Upload ChatGLMForConditionalGeneration

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "sharpbai/chatglm2-6b",
+  "add_bias_linear": false,
+  "add_qkv_bias": true,
+  "apply_query_key_layer_scaling": true,
+  "apply_residual_connection_post_layernorm": false,
+  "architectures": [
+    "ChatGLMForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "attention_softmax_in_fp32": true,
+  "auto_map": {
+    "AutoConfig": "THUDM/chatglm2-6b--configuration_chatglm.ChatGLMConfig",
+    "AutoModel": "THUDM/chatglm2-6b--modeling_chatglm.ChatGLMForConditionalGeneration",
+    "AutoModelForSeq2SeqLM": "THUDM/chatglm2-6b--modeling_chatglm.ChatGLMForConditionalGeneration"
+  },
+  "bias_dropout_fusion": true,
+  "eos_token_id": 2,
+  "ffn_hidden_size": 13696,
+  "fp32_residual_connection": false,
+  "hidden_dropout": 0.0,
+  "hidden_size": 4096,
+  "kv_channels": 128,
+  "layernorm_epsilon": 1e-05,
+  "multi_query_attention": true,
+  "multi_query_group_num": 2,
+  "num_attention_heads": 32,
+  "num_layers": 28,
+  "original_rope": true,
+  "padded_vocab_size": 65024,
+  "post_layer_norm": true,
+  "quantization_bit": 0,
+  "rmsnorm": true,
+  "seq_length": 32768,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.30.2",
+  "use_cache": true
+}

generation_config.json

@@ -0,0 +1,5 @@
+{
+  "_from_model_config": true,
+  "eos_token_id": 2,
+  "transformers_version": "4.30.2"
+}

pytorch_model-00001-of-00031.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4280a7cc4f42f284347fa8f824fdf72f9ffe8a43bb0393ce06f4fae297d94ca
+size 537

pytorch_model-00002-of-00031.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fa27a4470a6b6d0606ee05da17e800db1ed45363a31e5fe6892f7ddb30b92d8
+size 532677546

pytorch_model-00003-of-00031.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e828a2e5aae027fe260bed7e1672d523850a33c3340db639877b23045054d5a
+size 407933490

pytorch_model-00004-of-00031.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b6fdcdfb9c31857ddeea1ef60760012093f4fa2bbc98191aa0a8b95dbb920d5
+size 407924624

pytorch_model-00005-of-00031.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90190e76437017cb5cd85daf265dfb2309130d5b18ca14b6f7cf02e6e0af6fe8
+size 407924624

pytorch_model-00006-of-00031.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00e9370c20220ff8f405c26687c8bfef284c1d184414936e206825c9c551702a
+size 407924624

pytorch_model-00007-of-00031.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d2c616553a964c839aca6cd8efa2b95a8417002bfaa35c00249392b66a5bb95
+size 407924624

pytorch_model-00008-of-00031.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4491f700dccefc7ffe519436ecd94353b86b937f5f905f9b0382a2d330cba60d
+size 407924624

pytorch_model-00009-of-00031.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a92d963585bee0a378f8233759a0585bb2b30c1367b809c536478feea68dc414
+size 407924624

pytorch_model-00010-of-00031.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64c4b5baef6a30b55d8458bbe12c3f37cfa76f77b74c4670627915196f491fe0
+size 407924624

pytorch_model-00011-of-00031.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a55397cbf12647d5e0db97daeeacbecfaf62aca1263369880d5dbdc3587b68e
+size 407924624

pytorch_model-00012-of-00031.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aec4f65fef5386289f681b486bc9bb2771324e3c989f0a3911ae19e100ece708
+size 407924624

pytorch_model-00013-of-00031.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98b04c07580ef0a0b63e3c8f06b7001e94651dd89ccf534fa85b279afedc15d5
+size 407924624

pytorch_model-00014-of-00031.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d604505066ec413635bc86ea1b038a8f50814c1441c2a28563031c230ba102c
+size 407924624

pytorch_model-00015-of-00031.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45c361f52f766f5a0e3ff8fc87f75b0541bef7a3a5adfb07451829a48364c5dd
+size 407924624

pytorch_model-00016-of-00031.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43155d731326437310a7e8877bc7ca95f4c6de770123dd6c306453b58a15fdba
+size 407924624

pytorch_model-00017-of-00031.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f313e2fe2222183db6a5d467e900b760a9dbb1d51ab172767797ba47eb560b79
+size 407924624

pytorch_model-00018-of-00031.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f159de1e43b14bcbe3390cf8dc965e5fe9af77efcaa8fd42cf506a88acc7cdd3
+size 407924624

pytorch_model-00019-of-00031.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a584f2f8065749353290feaf86c0b4a40b2915a00ff780e310652bb5d659258b
+size 407924624

pytorch_model-00020-of-00031.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96bd5ffb033615ba4009e2bc2d48071569a4b4c86b2a7eade25b3117c213d82e
+size 407924624

pytorch_model-00021-of-00031.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41a66e633886d6c7742af7891898c60a8eaf34a1bf8a1c03e5bceea432ee9c47
+size 407924624

pytorch_model-00022-of-00031.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:726d314e0a06ebb10d173839158dc86186a75e5538a0fe56de63409369256dea
+size 407924624

pytorch_model-00023-of-00031.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d592386a5825274f51b488e643de37c8c71f6cb4a4c646611373ab1c55f98a9a
+size 407924624

pytorch_model-00024-of-00031.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:505a5153626765410af2d2a19dff8602d2c2c4e3c607004da1ab5b9fd87a4a78
+size 407924624

pytorch_model-00025-of-00031.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1fa1ec4dbee68de40278527cfdc56cfee80713515452b770c6076f6916e1b00
+size 407924624

pytorch_model-00026-of-00031.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a940c259a74083b4a24301dda5d795cc5858769e6e1c6e4667ec6208bf7a38c9
+size 407924624

pytorch_model-00027-of-00031.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41b9f33004610c3bdf1e6e7eff651b4105c8d11bd97c1559d1e05a8d8b8adfcc
+size 407924624

pytorch_model-00028-of-00031.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8da8f17cbfdae6cab4d0a40a0182346774d3c60ba871cd245fb3eea3369c49a
+size 407924624

pytorch_model-00029-of-00031.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9125da25776b3bbd5305005f5523f64774017551779bf44bd424a6091fa7b589
+size 407924624

pytorch_model-00030-of-00031.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be7a67df6c9161e1ac9469c4fd43c849527be71c6d8c7463eaf4c1dfd1c72a9b
+size 407924624

pytorch_model-00031-of-00031.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13a748b652725af18a2741c36eb9aed67609684c96bdb4740aa237a8aedab41d
+size 532677546

pytorch_model.bin.index.json

@@ -0,0 +1,207 @@
+{
+  "metadata": {
+    "total_size": 12487168064
+  },
+  "weight_map": {
+    "transformer.embedding.word_embeddings.weight": "pytorch_model-00002-of-00031.bin",
+    "transformer.encoder.final_layernorm.weight": "pytorch_model-00030-of-00031.bin",
+    "transformer.encoder.layers.0.input_layernorm.weight": "pytorch_model-00003-of-00031.bin",
+    "transformer.encoder.layers.0.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00031.bin",
+    "transformer.encoder.layers.0.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00031.bin",
+    "transformer.encoder.layers.0.post_attention_layernorm.weight": "pytorch_model-00003-of-00031.bin",
+    "transformer.encoder.layers.0.self_attention.dense.weight": "pytorch_model-00003-of-00031.bin",
+    "transformer.encoder.layers.0.self_attention.query_key_value.bias": "pytorch_model-00003-of-00031.bin",
+    "transformer.encoder.layers.0.self_attention.query_key_value.weight": "pytorch_model-00003-of-00031.bin",
+    "transformer.encoder.layers.1.input_layernorm.weight": "pytorch_model-00003-of-00031.bin",
+    "transformer.encoder.layers.1.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00031.bin",
+    "transformer.encoder.layers.1.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00031.bin",
+    "transformer.encoder.layers.1.post_attention_layernorm.weight": "pytorch_model-00004-of-00031.bin",
+    "transformer.encoder.layers.1.self_attention.dense.weight": "pytorch_model-00004-of-00031.bin",
+    "transformer.encoder.layers.1.self_attention.query_key_value.bias": "pytorch_model-00004-of-00031.bin",
+    "transformer.encoder.layers.1.self_attention.query_key_value.weight": "pytorch_model-00004-of-00031.bin",
+    "transformer.encoder.layers.10.input_layernorm.weight": "pytorch_model-00012-of-00031.bin",
+    "transformer.encoder.layers.10.mlp.dense_4h_to_h.weight": "pytorch_model-00013-of-00031.bin",
+    "transformer.encoder.layers.10.mlp.dense_h_to_4h.weight": "pytorch_model-00013-of-00031.bin",
+    "transformer.encoder.layers.10.post_attention_layernorm.weight": "pytorch_model-00013-of-00031.bin",
+    "transformer.encoder.layers.10.self_attention.dense.weight": "pytorch_model-00013-of-00031.bin",
+    "transformer.encoder.layers.10.self_attention.query_key_value.bias": "pytorch_model-00013-of-00031.bin",
+    "transformer.encoder.layers.10.self_attention.query_key_value.weight": "pytorch_model-00013-of-00031.bin",
+    "transformer.encoder.layers.11.input_layernorm.weight": "pytorch_model-00013-of-00031.bin",
+    "transformer.encoder.layers.11.mlp.dense_4h_to_h.weight": "pytorch_model-00014-of-00031.bin",
+    "transformer.encoder.layers.11.mlp.dense_h_to_4h.weight": "pytorch_model-00014-of-00031.bin",
+    "transformer.encoder.layers.11.post_attention_layernorm.weight": "pytorch_model-00014-of-00031.bin",
+    "transformer.encoder.layers.11.self_attention.dense.weight": "pytorch_model-00014-of-00031.bin",
+    "transformer.encoder.layers.11.self_attention.query_key_value.bias": "pytorch_model-00014-of-00031.bin",
+    "transformer.encoder.layers.11.self_attention.query_key_value.weight": "pytorch_model-00014-of-00031.bin",
+    "transformer.encoder.layers.12.input_layernorm.weight": "pytorch_model-00014-of-00031.bin",
+    "transformer.encoder.layers.12.mlp.dense_4h_to_h.weight": "pytorch_model-00015-of-00031.bin",
+    "transformer.encoder.layers.12.mlp.dense_h_to_4h.weight": "pytorch_model-00015-of-00031.bin",
+    "transformer.encoder.layers.12.post_attention_layernorm.weight": "pytorch_model-00015-of-00031.bin",
+    "transformer.encoder.layers.12.self_attention.dense.weight": "pytorch_model-00015-of-00031.bin",
+    "transformer.encoder.layers.12.self_attention.query_key_value.bias": "pytorch_model-00015-of-00031.bin",
+    "transformer.encoder.layers.12.self_attention.query_key_value.weight": "pytorch_model-00015-of-00031.bin",
+    "transformer.encoder.layers.13.input_layernorm.weight": "pytorch_model-00015-of-00031.bin",
+    "transformer.encoder.layers.13.mlp.dense_4h_to_h.weight": "pytorch_model-00016-of-00031.bin",
+    "transformer.encoder.layers.13.mlp.dense_h_to_4h.weight": "pytorch_model-00016-of-00031.bin",
+    "transformer.encoder.layers.13.post_attention_layernorm.weight": "pytorch_model-00016-of-00031.bin",
+    "transformer.encoder.layers.13.self_attention.dense.weight": "pytorch_model-00016-of-00031.bin",
+    "transformer.encoder.layers.13.self_attention.query_key_value.bias": "pytorch_model-00016-of-00031.bin",
+    "transformer.encoder.layers.13.self_attention.query_key_value.weight": "pytorch_model-00016-of-00031.bin",
+    "transformer.encoder.layers.14.input_layernorm.weight": "pytorch_model-00016-of-00031.bin",
+    "transformer.encoder.layers.14.mlp.dense_4h_to_h.weight": "pytorch_model-00017-of-00031.bin",
+    "transformer.encoder.layers.14.mlp.dense_h_to_4h.weight": "pytorch_model-00017-of-00031.bin",
+    "transformer.encoder.layers.14.post_attention_layernorm.weight": "pytorch_model-00017-of-00031.bin",
+    "transformer.encoder.layers.14.self_attention.dense.weight": "pytorch_model-00017-of-00031.bin",
+    "transformer.encoder.layers.14.self_attention.query_key_value.bias": "pytorch_model-00017-of-00031.bin",
+    "transformer.encoder.layers.14.self_attention.query_key_value.weight": "pytorch_model-00017-of-00031.bin",
+    "transformer.encoder.layers.15.input_layernorm.weight": "pytorch_model-00017-of-00031.bin",
+    "transformer.encoder.layers.15.mlp.dense_4h_to_h.weight": "pytorch_model-00018-of-00031.bin",
+    "transformer.encoder.layers.15.mlp.dense_h_to_4h.weight": "pytorch_model-00018-of-00031.bin",
+    "transformer.encoder.layers.15.post_attention_layernorm.weight": "pytorch_model-00018-of-00031.bin",
+    "transformer.encoder.layers.15.self_attention.dense.weight": "pytorch_model-00018-of-00031.bin",
+    "transformer.encoder.layers.15.self_attention.query_key_value.bias": "pytorch_model-00018-of-00031.bin",
+    "transformer.encoder.layers.15.self_attention.query_key_value.weight": "pytorch_model-00018-of-00031.bin",
+    "transformer.encoder.layers.16.input_layernorm.weight": "pytorch_model-00018-of-00031.bin",
+    "transformer.encoder.layers.16.mlp.dense_4h_to_h.weight": "pytorch_model-00019-of-00031.bin",
+    "transformer.encoder.layers.16.mlp.dense_h_to_4h.weight": "pytorch_model-00019-of-00031.bin",
+    "transformer.encoder.layers.16.post_attention_layernorm.weight": "pytorch_model-00019-of-00031.bin",
+    "transformer.encoder.layers.16.self_attention.dense.weight": "pytorch_model-00019-of-00031.bin",
+    "transformer.encoder.layers.16.self_attention.query_key_value.bias": "pytorch_model-00019-of-00031.bin",
+    "transformer.encoder.layers.16.self_attention.query_key_value.weight": "pytorch_model-00019-of-00031.bin",
+    "transformer.encoder.layers.17.input_layernorm.weight": "pytorch_model-00019-of-00031.bin",
+    "transformer.encoder.layers.17.mlp.dense_4h_to_h.weight": "pytorch_model-00020-of-00031.bin",
+    "transformer.encoder.layers.17.mlp.dense_h_to_4h.weight": "pytorch_model-00020-of-00031.bin",
+    "transformer.encoder.layers.17.post_attention_layernorm.weight": "pytorch_model-00020-of-00031.bin",
+    "transformer.encoder.layers.17.self_attention.dense.weight": "pytorch_model-00020-of-00031.bin",
+    "transformer.encoder.layers.17.self_attention.query_key_value.bias": "pytorch_model-00020-of-00031.bin",
+    "transformer.encoder.layers.17.self_attention.query_key_value.weight": "pytorch_model-00020-of-00031.bin",
+    "transformer.encoder.layers.18.input_layernorm.weight": "pytorch_model-00020-of-00031.bin",
+    "transformer.encoder.layers.18.mlp.dense_4h_to_h.weight": "pytorch_model-00021-of-00031.bin",
+    "transformer.encoder.layers.18.mlp.dense_h_to_4h.weight": "pytorch_model-00021-of-00031.bin",
+    "transformer.encoder.layers.18.post_attention_layernorm.weight": "pytorch_model-00021-of-00031.bin",
+    "transformer.encoder.layers.18.self_attention.dense.weight": "pytorch_model-00021-of-00031.bin",
+    "transformer.encoder.layers.18.self_attention.query_key_value.bias": "pytorch_model-00021-of-00031.bin",
+    "transformer.encoder.layers.18.self_attention.query_key_value.weight": "pytorch_model-00021-of-00031.bin",
+    "transformer.encoder.layers.19.input_layernorm.weight": "pytorch_model-00021-of-00031.bin",
+    "transformer.encoder.layers.19.mlp.dense_4h_to_h.weight": "pytorch_model-00022-of-00031.bin",
+    "transformer.encoder.layers.19.mlp.dense_h_to_4h.weight": "pytorch_model-00022-of-00031.bin",
+    "transformer.encoder.layers.19.post_attention_layernorm.weight": "pytorch_model-00022-of-00031.bin",
+    "transformer.encoder.layers.19.self_attention.dense.weight": "pytorch_model-00022-of-00031.bin",
+    "transformer.encoder.layers.19.self_attention.query_key_value.bias": "pytorch_model-00022-of-00031.bin",
+    "transformer.encoder.layers.19.self_attention.query_key_value.weight": "pytorch_model-00022-of-00031.bin",
+    "transformer.encoder.layers.2.input_layernorm.weight": "pytorch_model-00004-of-00031.bin",
+    "transformer.encoder.layers.2.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00031.bin",
+    "transformer.encoder.layers.2.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00031.bin",
+    "transformer.encoder.layers.2.post_attention_layernorm.weight": "pytorch_model-00005-of-00031.bin",
+    "transformer.encoder.layers.2.self_attention.dense.weight": "pytorch_model-00005-of-00031.bin",
+    "transformer.encoder.layers.2.self_attention.query_key_value.bias": "pytorch_model-00005-of-00031.bin",
+    "transformer.encoder.layers.2.self_attention.query_key_value.weight": "pytorch_model-00005-of-00031.bin",
+    "transformer.encoder.layers.20.input_layernorm.weight": "pytorch_model-00022-of-00031.bin",
+    "transformer.encoder.layers.20.mlp.dense_4h_to_h.weight": "pytorch_model-00023-of-00031.bin",
+    "transformer.encoder.layers.20.mlp.dense_h_to_4h.weight": "pytorch_model-00023-of-00031.bin",
+    "transformer.encoder.layers.20.post_attention_layernorm.weight": "pytorch_model-00023-of-00031.bin",
+    "transformer.encoder.layers.20.self_attention.dense.weight": "pytorch_model-00023-of-00031.bin",
+    "transformer.encoder.layers.20.self_attention.query_key_value.bias": "pytorch_model-00023-of-00031.bin",
+    "transformer.encoder.layers.20.self_attention.query_key_value.weight": "pytorch_model-00023-of-00031.bin",
+    "transformer.encoder.layers.21.input_layernorm.weight": "pytorch_model-00023-of-00031.bin",
+    "transformer.encoder.layers.21.mlp.dense_4h_to_h.weight": "pytorch_model-00024-of-00031.bin",
+    "transformer.encoder.layers.21.mlp.dense_h_to_4h.weight": "pytorch_model-00024-of-00031.bin",
+    "transformer.encoder.layers.21.post_attention_layernorm.weight": "pytorch_model-00024-of-00031.bin",
+    "transformer.encoder.layers.21.self_attention.dense.weight": "pytorch_model-00024-of-00031.bin",
+    "transformer.encoder.layers.21.self_attention.query_key_value.bias": "pytorch_model-00024-of-00031.bin",
+    "transformer.encoder.layers.21.self_attention.query_key_value.weight": "pytorch_model-00024-of-00031.bin",
+    "transformer.encoder.layers.22.input_layernorm.weight": "pytorch_model-00024-of-00031.bin",
+    "transformer.encoder.layers.22.mlp.dense_4h_to_h.weight": "pytorch_model-00025-of-00031.bin",
+    "transformer.encoder.layers.22.mlp.dense_h_to_4h.weight": "pytorch_model-00025-of-00031.bin",
+    "transformer.encoder.layers.22.post_attention_layernorm.weight": "pytorch_model-00025-of-00031.bin",
+    "transformer.encoder.layers.22.self_attention.dense.weight": "pytorch_model-00025-of-00031.bin",
+    "transformer.encoder.layers.22.self_attention.query_key_value.bias": "pytorch_model-00025-of-00031.bin",
+    "transformer.encoder.layers.22.self_attention.query_key_value.weight": "pytorch_model-00025-of-00031.bin",
+    "transformer.encoder.layers.23.input_layernorm.weight": "pytorch_model-00025-of-00031.bin",
+    "transformer.encoder.layers.23.mlp.dense_4h_to_h.weight": "pytorch_model-00026-of-00031.bin",
+    "transformer.encoder.layers.23.mlp.dense_h_to_4h.weight": "pytorch_model-00026-of-00031.bin",
+    "transformer.encoder.layers.23.post_attention_layernorm.weight": "pytorch_model-00026-of-00031.bin",
+    "transformer.encoder.layers.23.self_attention.dense.weight": "pytorch_model-00026-of-00031.bin",
+    "transformer.encoder.layers.23.self_attention.query_key_value.bias": "pytorch_model-00026-of-00031.bin",
+    "transformer.encoder.layers.23.self_attention.query_key_value.weight": "pytorch_model-00026-of-00031.bin",
+    "transformer.encoder.layers.24.input_layernorm.weight": "pytorch_model-00026-of-00031.bin",
+    "transformer.encoder.layers.24.mlp.dense_4h_to_h.weight": "pytorch_model-00027-of-00031.bin",
+    "transformer.encoder.layers.24.mlp.dense_h_to_4h.weight": "pytorch_model-00027-of-00031.bin",
+    "transformer.encoder.layers.24.post_attention_layernorm.weight": "pytorch_model-00027-of-00031.bin",
+    "transformer.encoder.layers.24.self_attention.dense.weight": "pytorch_model-00027-of-00031.bin",
+    "transformer.encoder.layers.24.self_attention.query_key_value.bias": "pytorch_model-00027-of-00031.bin",
+    "transformer.encoder.layers.24.self_attention.query_key_value.weight": "pytorch_model-00027-of-00031.bin",
+    "transformer.encoder.layers.25.input_layernorm.weight": "pytorch_model-00027-of-00031.bin",
+    "transformer.encoder.layers.25.mlp.dense_4h_to_h.weight": "pytorch_model-00028-of-00031.bin",
+    "transformer.encoder.layers.25.mlp.dense_h_to_4h.weight": "pytorch_model-00028-of-00031.bin",
+    "transformer.encoder.layers.25.post_attention_layernorm.weight": "pytorch_model-00028-of-00031.bin",
+    "transformer.encoder.layers.25.self_attention.dense.weight": "pytorch_model-00028-of-00031.bin",
+    "transformer.encoder.layers.25.self_attention.query_key_value.bias": "pytorch_model-00028-of-00031.bin",
+    "transformer.encoder.layers.25.self_attention.query_key_value.weight": "pytorch_model-00028-of-00031.bin",
+    "transformer.encoder.layers.26.input_layernorm.weight": "pytorch_model-00028-of-00031.bin",
+    "transformer.encoder.layers.26.mlp.dense_4h_to_h.weight": "pytorch_model-00029-of-00031.bin",
+    "transformer.encoder.layers.26.mlp.dense_h_to_4h.weight": "pytorch_model-00029-of-00031.bin",
+    "transformer.encoder.layers.26.post_attention_layernorm.weight": "pytorch_model-00029-of-00031.bin",
+    "transformer.encoder.layers.26.self_attention.dense.weight": "pytorch_model-00029-of-00031.bin",
+    "transformer.encoder.layers.26.self_attention.query_key_value.bias": "pytorch_model-00029-of-00031.bin",
+    "transformer.encoder.layers.26.self_attention.query_key_value.weight": "pytorch_model-00029-of-00031.bin",
+    "transformer.encoder.layers.27.input_layernorm.weight": "pytorch_model-00029-of-00031.bin",
+    "transformer.encoder.layers.27.mlp.dense_4h_to_h.weight": "pytorch_model-00030-of-00031.bin",
+    "transformer.encoder.layers.27.mlp.dense_h_to_4h.weight": "pytorch_model-00030-of-00031.bin",
+    "transformer.encoder.layers.27.post_attention_layernorm.weight": "pytorch_model-00030-of-00031.bin",
+    "transformer.encoder.layers.27.self_attention.dense.weight": "pytorch_model-00030-of-00031.bin",
+    "transformer.encoder.layers.27.self_attention.query_key_value.bias": "pytorch_model-00030-of-00031.bin",
+    "transformer.encoder.layers.27.self_attention.query_key_value.weight": "pytorch_model-00030-of-00031.bin",
+    "transformer.encoder.layers.3.input_layernorm.weight": "pytorch_model-00005-of-00031.bin",
+    "transformer.encoder.layers.3.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00031.bin",
+    "transformer.encoder.layers.3.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00031.bin",
+    "transformer.encoder.layers.3.post_attention_layernorm.weight": "pytorch_model-00006-of-00031.bin",
+    "transformer.encoder.layers.3.self_attention.dense.weight": "pytorch_model-00006-of-00031.bin",
+    "transformer.encoder.layers.3.self_attention.query_key_value.bias": "pytorch_model-00006-of-00031.bin",
+    "transformer.encoder.layers.3.self_attention.query_key_value.weight": "pytorch_model-00006-of-00031.bin",
+    "transformer.encoder.layers.4.input_layernorm.weight": "pytorch_model-00006-of-00031.bin",
+    "transformer.encoder.layers.4.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00031.bin",
+    "transformer.encoder.layers.4.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00031.bin",
+    "transformer.encoder.layers.4.post_attention_layernorm.weight": "pytorch_model-00007-of-00031.bin",
+    "transformer.encoder.layers.4.self_attention.dense.weight": "pytorch_model-00007-of-00031.bin",
+    "transformer.encoder.layers.4.self_attention.query_key_value.bias": "pytorch_model-00007-of-00031.bin",
+    "transformer.encoder.layers.4.self_attention.query_key_value.weight": "pytorch_model-00007-of-00031.bin",
+    "transformer.encoder.layers.5.input_layernorm.weight": "pytorch_model-00007-of-00031.bin",
+    "transformer.encoder.layers.5.mlp.dense_4h_to_h.weight": "pytorch_model-00008-of-00031.bin",
+    "transformer.encoder.layers.5.mlp.dense_h_to_4h.weight": "pytorch_model-00008-of-00031.bin",
+    "transformer.encoder.layers.5.post_attention_layernorm.weight": "pytorch_model-00008-of-00031.bin",
+    "transformer.encoder.layers.5.self_attention.dense.weight": "pytorch_model-00008-of-00031.bin",
+    "transformer.encoder.layers.5.self_attention.query_key_value.bias": "pytorch_model-00008-of-00031.bin",
+    "transformer.encoder.layers.5.self_attention.query_key_value.weight": "pytorch_model-00008-of-00031.bin",
+    "transformer.encoder.layers.6.input_layernorm.weight": "pytorch_model-00008-of-00031.bin",
+    "transformer.encoder.layers.6.mlp.dense_4h_to_h.weight": "pytorch_model-00009-of-00031.bin",
+    "transformer.encoder.layers.6.mlp.dense_h_to_4h.weight": "pytorch_model-00009-of-00031.bin",
+    "transformer.encoder.layers.6.post_attention_layernorm.weight": "pytorch_model-00009-of-00031.bin",
+    "transformer.encoder.layers.6.self_attention.dense.weight": "pytorch_model-00009-of-00031.bin",
+    "transformer.encoder.layers.6.self_attention.query_key_value.bias": "pytorch_model-00009-of-00031.bin",
+    "transformer.encoder.layers.6.self_attention.query_key_value.weight": "pytorch_model-00009-of-00031.bin",
+    "transformer.encoder.layers.7.input_layernorm.weight": "pytorch_model-00009-of-00031.bin",
+    "transformer.encoder.layers.7.mlp.dense_4h_to_h.weight": "pytorch_model-00010-of-00031.bin",
+    "transformer.encoder.layers.7.mlp.dense_h_to_4h.weight": "pytorch_model-00010-of-00031.bin",
+    "transformer.encoder.layers.7.post_attention_layernorm.weight": "pytorch_model-00010-of-00031.bin",
+    "transformer.encoder.layers.7.self_attention.dense.weight": "pytorch_model-00010-of-00031.bin",
+    "transformer.encoder.layers.7.self_attention.query_key_value.bias": "pytorch_model-00010-of-00031.bin",
+    "transformer.encoder.layers.7.self_attention.query_key_value.weight": "pytorch_model-00010-of-00031.bin",
+    "transformer.encoder.layers.8.input_layernorm.weight": "pytorch_model-00010-of-00031.bin",
+    "transformer.encoder.layers.8.mlp.dense_4h_to_h.weight": "pytorch_model-00011-of-00031.bin",
+    "transformer.encoder.layers.8.mlp.dense_h_to_4h.weight": "pytorch_model-00011-of-00031.bin",
+    "transformer.encoder.layers.8.post_attention_layernorm.weight": "pytorch_model-00011-of-00031.bin",
+    "transformer.encoder.layers.8.self_attention.dense.weight": "pytorch_model-00011-of-00031.bin",
+    "transformer.encoder.layers.8.self_attention.query_key_value.bias": "pytorch_model-00011-of-00031.bin",
+    "transformer.encoder.layers.8.self_attention.query_key_value.weight": "pytorch_model-00011-of-00031.bin",
+    "transformer.encoder.layers.9.input_layernorm.weight": "pytorch_model-00011-of-00031.bin",
+    "transformer.encoder.layers.9.mlp.dense_4h_to_h.weight": "pytorch_model-00012-of-00031.bin",
+    "transformer.encoder.layers.9.mlp.dense_h_to_4h.weight": "pytorch_model-00012-of-00031.bin",
+    "transformer.encoder.layers.9.post_attention_layernorm.weight": "pytorch_model-00012-of-00031.bin",
+    "transformer.encoder.layers.9.self_attention.dense.weight": "pytorch_model-00012-of-00031.bin",
+    "transformer.encoder.layers.9.self_attention.query_key_value.bias": "pytorch_model-00012-of-00031.bin",
+    "transformer.encoder.layers.9.self_attention.query_key_value.weight": "pytorch_model-00012-of-00031.bin",
+    "transformer.output_layer.weight": "pytorch_model-00031-of-00031.bin",
+    "transformer.rotary_pos_emb.inv_freq": "pytorch_model-00003-of-00031.bin"
+  }
+}