Adding `safetensors` variant of this model

This is an automated PR created with https://huggingface.co/spaces/safetensors/convert

This new file is equivalent to `pytorch_model.bin` but safe in the sense that
no arbitrary code can be put into it.

These files also happen to load much faster than their pytorch counterpart:
https://colab.research.google.com/github/huggingface/notebooks/blob/main/safetensors_doc/en/speed.ipynb

The widgets on your model page will run using this model even if this is not merged
making sure the file actually works.

If you find any issues: please report here: https://huggingface.co/spaces/safetensors/convert/discussions

Feel free to ignore this PR.

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e124e0f5b0183c0c330706b37f45b67f7031b53c242a359b66689f926ea2d70
+size 9982870976

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74eaec55d3260e2a589e360a96f8aca3748e28ccd20e4cb86c9744d54a2f46ae
+size 9934751696

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:830bc9005155f065c9a0362106a1f85c72f18e7c5fe6e88c325105d2e6ef94f8
+size 9934735552

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f45d8f43dc8fa55a4d6287b705795945622d539bee1b4a9cec67a0c07065bbe8
+size 9666250408

model.safetensors.index.json

@@ -0,0 +1,588 @@
+{
+    "metadata": {
+        "total_size": 39518535680
+    },
+    "weight_map": {
+        "glm.transformer.block_position_embeddings.weight": "model-00001-of-00004.safetensors",
+        "glm.transformer.final_layernorm.bias": "model-00004-of-00004.safetensors",
+        "glm.transformer.final_layernorm.weight": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.0.attention.dense.bias": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.0.attention.dense.weight": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.0.attention.query_key_value.bias": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.0.attention.query_key_value.weight": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.0.input_layernorm.bias": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.0.mlp.dense_4h_to_h.bias": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.0.mlp.dense_4h_to_h.weight": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.0.mlp.dense_h_to_4h.bias": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.0.mlp.dense_h_to_4h.weight": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.0.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.1.attention.dense.bias": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.1.attention.dense.weight": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.1.attention.query_key_value.bias": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.1.attention.query_key_value.weight": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.1.input_layernorm.bias": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.1.mlp.dense_4h_to_h.bias": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.1.mlp.dense_4h_to_h.weight": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.1.mlp.dense_h_to_4h.bias": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.1.mlp.dense_h_to_4h.weight": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.1.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.10.attention.dense.bias": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.10.attention.dense.weight": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.10.attention.query_key_value.bias": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.10.attention.query_key_value.weight": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.10.input_layernorm.bias": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.10.input_layernorm.weight": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.10.mlp.dense_4h_to_h.bias": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.10.mlp.dense_4h_to_h.weight": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.10.mlp.dense_h_to_4h.bias": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.10.mlp.dense_h_to_4h.weight": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.10.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.10.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.11.attention.dense.bias": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.11.attention.dense.weight": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.11.attention.query_key_value.bias": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.11.attention.query_key_value.weight": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.11.input_layernorm.bias": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.11.input_layernorm.weight": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.11.mlp.dense_4h_to_h.bias": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.11.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.11.mlp.dense_h_to_4h.bias": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.11.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.11.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.11.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.12.attention.dense.bias": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.12.attention.dense.weight": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.12.attention.query_key_value.bias": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.12.attention.query_key_value.weight": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.12.input_layernorm.bias": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.12.mlp.dense_4h_to_h.bias": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.12.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.12.mlp.dense_h_to_4h.bias": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.12.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.12.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.13.attention.dense.bias": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.13.attention.dense.weight": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.13.attention.query_key_value.bias": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.13.attention.query_key_value.weight": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.13.input_layernorm.bias": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.13.mlp.dense_4h_to_h.bias": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.13.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.13.mlp.dense_h_to_4h.bias": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.13.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.13.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.14.attention.dense.bias": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.14.attention.dense.weight": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.14.attention.query_key_value.bias": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.14.attention.query_key_value.weight": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.14.input_layernorm.bias": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.14.mlp.dense_4h_to_h.bias": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.14.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.14.mlp.dense_h_to_4h.bias": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.14.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.14.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.15.attention.dense.bias": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.15.attention.dense.weight": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.15.attention.query_key_value.bias": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.15.attention.query_key_value.weight": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.15.input_layernorm.bias": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.15.mlp.dense_4h_to_h.bias": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.15.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.15.mlp.dense_h_to_4h.bias": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.15.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.15.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.16.attention.dense.bias": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.16.attention.dense.weight": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.16.attention.query_key_value.bias": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.16.attention.query_key_value.weight": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.16.input_layernorm.bias": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.16.mlp.dense_4h_to_h.bias": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.16.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.16.mlp.dense_h_to_4h.bias": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.16.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.16.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.17.attention.dense.bias": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.17.attention.dense.weight": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.17.attention.query_key_value.bias": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.17.attention.query_key_value.weight": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.17.input_layernorm.bias": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.17.mlp.dense_4h_to_h.bias": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.17.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.17.mlp.dense_h_to_4h.bias": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.17.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.17.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.18.attention.dense.bias": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.18.attention.dense.weight": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.18.attention.query_key_value.bias": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.18.attention.query_key_value.weight": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.18.input_layernorm.bias": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.18.mlp.dense_4h_to_h.bias": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.18.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.18.mlp.dense_h_to_4h.bias": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.18.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.18.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.19.attention.dense.bias": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.19.attention.dense.weight": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.19.attention.query_key_value.bias": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.19.attention.query_key_value.weight": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.19.input_layernorm.bias": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.19.mlp.dense_4h_to_h.bias": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.19.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.19.mlp.dense_h_to_4h.bias": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.19.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.19.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.2.attention.dense.bias": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.2.attention.dense.weight": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.2.attention.query_key_value.bias": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.2.attention.query_key_value.weight": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.2.input_layernorm.bias": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.2.mlp.dense_4h_to_h.bias": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.2.mlp.dense_4h_to_h.weight": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.2.mlp.dense_h_to_4h.bias": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.2.mlp.dense_h_to_4h.weight": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.2.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.20.attention.dense.bias": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.20.attention.dense.weight": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.20.attention.query_key_value.bias": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.20.attention.query_key_value.weight": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.20.input_layernorm.bias": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.20.mlp.dense_4h_to_h.bias": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.20.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.20.mlp.dense_h_to_4h.bias": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.20.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.20.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.21.attention.dense.bias": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.21.attention.dense.weight": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.21.attention.query_key_value.bias": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.21.attention.query_key_value.weight": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.21.input_layernorm.bias": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.21.mlp.dense_4h_to_h.bias": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.21.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.21.mlp.dense_h_to_4h.bias": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.21.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.21.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.22.attention.dense.bias": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.22.attention.dense.weight": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.22.attention.query_key_value.bias": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.22.attention.query_key_value.weight": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.22.input_layernorm.bias": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.22.input_layernorm.weight": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.22.mlp.dense_4h_to_h.bias": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.22.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.22.mlp.dense_h_to_4h.bias": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.22.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.22.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.22.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.23.attention.dense.bias": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.23.attention.dense.weight": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.23.attention.query_key_value.bias": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.23.attention.query_key_value.weight": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.23.input_layernorm.bias": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.23.input_layernorm.weight": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.23.mlp.dense_4h_to_h.bias": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.23.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.23.mlp.dense_h_to_4h.bias": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.23.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.23.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.23.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+        "glm.transformer.layers.24.attention.dense.bias": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.24.attention.dense.weight": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.24.attention.query_key_value.bias": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.24.attention.query_key_value.weight": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.24.input_layernorm.bias": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.24.mlp.dense_4h_to_h.bias": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.24.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.24.mlp.dense_h_to_4h.bias": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.24.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.24.post_attention_layernorm.bias": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.25.attention.dense.bias": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.25.attention.dense.weight": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.25.attention.query_key_value.bias": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.25.attention.query_key_value.weight": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.25.input_layernorm.bias": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.25.mlp.dense_4h_to_h.bias": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.25.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.25.mlp.dense_h_to_4h.bias": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.25.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.25.post_attention_layernorm.bias": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.26.attention.dense.bias": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.26.attention.dense.weight": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.26.attention.query_key_value.bias": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.26.attention.query_key_value.weight": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.26.input_layernorm.bias": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.26.mlp.dense_4h_to_h.bias": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.26.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.26.mlp.dense_h_to_4h.bias": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.26.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.26.post_attention_layernorm.bias": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.27.attention.dense.bias": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.27.attention.dense.weight": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.27.attention.query_key_value.bias": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.27.attention.query_key_value.weight": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.27.input_layernorm.bias": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.27.mlp.dense_4h_to_h.bias": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.27.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.27.mlp.dense_h_to_4h.bias": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.27.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.27.post_attention_layernorm.bias": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.28.attention.dense.bias": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.28.attention.dense.weight": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.28.attention.query_key_value.bias": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.28.attention.query_key_value.weight": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.28.input_layernorm.bias": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.28.mlp.dense_4h_to_h.bias": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.28.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.28.mlp.dense_h_to_4h.bias": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.28.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.28.post_attention_layernorm.bias": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.29.attention.dense.bias": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.29.attention.dense.weight": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.29.attention.query_key_value.bias": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.29.attention.query_key_value.weight": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.29.input_layernorm.bias": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.29.mlp.dense_4h_to_h.bias": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.29.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.29.mlp.dense_h_to_4h.bias": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.29.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.29.post_attention_layernorm.bias": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.3.attention.dense.bias": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.3.attention.dense.weight": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.3.attention.query_key_value.bias": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.3.attention.query_key_value.weight": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.3.input_layernorm.bias": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.3.mlp.dense_4h_to_h.bias": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.3.mlp.dense_4h_to_h.weight": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.3.mlp.dense_h_to_4h.bias": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.3.mlp.dense_h_to_4h.weight": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.3.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.30.attention.dense.bias": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.30.attention.dense.weight": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.30.attention.query_key_value.bias": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.30.attention.query_key_value.weight": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.30.input_layernorm.bias": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.30.mlp.dense_4h_to_h.bias": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.30.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.30.mlp.dense_h_to_4h.bias": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.30.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.30.post_attention_layernorm.bias": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.31.attention.dense.bias": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.31.attention.dense.weight": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.31.attention.query_key_value.bias": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.31.attention.query_key_value.weight": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.31.input_layernorm.bias": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.31.mlp.dense_4h_to_h.bias": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.31.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.31.mlp.dense_h_to_4h.bias": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.31.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.31.post_attention_layernorm.bias": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.32.attention.dense.bias": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.32.attention.dense.weight": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.32.attention.query_key_value.bias": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.32.attention.query_key_value.weight": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.32.input_layernorm.bias": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.32.mlp.dense_4h_to_h.bias": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.32.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.32.mlp.dense_h_to_4h.bias": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.32.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.32.post_attention_layernorm.bias": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.33.attention.dense.bias": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.33.attention.dense.weight": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.33.attention.query_key_value.bias": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.33.attention.query_key_value.weight": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.33.input_layernorm.bias": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.33.mlp.dense_4h_to_h.bias": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.33.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.33.mlp.dense_h_to_4h.bias": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.33.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.33.post_attention_layernorm.bias": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.33.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.34.attention.dense.bias": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.34.attention.dense.weight": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.34.attention.query_key_value.bias": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.34.attention.query_key_value.weight": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.34.input_layernorm.bias": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.34.input_layernorm.weight": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.34.mlp.dense_4h_to_h.bias": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.34.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.34.mlp.dense_h_to_4h.bias": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.34.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.34.post_attention_layernorm.bias": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.34.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.35.attention.dense.bias": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.35.attention.dense.weight": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.35.attention.query_key_value.bias": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.35.attention.query_key_value.weight": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.35.input_layernorm.bias": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.35.input_layernorm.weight": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.35.mlp.dense_4h_to_h.bias": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.35.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.35.mlp.dense_h_to_4h.bias": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.35.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.35.post_attention_layernorm.bias": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.35.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.36.attention.dense.bias": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.36.attention.dense.weight": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.36.attention.query_key_value.bias": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.36.attention.query_key_value.weight": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.36.input_layernorm.bias": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.36.input_layernorm.weight": "model-00003-of-00004.safetensors",
+        "glm.transformer.layers.36.mlp.dense_4h_to_h.bias": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.36.mlp.dense_4h_to_h.weight": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.36.mlp.dense_h_to_4h.bias": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.36.mlp.dense_h_to_4h.weight": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.36.post_attention_layernorm.bias": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.36.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.37.attention.dense.bias": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.37.attention.dense.weight": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.37.attention.query_key_value.bias": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.37.attention.query_key_value.weight": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.37.input_layernorm.bias": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.37.input_layernorm.weight": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.37.mlp.dense_4h_to_h.bias": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.37.mlp.dense_4h_to_h.weight": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.37.mlp.dense_h_to_4h.bias": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.37.mlp.dense_h_to_4h.weight": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.37.post_attention_layernorm.bias": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.37.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.38.attention.dense.bias": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.38.attention.dense.weight": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.38.attention.query_key_value.bias": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.38.attention.query_key_value.weight": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.38.input_layernorm.bias": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.38.input_layernorm.weight": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.38.mlp.dense_4h_to_h.bias": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.38.mlp.dense_4h_to_h.weight": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.38.mlp.dense_h_to_4h.bias": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.38.mlp.dense_h_to_4h.weight": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.38.post_attention_layernorm.bias": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.38.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.39.attention.dense.bias": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.39.attention.dense.weight": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.39.attention.query_key_value.bias": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.39.attention.query_key_value.weight": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.39.input_layernorm.bias": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.39.input_layernorm.weight": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.39.mlp.dense_4h_to_h.bias": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.39.mlp.dense_4h_to_h.weight": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.39.mlp.dense_h_to_4h.bias": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.39.mlp.dense_h_to_4h.weight": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.39.post_attention_layernorm.bias": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.39.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.4.attention.dense.bias": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.4.attention.dense.weight": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.4.attention.query_key_value.bias": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.4.attention.query_key_value.weight": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.4.input_layernorm.bias": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.4.mlp.dense_4h_to_h.bias": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.4.mlp.dense_4h_to_h.weight": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.4.mlp.dense_h_to_4h.bias": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.4.mlp.dense_h_to_4h.weight": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.4.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.40.attention.dense.bias": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.40.attention.dense.weight": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.40.attention.query_key_value.bias": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.40.attention.query_key_value.weight": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.40.input_layernorm.bias": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.40.input_layernorm.weight": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.40.mlp.dense_4h_to_h.bias": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.40.mlp.dense_4h_to_h.weight": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.40.mlp.dense_h_to_4h.bias": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.40.mlp.dense_h_to_4h.weight": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.40.post_attention_layernorm.bias": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.40.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.41.attention.dense.bias": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.41.attention.dense.weight": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.41.attention.query_key_value.bias": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.41.attention.query_key_value.weight": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.41.input_layernorm.bias": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.41.input_layernorm.weight": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.41.mlp.dense_4h_to_h.bias": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.41.mlp.dense_4h_to_h.weight": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.41.mlp.dense_h_to_4h.bias": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.41.mlp.dense_h_to_4h.weight": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.41.post_attention_layernorm.bias": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.41.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.42.attention.dense.bias": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.42.attention.dense.weight": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.42.attention.query_key_value.bias": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.42.attention.query_key_value.weight": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.42.input_layernorm.bias": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.42.input_layernorm.weight": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.42.mlp.dense_4h_to_h.bias": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.42.mlp.dense_4h_to_h.weight": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.42.mlp.dense_h_to_4h.bias": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.42.mlp.dense_h_to_4h.weight": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.42.post_attention_layernorm.bias": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.42.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.43.attention.dense.bias": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.43.attention.dense.weight": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.43.attention.query_key_value.bias": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.43.attention.query_key_value.weight": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.43.input_layernorm.bias": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.43.input_layernorm.weight": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.43.mlp.dense_4h_to_h.bias": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.43.mlp.dense_4h_to_h.weight": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.43.mlp.dense_h_to_4h.bias": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.43.mlp.dense_h_to_4h.weight": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.43.post_attention_layernorm.bias": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.43.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.44.attention.dense.bias": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.44.attention.dense.weight": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.44.attention.query_key_value.bias": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.44.attention.query_key_value.weight": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.44.input_layernorm.bias": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.44.input_layernorm.weight": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.44.mlp.dense_4h_to_h.bias": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.44.mlp.dense_4h_to_h.weight": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.44.mlp.dense_h_to_4h.bias": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.44.mlp.dense_h_to_4h.weight": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.44.post_attention_layernorm.bias": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.44.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.45.attention.dense.bias": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.45.attention.dense.weight": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.45.attention.query_key_value.bias": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.45.attention.query_key_value.weight": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.45.input_layernorm.bias": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.45.input_layernorm.weight": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.45.mlp.dense_4h_to_h.bias": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.45.mlp.dense_4h_to_h.weight": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.45.mlp.dense_h_to_4h.bias": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.45.mlp.dense_h_to_4h.weight": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.45.post_attention_layernorm.bias": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.45.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.46.attention.dense.bias": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.46.attention.dense.weight": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.46.attention.query_key_value.bias": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.46.attention.query_key_value.weight": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.46.input_layernorm.bias": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.46.input_layernorm.weight": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.46.mlp.dense_4h_to_h.bias": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.46.mlp.dense_4h_to_h.weight": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.46.mlp.dense_h_to_4h.bias": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.46.mlp.dense_h_to_4h.weight": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.46.post_attention_layernorm.bias": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.46.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.47.attention.dense.bias": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.47.attention.dense.weight": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.47.attention.query_key_value.bias": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.47.attention.query_key_value.weight": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.47.input_layernorm.bias": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.47.input_layernorm.weight": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.47.mlp.dense_4h_to_h.bias": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.47.mlp.dense_4h_to_h.weight": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.47.mlp.dense_h_to_4h.bias": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.47.mlp.dense_h_to_4h.weight": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.47.post_attention_layernorm.bias": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.47.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+        "glm.transformer.layers.5.attention.dense.bias": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.5.attention.dense.weight": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.5.attention.query_key_value.bias": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.5.attention.query_key_value.weight": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.5.input_layernorm.bias": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.5.mlp.dense_4h_to_h.bias": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.5.mlp.dense_4h_to_h.weight": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.5.mlp.dense_h_to_4h.bias": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.5.mlp.dense_h_to_4h.weight": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.5.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.6.attention.dense.bias": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.6.attention.dense.weight": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.6.attention.query_key_value.bias": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.6.attention.query_key_value.weight": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.6.input_layernorm.bias": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.6.mlp.dense_4h_to_h.bias": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.6.mlp.dense_4h_to_h.weight": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.6.mlp.dense_h_to_4h.bias": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.6.mlp.dense_h_to_4h.weight": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.6.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.7.attention.dense.bias": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.7.attention.dense.weight": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.7.attention.query_key_value.bias": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.7.attention.query_key_value.weight": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.7.input_layernorm.bias": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.7.mlp.dense_4h_to_h.bias": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.7.mlp.dense_4h_to_h.weight": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.7.mlp.dense_h_to_4h.bias": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.7.mlp.dense_h_to_4h.weight": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.7.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.8.attention.dense.bias": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.8.attention.dense.weight": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.8.attention.query_key_value.bias": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.8.attention.query_key_value.weight": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.8.input_layernorm.bias": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.8.mlp.dense_4h_to_h.bias": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.8.mlp.dense_4h_to_h.weight": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.8.mlp.dense_h_to_4h.bias": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.8.mlp.dense_h_to_4h.weight": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.8.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.9.attention.dense.bias": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.9.attention.dense.weight": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.9.attention.query_key_value.bias": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.9.attention.query_key_value.weight": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.9.input_layernorm.bias": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.9.input_layernorm.weight": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.9.mlp.dense_4h_to_h.bias": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.9.mlp.dense_4h_to_h.weight": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.9.mlp.dense_h_to_4h.bias": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.9.mlp.dense_h_to_4h.weight": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.9.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
+        "glm.transformer.layers.9.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+        "glm.transformer.position_embeddings.weight": "model-00001-of-00004.safetensors",
+        "glm.word_embeddings.weight": "model-00001-of-00004.safetensors"
+    }
+}