Uploaded model in fp16.

config.json

@@ -10,5 +10,7 @@
     "layer_norm_epsilon": 1e-05,
     "n_head": 32,
     "attention_dropout": 0.0,
-    "model_type": "bloom"
+    "model_type": "bloom",
+    "torch_dtype": "float16",
+    "transformers_version": "4.35.2"
 }

pytorch_model-00001-of-00003.bin → model-00001-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c6f71cf6cfe71fbe876366c18de4985f06d036e1a04424c6a069f898157be20
-size 9952772288
+oid sha256:c9190868d86cb15acd1dc9f21e9dc3577bd853c088b1f64391eef24aff214c4e
+size 4976378256

pytorch_model-00001-of-00003.safetensors → model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08fca79f87c2bb2dd8746765b92d8a232db052605259f55a529d96dc2465639f
-size 9952739760
+oid sha256:b26ffb41970cfb3c7df671b97ceea958f84bad0c0548564157a7ec3607b117e8
+size 4967383936

pytorch_model-00002-of-00003.bin → model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34854460d608ab7904c328e02e0a25fd54339ca0ec51a3f62c3391ce0db8c206
-size 9934783849
+oid sha256:58b208b1e11d3ff61b989d7a3a89477654a0a74f73c65567b5da9683d9aa212e
+size 2550809312

model.safetensors.index.json

@@ -0,0 +1,372 @@
+{
+  "metadata": {
+    "total_size": 12494528512
+  },
+  "weight_map": {
+    "transformer.h.0.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.0.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.0.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.0.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.0.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.0.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.0.self_attention.dense.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.0.self_attention.dense.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.0.self_attention.query_key_value.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.0.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.1.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.1.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.1.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.1.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.1.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.1.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.1.self_attention.dense.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.1.self_attention.dense.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.1.self_attention.query_key_value.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.1.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.10.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.10.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.10.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.10.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.10.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.10.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.10.self_attention.dense.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.10.self_attention.dense.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.10.self_attention.query_key_value.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.10.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.11.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.11.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.11.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.11.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.11.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.11.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.11.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.11.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.11.self_attention.dense.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.11.self_attention.dense.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.11.self_attention.query_key_value.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.11.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.12.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.12.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.12.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.12.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.12.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.12.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.12.self_attention.dense.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.12.self_attention.dense.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.12.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.12.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.13.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.13.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.13.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.13.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.13.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.13.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.13.self_attention.dense.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.13.self_attention.dense.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.13.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.13.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.14.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.14.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.14.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.14.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.14.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.14.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.14.self_attention.dense.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.14.self_attention.dense.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.14.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.14.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.15.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.15.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.15.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.15.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.15.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.15.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.15.self_attention.dense.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.15.self_attention.dense.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.15.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.15.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.16.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.16.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.16.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.16.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.16.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.16.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.16.self_attention.dense.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.16.self_attention.dense.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.16.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.16.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.17.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.17.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.17.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.17.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.17.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.17.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.17.self_attention.dense.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.17.self_attention.dense.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.17.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.17.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.18.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.18.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.18.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.18.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.18.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.18.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.18.self_attention.dense.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.18.self_attention.dense.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.18.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.18.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.19.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.19.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.19.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.19.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.19.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.19.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.19.self_attention.dense.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.19.self_attention.dense.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.19.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.19.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.2.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.2.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.2.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.2.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.2.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.2.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.2.self_attention.dense.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.2.self_attention.dense.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.2.self_attention.query_key_value.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.2.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.20.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.20.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.20.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.20.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.20.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.20.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.20.self_attention.dense.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.20.self_attention.dense.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.20.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.20.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.21.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.21.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.21.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.21.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.21.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.21.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.21.self_attention.dense.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.21.self_attention.dense.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.21.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.21.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.22.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.22.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.22.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.22.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.22.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.22.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.22.self_attention.dense.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.22.self_attention.dense.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.22.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.22.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.23.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.23.mlp.dense_4h_to_h.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.23.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.23.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.23.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.23.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.23.self_attention.dense.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.23.self_attention.dense.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.23.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.23.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.24.input_layernorm.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.24.mlp.dense_4h_to_h.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.24.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.24.mlp.dense_h_to_4h.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.24.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.24.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.24.self_attention.dense.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.24.self_attention.dense.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.24.self_attention.query_key_value.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.24.self_attention.query_key_value.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.25.input_layernorm.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.25.mlp.dense_4h_to_h.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.25.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.25.mlp.dense_h_to_4h.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.25.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.25.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.25.self_attention.dense.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.25.self_attention.dense.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.25.self_attention.query_key_value.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.25.self_attention.query_key_value.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.26.input_layernorm.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.26.mlp.dense_4h_to_h.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.26.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.26.mlp.dense_h_to_4h.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.26.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.26.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.26.self_attention.dense.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.26.self_attention.dense.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.26.self_attention.query_key_value.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.26.self_attention.query_key_value.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.27.input_layernorm.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.27.mlp.dense_4h_to_h.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.27.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.27.mlp.dense_h_to_4h.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.27.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.27.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.27.self_attention.dense.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.27.self_attention.dense.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.27.self_attention.query_key_value.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.27.self_attention.query_key_value.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.28.input_layernorm.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.28.mlp.dense_4h_to_h.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.28.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.28.mlp.dense_h_to_4h.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.28.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.28.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.28.self_attention.dense.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.28.self_attention.dense.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.28.self_attention.query_key_value.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.28.self_attention.query_key_value.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.29.input_layernorm.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.29.mlp.dense_4h_to_h.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.29.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.29.mlp.dense_h_to_4h.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.29.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.29.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.29.self_attention.dense.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.29.self_attention.dense.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.29.self_attention.query_key_value.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.29.self_attention.query_key_value.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.3.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.3.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.3.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.3.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.3.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.3.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.3.self_attention.dense.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.3.self_attention.dense.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.3.self_attention.query_key_value.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.3.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.4.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.4.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.4.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.4.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.4.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.4.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.4.self_attention.dense.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.4.self_attention.dense.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.4.self_attention.query_key_value.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.4.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.5.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.5.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.5.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.5.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.5.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.5.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.5.self_attention.dense.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.5.self_attention.dense.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.5.self_attention.query_key_value.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.5.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.6.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.6.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.6.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.6.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.6.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.6.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.6.self_attention.dense.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.6.self_attention.dense.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.6.self_attention.query_key_value.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.6.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.7.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.7.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.7.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.7.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.7.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.7.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.7.self_attention.dense.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.7.self_attention.dense.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.7.self_attention.query_key_value.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.7.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.8.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.8.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.8.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.8.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.8.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.8.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.8.self_attention.dense.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.8.self_attention.dense.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.8.self_attention.query_key_value.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.8.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.9.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.9.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.9.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.9.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.9.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.9.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.9.self_attention.dense.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.9.self_attention.dense.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.9.self_attention.query_key_value.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.9.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
+    "transformer.ln_f.bias": "model-00003-of-00003.safetensors",
+    "transformer.ln_f.weight": "model-00003-of-00003.safetensors",
+    "transformer.word_embeddings.weight": "model-00001-of-00003.safetensors",
+    "transformer.word_embeddings_layernorm.bias": "model-00001-of-00003.safetensors",
+    "transformer.word_embeddings_layernorm.weight": "model-00001-of-00003.safetensors"
+  }
+}

pytorch_model-00002-of-00003.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:20738e0b67b025e51d55ae480e9810b788541899cf66763ab5e14677dddb60ac
-size 9934750632

pytorch_model-00003-of-00003.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:62413a5a62df4b80b85b11676b24fe04678632a92efca4473532575bd440a4ba
-size 5925037617

pytorch_model-00003-of-00003.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:94a400fd74983d1713e2120f5480dc52b1c47a77ac3f45d56c98bbc8f62078fa
-size 5925020536

pytorch_model.bin.index.json

@@ -1,373 +0,0 @@
-{
-    "metadata": {
-        "total_size": 25812467712
-    },
-    "weight_map": {
-        "transformer.word_embeddings.weight": "pytorch_model-00001-of-00003.bin",
-        "transformer.word_embeddings_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-        "transformer.word_embeddings_layernorm.bias": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.0.self_attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.0.self_attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.0.self_attention.dense.weight": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.0.self_attention.dense.bias": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.0.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.0.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.0.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.0.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.0.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.0.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.0.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.1.self_attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.1.self_attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.1.self_attention.dense.weight": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.1.self_attention.dense.bias": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.1.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.1.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.1.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.1.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.1.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.1.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.1.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.2.self_attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.2.self_attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.2.self_attention.dense.weight": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.2.self_attention.dense.bias": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.2.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.2.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.2.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.2.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.2.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.2.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.2.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.3.self_attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.3.self_attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.3.self_attention.dense.weight": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.3.self_attention.dense.bias": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.3.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.3.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.3.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.3.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.3.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.3.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.3.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.4.self_attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.4.self_attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.4.self_attention.dense.weight": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.4.self_attention.dense.bias": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.4.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.4.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.4.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.4.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.4.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.4.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.4.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.5.self_attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.5.self_attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.5.self_attention.dense.weight": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.5.self_attention.dense.bias": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.5.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.5.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.5.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.5.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.5.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.5.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.5.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.6.self_attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.6.self_attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.6.self_attention.dense.weight": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.6.self_attention.dense.bias": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.6.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.6.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.6.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.6.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.6.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.6.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.6.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.7.self_attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.7.self_attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.7.self_attention.dense.weight": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.7.self_attention.dense.bias": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.7.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.7.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.7.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.7.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.7.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.7.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.7.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.8.self_attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.8.self_attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.8.self_attention.dense.weight": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.8.self_attention.dense.bias": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.8.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.8.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.8.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.8.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.8.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.8.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.8.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.9.self_attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.9.self_attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.9.self_attention.dense.weight": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.9.self_attention.dense.bias": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.9.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.9.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.9.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.9.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.9.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.9.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.9.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.10.self_attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.10.self_attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.10.self_attention.dense.weight": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.10.self_attention.dense.bias": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.10.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.10.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.10.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.10.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.10.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.10.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.10.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.11.self_attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.11.self_attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.11.self_attention.dense.weight": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.11.self_attention.dense.bias": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.11.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.11.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.11.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
-        "transformer.h.11.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.11.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.11.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.11.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.12.self_attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.12.self_attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.12.self_attention.dense.weight": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.12.self_attention.dense.bias": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.12.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.12.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.12.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.12.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.12.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.12.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.12.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.13.self_attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.13.self_attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.13.self_attention.dense.weight": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.13.self_attention.dense.bias": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.13.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.13.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.13.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.13.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.13.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.13.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.13.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.14.self_attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.14.self_attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.14.self_attention.dense.weight": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.14.self_attention.dense.bias": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.14.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.14.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.14.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.14.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.14.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.14.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.14.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.15.self_attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.15.self_attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.15.self_attention.dense.weight": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.15.self_attention.dense.bias": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.15.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.15.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.15.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.15.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.15.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.15.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.15.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.16.self_attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.16.self_attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.16.self_attention.dense.weight": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.16.self_attention.dense.bias": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.16.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.16.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.16.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.16.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.16.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.16.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.16.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.17.self_attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.17.self_attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.17.self_attention.dense.weight": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.17.self_attention.dense.bias": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.17.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.17.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.17.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.17.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.17.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.17.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.17.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.18.self_attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.18.self_attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.18.self_attention.dense.weight": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.18.self_attention.dense.bias": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.18.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.18.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.18.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.18.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.18.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.18.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.18.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.19.self_attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.19.self_attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.19.self_attention.dense.weight": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.19.self_attention.dense.bias": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.19.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.19.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.19.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.19.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.19.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.19.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.19.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.20.self_attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.20.self_attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.20.self_attention.dense.weight": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.20.self_attention.dense.bias": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.20.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.20.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.20.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.20.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.20.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.20.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.20.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.21.self_attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.21.self_attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.21.self_attention.dense.weight": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.21.self_attention.dense.bias": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.21.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.21.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.21.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.21.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.21.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.21.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.21.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.22.self_attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.22.self_attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.22.self_attention.dense.weight": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.22.self_attention.dense.bias": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.22.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.22.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.22.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.22.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.22.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.22.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.22.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.23.self_attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.23.self_attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.23.self_attention.dense.weight": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.23.self_attention.dense.bias": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.23.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.23.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.23.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.23.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.23.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
-        "transformer.h.23.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
-        "transformer.h.23.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00003.bin",
-        "transformer.h.24.self_attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
-        "transformer.h.24.self_attention.query_key_value.bias": "pytorch_model-00003-of-00003.bin",
-        "transformer.h.24.self_attention.dense.weight": "pytorch_model-00003-of-00003.bin",
-        "transformer.h.24.self_attention.dense.bias": "pytorch_model-00003-of-00003.bin",
-        "transformer.h.24.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
-        "transformer.h.24.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
-        "transformer.h.24.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
-        "transformer.h.24.post_attention_layernorm.bias": "pytorch_model-00003-of-00003.bin",
-        "transformer.h.24.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
-        "transformer.h.24.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00003.bin",
-        "transformer.h.24.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
-        "transformer.h.24.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00003.bin",
-        "transformer.h.25.self_attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
-        "transformer.h.25.self_attention.query_key_value.bias": "pytorch_model-00003-of-00003.bin",
-        "transformer.h.25.self_attention.dense.weight": "pytorch_model-00003-of-00003.bin",
-        "transformer.h.25.self_attention.dense.bias": "pytorch_model-00003-of-00003.bin",
-        "transformer.h.25.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
-        "transformer.h.25.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
-        "transformer.h.25.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
-        "transformer.h.25.post_attention_layernorm.bias": "pytorch_model-00003-of-00003.bin",
-        "transformer.h.25.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
-        "transformer.h.25.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00003.bin",
-        "transformer.h.25.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
-        "transformer.h.25.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00003.bin",
-        "transformer.h.26.self_attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
-        "transformer.h.26.self_attention.query_key_value.bias": "pytorch_model-00003-of-00003.bin",
-        "transformer.h.26.self_attention.dense.weight": "pytorch_model-00003-of-00003.bin",
-        "transformer.h.26.self_attention.dense.bias": "pytorch_model-00003-of-00003.bin",
-        "transformer.h.26.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
-        "transformer.h.26.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
-        "transformer.h.26.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
-        "transformer.h.26.post_attention_layernorm.bias": "pytorch_model-00003-of-00003.bin",
-        "transformer.h.26.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
-        "transformer.h.26.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00003.bin",
-        "transformer.h.26.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
-        "transformer.h.26.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00003.bin",
-        "transformer.h.27.self_attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
-        "transformer.h.27.self_attention.query_key_value.bias": "pytorch_model-00003-of-00003.bin",
-        "transformer.h.27.self_attention.dense.weight": "pytorch_model-00003-of-00003.bin",
-        "transformer.h.27.self_attention.dense.bias": "pytorch_model-00003-of-00003.bin",
-        "transformer.h.27.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
-        "transformer.h.27.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
-        "transformer.h.27.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
-        "transformer.h.27.post_attention_layernorm.bias": "pytorch_model-00003-of-00003.bin",
-        "transformer.h.27.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
-        "transformer.h.27.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00003.bin",
-        "transformer.h.27.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
-        "transformer.h.27.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00003.bin",
-        "transformer.h.28.self_attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
-        "transformer.h.28.self_attention.query_key_value.bias": "pytorch_model-00003-of-00003.bin",
-        "transformer.h.28.self_attention.dense.weight": "pytorch_model-00003-of-00003.bin",
-        "transformer.h.28.self_attention.dense.bias": "pytorch_model-00003-of-00003.bin",
-        "transformer.h.28.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
-        "transformer.h.28.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
-        "transformer.h.28.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
-        "transformer.h.28.post_attention_layernorm.bias": "pytorch_model-00003-of-00003.bin",
-        "transformer.h.28.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
-        "transformer.h.28.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00003.bin",
-        "transformer.h.28.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
-        "transformer.h.28.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00003.bin",
-        "transformer.h.29.self_attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
-        "transformer.h.29.self_attention.query_key_value.bias": "pytorch_model-00003-of-00003.bin",
-        "transformer.h.29.self_attention.dense.weight": "pytorch_model-00003-of-00003.bin",
-        "transformer.h.29.self_attention.dense.bias": "pytorch_model-00003-of-00003.bin",
-        "transformer.h.29.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
-        "transformer.h.29.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
-        "transformer.h.29.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
-        "transformer.h.29.post_attention_layernorm.bias": "pytorch_model-00003-of-00003.bin",
-        "transformer.h.29.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
-        "transformer.h.29.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00003.bin",
-        "transformer.h.29.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
-        "transformer.h.29.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00003.bin",
-        "transformer.ln_f.weight": "pytorch_model-00003-of-00003.bin",
-        "transformer.ln_f.bias": "pytorch_model-00003-of-00003.bin",
-        "lm_head.weight": "pytorch_model-00003-of-00003.bin"
-    }
-}