.21.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.21.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.21.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.21.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.21.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.21.self_attention.dense.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.21.self_attention.dense.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.21.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.21.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.22.input_layernorm.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.22.mlp.dense_4h_to_h.bias": "model-00002-of-00002.safetensors",
-    "transformer.h.22.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors",
-    "transformer.h.22.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.22.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.22.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.22.self_attention.dense.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.22.self_attention.dense.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.22.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.22.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.23.input_layernorm.bias": "model-00002-of-00002.safetensors",
-    "transformer.h.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "transformer.h.23.mlp.dense_4h_to_h.bias": "model-00002-of-00002.safetensors",
-    "transformer.h.23.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors",
-    "transformer.h.23.mlp.dense_h_to_4h.bias": "model-00002-of-00002.safetensors",
-    "transformer.h.23.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors",
-    "transformer.h.23.post_attention_layernorm.bias": "model-00002-of-00002.safetensors",
-    "transformer.h.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "transformer.h.23.self_attention.dense.bias": "model-00002-of-00002.safetensors",
-    "transformer.h.23.self_attention.dense.weight": "model-00002-of-00002.safetensors",
-    "transformer.h.23.self_attention.query_key_value.bias": "model-00002-of-00002.safetensors",
-    "transformer.h.23.self_attention.query_key_value.weight": "model-00002-of-00002.safetensors",
-    "transformer.h.3.input_layernorm.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.3.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.3.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.3.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.3.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.3.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.3.self_attention.dense.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.3.self_attention.dense.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.3.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.3.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.4.input_layernorm.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.4.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.4.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.4.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.4.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.4.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.4.self_attention.dense.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.4.self_attention.dense.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.4.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.4.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.5.input_layernorm.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.5.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.5.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.5.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.5.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.5.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.5.self_attention.dense.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.5.self_attention.dense.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.5.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.5.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.6.input_layernorm.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.6.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.6.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.6.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.6.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.6.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.6.self_attention.dense.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.6.self_attention.dense.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.6.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.6.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.7.input_layernorm.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.7.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.7.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.7.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.7.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.7.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.7.self_attention.dense.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.7.self_attention.dense.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.7.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.7.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.8.input_layernorm.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.8.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.8.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.8.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.8.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.8.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.8.self_attention.dense.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.8.self_attention.dense.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.8.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.8.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.9.input_layernorm.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.9.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.9.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.9.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.9.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.9.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.9.self_attention.dense.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.9.self_attention.dense.weight": "model-00001-of-00002.safetensors",
-    "transformer.h.9.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
-    "transformer.h.9.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
-    "transformer.ln_f.bias": "model-00002-of-00002.safetensors",
-    "transformer.ln_f.weight": "model-00002-of-00002.safetensors",
-    "transformer.word_embeddings.weight": "model-00001-of-00002.safetensors",
-    "transformer.word_embeddings_layernorm.bias": "model-00001-of-00002.safetensors",
-    "transformer.word_embeddings_layernorm.weight": "model-00001-of-00002.safetensors"
+    "h.0.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "h.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "h.0.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "h.0.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "h.0.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "h.0.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "h.0.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "h.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "h.0.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+    "h.0.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+    "h.0.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "h.0.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "h.1.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "h.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "h.1.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "h.1.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "h.1.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "h.1.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "h.1.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "h.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "h.1.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+    "h.1.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+    "h.1.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "h.1.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "h.10.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "h.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "h.10.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "h.10.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "h.10.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "h.10.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "h.10.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "h.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "h.10.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+    "h.10.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+    "h.10.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "h.10.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "h.11.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "h.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "h.11.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "h.11.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "h.11.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "h.11.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "h.11.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "h.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "h.11.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+    "h.11.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+    "h.11.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "h.11.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "h.12.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "h.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "h.12.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "h.12.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "h.12.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "h.12.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "h.12.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "h.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "h.12.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+    "h.12.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+    "h.12.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "h.12.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "h.13.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "h.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "h.13.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "h.13.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "h.13.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "h.13.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "h.13.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "h.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "h.13.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+    "h.13.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+    "h.13.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "h.13.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "h.14.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "h.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "h.14.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "h.14.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "h.14.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "h.14.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "h.14.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "h.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "h.14.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+    "h.14.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+    "h.14.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "h.14.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "h.15.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "h.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "h.15.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "h.15.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "h.15.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "h.15.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "h.15.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "h.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "h.15.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+    "h.15.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+    "h.15.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "h.15.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "h.16.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "h.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "h.16.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "h.16.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "h.16.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "h.16.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "h.16.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "h.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "h.16.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+    "h.16.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+    "h.16.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "h.16.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "h.17.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "h.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "h.17.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "h.17.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "h.17.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "h.17.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "h.17.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "h.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "h.17.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+    "h.17.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+    "h.17.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "h.17.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "h.18.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "h.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "h.18.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "h.18.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "h.18.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "h.18.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "h.18.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "h.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "h.18.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+    "h.18.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+    "h.18.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "h.18.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "h.19.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "h.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "h.19.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "h.19.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "h.19.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "h.19.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "h.19.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "h.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "h.19.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+    "h.19.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+    "h.19.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "h.19.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "h.2.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "h.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "h.2.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "h.2.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "h.2.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "h.2.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "h.2.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "h.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "h.2.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+    "h.2.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+    "h.2.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "h.2.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "h.20.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "h.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "h.20.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "h.20.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "h.20.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "h.20.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "h.20.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "h.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "h.20.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+    "h.20.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+    "h.20.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "h.20.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "h.21.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "h.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "h.21.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "h.21.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "h.21.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "h.21.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "h.21.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "h.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "h.21.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+    "h.21.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+    "h.21.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "h.21.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "h.22.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "h.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "h.22.mlp.dense_4h_to_h.bias": "model-00002-of-00002.safetensors",
+    "h.22.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors",
+    "h.22.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "h.22.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "h.22.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "h.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "h.22.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+    "h.22.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+    "h.22.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "h.22.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "h.23.input_layernorm.bias": "model-00002-of-00002.safetensors",
+    "h.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "h.23.mlp.dense_4h_to_h.bias": "model-00002-of-00002.safetensors",
+    "h.23.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors",
+    "h.23.mlp.dense_h_to_4h.bias": "model-00002-of-00002.safetensors",
+    "h.23.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors",
+    "h.23.post_attention_layernorm.bias": "model-00002-of-00002.safetensors",
+    "h.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "h.23.self_attention.dense.bias": "model-00002-of-00002.safetensors",
+    "h.23.self_attention.dense.weight": "model-00002-of-00002.safetensors",
+    "h.23.self_attention.query_key_value.bias": "model-00002-of-00002.safetensors",
+    "h.23.self_attention.query_key_value.weight": "model-00002-of-00002.safetensors",
+    "h.3.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "h.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "h.3.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "h.3.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "h.3.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "h.3.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "h.3.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "h.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "h.3.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+    "h.3.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+    "h.3.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "h.3.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "h.4.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "h.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "h.4.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "h.4.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "h.4.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "h.4.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "h.4.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "h.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "h.4.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+    "h.4.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+    "h.4.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "h.4.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "h.5.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "h.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "h.5.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "h.5.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "h.5.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "h.5.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "h.5.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "h.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "h.5.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+    "h.5.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+    "h.5.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "h.5.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "h.6.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "h.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "h.6.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "h.6.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "h.6.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "h.6.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "h.6.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "h.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "h.6.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+    "h.6.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+    "h.6.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "h.6.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "h.7.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "h.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "h.7.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "h.7.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "h.7.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "h.7.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "h.7.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "h.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "h.7.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+    "h.7.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+    "h.7.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "h.7.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "h.8.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "h.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "h.8.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "h.8.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "h.8.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "h.8.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "h.8.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "h.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "h.8.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+    "h.8.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+    "h.8.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "h.8.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "h.9.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "h.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "h.9.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "h.9.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "h.9.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "h.9.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "h.9.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "h.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "h.9.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+    "h.9.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+    "h.9.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "h.9.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "ln_f.bias": "model-00002-of-00002.safetensors",
+    "ln_f.weight": "model-00002-of-00002.safetensors",
+    "word_embeddings.weight": "model-00001-of-00002.safetensors",
+    "word_embeddings_layernorm.bias": "model-00001-of-00002.safetensors",
+    "word_embeddings_layernorm.weight": "model-00001-of-00002.safetensors"
   }
 }