Shard checkpoint

config.json

@@ -1,29 +1,31 @@
 {
   "apply_residual_connection_post_layernorm": false,
+  "architectures": [
+    "BloomModel"
+  ],
   "attention_dropout": 0.0,
   "attention_softmax_in_fp32": true,
   "bias_dropout_fusion": true,
   "bos_token_id": 1,
-  "architectures": [
-    "BloomModel"
-  ],
   "eos_token_id": 2,
-  "pad_token_id": 3,
-  "unk_token_id": 0,
   "hidden_dropout": 0.0,
+  "hidden_size": 4096,
   "initializer_range": 0.02,
   "layer_norm_epsilon": 1e-05,
   "masked_softmax_fusion": true,
   "model_type": "bloom",
-  "n_embed": 4096,
+  "n_head": 32,
   "n_inner": null,
   "n_layer": 30,
-  "num_attention_heads": 32,
   "offset_alibi": 100,
+  "pad_token_id": 3,
   "pretraining_tp": 1,
   "skip_bias_add": true,
   "skip_bias_add_qkv": false,
-  "transformers_version": "4.20.0",
+  "slow_but_exact": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.22.2",
+  "unk_token_id": 0,
   "use_cache": true,
   "vocab_size": 250880
 }

pytorch_model.bin → pytorch_model-00001-of-00002.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:179bb023e04beaee344fb6a5bb83765a39d736481f81d1364195fffb3ec0ca81
-size 14138164543
+oid sha256:f827f093c3e30875e96bc8093800f6fffcb81f8bd73e84109efcaae57f5d77ff
+size 9976268775

pytorch_model-00002-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a68540e3387c76ee41cc0e9c3ef8d73bd3ebcf00b7fbc3d689a70f583c7d70f1
+size 4161876233

pytorch_model.bin.index.json

@@ -0,0 +1,372 @@
+{
+  "metadata": {
+    "total_size": 14138032128
+  },
+  "weight_map": {
+    "h.0.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.0.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.0.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.0.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.0.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.0.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.0.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "h.0.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "h.0.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "h.0.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "h.1.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.1.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.1.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.1.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.1.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.1.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.1.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "h.1.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "h.1.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "h.1.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "h.10.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.10.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.10.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.10.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.10.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.10.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.10.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "h.10.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "h.10.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "h.10.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "h.11.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.11.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.11.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.11.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.11.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.11.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.11.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "h.11.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "h.11.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "h.11.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "h.12.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.12.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.12.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.12.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.12.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.12.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.12.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "h.12.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "h.12.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "h.12.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "h.13.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.13.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.13.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.13.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.13.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.13.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.13.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "h.13.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "h.13.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "h.13.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "h.14.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.14.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.14.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.14.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.14.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.14.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.14.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "h.14.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "h.14.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "h.14.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "h.15.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.15.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.15.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.15.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.15.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.15.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.15.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.15.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.15.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "h.15.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "h.15.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "h.15.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "h.16.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.16.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.16.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.16.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.16.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.16.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.16.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.16.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.16.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "h.16.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "h.16.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "h.16.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "h.17.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.17.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.17.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.17.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.17.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.17.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.17.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.17.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.17.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "h.17.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "h.17.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "h.17.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "h.18.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.18.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.18.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.18.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.18.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.18.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.18.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.18.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.18.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "h.18.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "h.18.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "h.18.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "h.19.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.19.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.19.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
+    "h.19.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "h.19.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.19.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.19.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.19.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.19.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "h.19.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "h.19.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "h.19.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "h.2.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.2.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.2.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.2.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.2.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.2.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.2.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "h.2.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "h.2.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "h.2.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "h.20.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "h.20.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "h.20.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
+    "h.20.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "h.20.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
+    "h.20.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
+    "h.20.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "h.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "h.20.self_attention.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "h.20.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "h.20.self_attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
+    "h.20.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
+    "h.21.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "h.21.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "h.21.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
+    "h.21.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "h.21.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
+    "h.21.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
+    "h.21.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "h.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "h.21.self_attention.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "h.21.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "h.21.self_attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
+    "h.21.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
+    "h.22.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "h.22.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "h.22.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
+    "h.22.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "h.22.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
+    "h.22.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
+    "h.22.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "h.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "h.22.self_attention.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "h.22.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "h.22.self_attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
+    "h.22.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
+    "h.23.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "h.23.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "h.23.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
+    "h.23.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "h.23.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
+    "h.23.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
+    "h.23.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "h.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "h.23.self_attention.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "h.23.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "h.23.self_attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
+    "h.23.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
+    "h.24.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "h.24.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "h.24.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
+    "h.24.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "h.24.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
+    "h.24.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
+    "h.24.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "h.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "h.24.self_attention.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "h.24.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "h.24.self_attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
+    "h.24.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
+    "h.25.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "h.25.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "h.25.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
+    "h.25.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "h.25.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
+    "h.25.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
+    "h.25.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "h.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "h.25.self_attention.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "h.25.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "h.25.self_attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
+    "h.25.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
+    "h.26.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "h.26.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "h.26.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
+    "h.26.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "h.26.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
+    "h.26.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
+    "h.26.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "h.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "h.26.self_attention.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "h.26.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "h.26.self_attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
+    "h.26.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
+    "h.27.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "h.27.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "h.27.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
+    "h.27.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "h.27.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
+    "h.27.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
+    "h.27.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "h.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "h.27.self_attention.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "h.27.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "h.27.self_attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
+    "h.27.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
+    "h.28.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "h.28.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "h.28.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
+    "h.28.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "h.28.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
+    "h.28.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
+    "h.28.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "h.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "h.28.self_attention.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "h.28.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "h.28.self_attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
+    "h.28.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
+    "h.29.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "h.29.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "h.29.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
+    "h.29.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "h.29.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
+    "h.29.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
+    "h.29.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "h.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "h.29.self_attention.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "h.29.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "h.29.self_attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
+    "h.29.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
+    "h.3.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.3.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.3.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.3.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.3.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.3.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.3.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "h.3.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "h.3.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "h.3.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "h.4.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.4.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.4.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.4.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.4.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.4.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.4.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "h.4.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "h.4.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "h.4.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "h.5.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.5.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.5.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.5.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.5.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.5.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.5.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "h.5.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "h.5.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "h.5.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "h.6.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.6.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.6.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.6.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.6.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.6.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.6.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "h.6.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "h.6.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "h.6.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "h.7.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.7.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.7.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.7.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.7.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.7.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.7.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "h.7.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "h.7.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "h.7.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "h.8.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.8.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.8.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.8.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.8.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.8.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.8.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "h.8.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "h.8.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "h.8.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "h.9.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.9.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.9.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.9.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.9.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.9.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.9.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "h.9.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "h.9.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "h.9.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "ln_f.bias": "pytorch_model-00002-of-00002.bin",
+    "ln_f.weight": "pytorch_model-00002-of-00002.bin",
+    "word_embeddings.weight": "pytorch_model-00001-of-00002.bin",
+    "word_embeddings_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "word_embeddings_layernorm.weight": "pytorch_model-00001-of-00002.bin"
+  }
+}