Upload ChatGLMForConditionalGeneration

README.md

@@ -1,10 +1,4 @@
 ---
-library_name: transformers
-tags:
-- llama-factory
-license: other
-license_name: glm-4
-license_link: https://huggingface.co/THUDM/glm-4v-9b/blob/main/LICENSE
 datasets:
 - jojo0217/korean_rlhf_dataset
 - jojo0217/korean_safe_conversation
@@ -17,7 +11,13 @@ datasets:
 - 4n3mone/vector_bench
 language:
 - ko
+library_name: transformers
+license: other
+license_name: glm-4
+license_link: https://huggingface.co/THUDM/glm-4v-9b/blob/main/LICENSE
 pipeline_tag: text-generation
+tags:
+- llama-factory
 ---
 
 ## Model

config.json

@@ -10,8 +10,8 @@
   "attention_dropout": 0.0,
   "attention_softmax_in_fp32": true,
   "auto_map": {
-    "AutoConfig": "THUDM/glm-4-9b--configuration_chatglm.ChatGLMConfig",
-    "AutoModel": "THUDM/glm-4-9b--modeling_chatglm.ChatGLMForConditionalGeneration",
+    "AutoConfig": "configuration_chatglm.ChatGLMConfig",
+    "AutoModel": "modeling_chatglm.ChatGLMForConditionalGeneration",
     "AutoModelForCausalLM": "THUDM/glm-4-9b--modeling_chatglm.ChatGLMForConditionalGeneration",
     "AutoModelForSeq2SeqLM": "THUDM/glm-4-9b--modeling_chatglm.ChatGLMForConditionalGeneration",
     "AutoModelForSequenceClassification": "THUDM/glm-4-9b--modeling_chatglm.ChatGLMForSequenceClassification"

model-00001-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35f41c95a7d769f3409acf19f79a87a3d00cacc54b7793c9267e8ad2640630c5
+size 1241514144

model-00002-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bb58bd5e2e995cbc57c2a7794989a10c0ef6a771af0d066f78cdd9634968a75
+size 887174816

model-00003-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:190eea50c32591b8a566cce73101a76837cc10fa02d47a46fb72183ccb49ddd4
+size 815845224

model-00004-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ad2874378a6a80a3a395e73b9169b136b241390eec6964a218e39ddd9f2c32c
+size 815845224

model-00005-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c6505cdcb269f10cc0cee05d4dda896b0ac13b23557eabfae052ece255999d7
+size 815845224

model-00006-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d0d14ad88f361525a1a9e2bc4b0564262000f87d46d3bd17cf6e8269bb660d8
+size 815845200

model-00007-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c96c636076c5663daecd68cd505d162bbbce8e6d70ad4ce50665fc9dc7dfe618
+size 815845232

model-00008-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7cacb0c5ed29014c5e11c400b6a20c4aa1e84a754eba3c06ddfb10e37c9d822a
+size 815845232

model-00009-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:464be04c73872b818f3513696a746904f34ab32c7e840a7abcaa30c2a2e90f91
+size 815845232

model-00010-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4e9f13e526bbc32cbdaeab3cb7fc8c7c2e26c6aa92343cd2a8faf9e6d79e28c
+size 815845232

model-00011-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:441feb243e7a15ca45a4500e4caae82e32ae52a2834322742376bb76abb00494
+size 815845232

model-00012-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51f26e8d6317da47e41bf2d51ced01b92a4aaf0e7f78ed9e414bd753f0aadfb0
+size 815845232

model-00013-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a641068da5a734fe934db6cf62dd334d0ca3c2a8a821a29d591b7ec95d1304c1
+size 815845232

model-00014-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0eb55efd1b870b87a700040cc0ab06ad6cd32514b3d2df848d8a4178877a3fab
+size 815845232

model-00015-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88747f14edd3c55f6761fbfe51141060d6585669a1388f989d88fd057479e4f8
+size 815845232

model-00016-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47aaab9d6dfdcfaf532fbc196e50f3bc6e5df90607c70596e50ca5ce2797f757
+size 815845232

model-00017-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95f1b9f6515411178ab64f1dfd31fa29f7d69455a6520463a372575af7bb3b8b
+size 815845232

model-00018-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:689562da25d0d8b7a55f17061078d5b40b42c705de3a8b0dcc7e136ad1b77177
+size 815845232

model-00019-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c0a65249eb87f107eee5c71705d1da3f881c91b601f65b72de0dd4790ad0c54
+size 815845232

model-00020-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8055cff72b021ed54cd3799d04c473bbda8ec9fc4c7bd57ee1c3b57cf55449f7
+size 815845232

model-00021-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c2287e994a34e6b0a6676924da3f7e6e5db8aaf444dcad6d98c89430f174289
+size 744524088

model-00022-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:094d18b12f89e772be812a7551d396816d1a76fccd8a12bea16c20e82dbf7c4f
+size 1241514128

model.safetensors.index.json

@@ -3,289 +3,289 @@
     "total_size": 18799902784
   },
   "weight_map": {
-    "transformer.embedding.word_embeddings.weight": "model-00001-of-00004.safetensors",
-    "transformer.encoder.final_layernorm.weight": "model-00004-of-00004.safetensors",
-    "transformer.encoder.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "transformer.encoder.layers.0.mlp.dense_4h_to_h.weight": "model-00001-of-00004.safetensors",
-    "transformer.encoder.layers.0.mlp.dense_h_to_4h.weight": "model-00001-of-00004.safetensors",
-    "transformer.encoder.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "transformer.encoder.layers.0.self_attention.dense.weight": "model-00001-of-00004.safetensors",
-    "transformer.encoder.layers.0.self_attention.query_key_value.bias": "model-00001-of-00004.safetensors",
-    "transformer.encoder.layers.0.self_attention.query_key_value.weight": "model-00001-of-00004.safetensors",
-    "transformer.encoder.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "transformer.encoder.layers.1.mlp.dense_4h_to_h.weight": "model-00001-of-00004.safetensors",
-    "transformer.encoder.layers.1.mlp.dense_h_to_4h.weight": "model-00001-of-00004.safetensors",
-    "transformer.encoder.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "transformer.encoder.layers.1.self_attention.dense.weight": "model-00001-of-00004.safetensors",
-    "transformer.encoder.layers.1.self_attention.query_key_value.bias": "model-00001-of-00004.safetensors",
-    "transformer.encoder.layers.1.self_attention.query_key_value.weight": "model-00001-of-00004.safetensors",
-    "transformer.encoder.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "transformer.encoder.layers.10.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
-    "transformer.encoder.layers.10.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
-    "transformer.encoder.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "transformer.encoder.layers.10.self_attention.dense.weight": "model-00002-of-00004.safetensors",
-    "transformer.encoder.layers.10.self_attention.query_key_value.bias": "model-00002-of-00004.safetensors",
-    "transformer.encoder.layers.10.self_attention.query_key_value.weight": "model-00002-of-00004.safetensors",
-    "transformer.encoder.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "transformer.encoder.layers.11.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
-    "transformer.encoder.layers.11.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
-    "transformer.encoder.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "transformer.encoder.layers.11.self_attention.dense.weight": "model-00002-of-00004.safetensors",
-    "transformer.encoder.layers.11.self_attention.query_key_value.bias": "model-00002-of-00004.safetensors",
-    "transformer.encoder.layers.11.self_attention.query_key_value.weight": "model-00002-of-00004.safetensors",
-    "transformer.encoder.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "transformer.encoder.layers.12.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
-    "transformer.encoder.layers.12.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
-    "transformer.encoder.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "transformer.encoder.layers.12.self_attention.dense.weight": "model-00002-of-00004.safetensors",
-    "transformer.encoder.layers.12.self_attention.query_key_value.bias": "model-00002-of-00004.safetensors",
-    "transformer.encoder.layers.12.self_attention.query_key_value.weight": "model-00002-of-00004.safetensors",
-    "transformer.encoder.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "transformer.encoder.layers.13.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
-    "transformer.encoder.layers.13.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
-    "transformer.encoder.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "transformer.encoder.layers.13.self_attention.dense.weight": "model-00002-of-00004.safetensors",
-    "transformer.encoder.layers.13.self_attention.query_key_value.bias": "model-00002-of-00004.safetensors",
-    "transformer.encoder.layers.13.self_attention.query_key_value.weight": "model-00002-of-00004.safetensors",
-    "transformer.encoder.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "transformer.encoder.layers.14.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
-    "transformer.encoder.layers.14.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
-    "transformer.encoder.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "transformer.encoder.layers.14.self_attention.dense.weight": "model-00002-of-00004.safetensors",
-    "transformer.encoder.layers.14.self_attention.query_key_value.bias": "model-00002-of-00004.safetensors",
-    "transformer.encoder.layers.14.self_attention.query_key_value.weight": "model-00002-of-00004.safetensors",
-    "transformer.encoder.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "transformer.encoder.layers.15.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
-    "transformer.encoder.layers.15.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
-    "transformer.encoder.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "transformer.encoder.layers.15.self_attention.dense.weight": "model-00002-of-00004.safetensors",
-    "transformer.encoder.layers.15.self_attention.query_key_value.bias": "model-00002-of-00004.safetensors",
-    "transformer.encoder.layers.15.self_attention.query_key_value.weight": "model-00002-of-00004.safetensors",
-    "transformer.encoder.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "transformer.encoder.layers.16.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
-    "transformer.encoder.layers.16.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
-    "transformer.encoder.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "transformer.encoder.layers.16.self_attention.dense.weight": "model-00002-of-00004.safetensors",
-    "transformer.encoder.layers.16.self_attention.query_key_value.bias": "model-00002-of-00004.safetensors",
-    "transformer.encoder.layers.16.self_attention.query_key_value.weight": "model-00002-of-00004.safetensors",
-    "transformer.encoder.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "transformer.encoder.layers.17.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
-    "transformer.encoder.layers.17.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
-    "transformer.encoder.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "transformer.encoder.layers.17.self_attention.dense.weight": "model-00002-of-00004.safetensors",
-    "transformer.encoder.layers.17.self_attention.query_key_value.bias": "model-00002-of-00004.safetensors",
-    "transformer.encoder.layers.17.self_attention.query_key_value.weight": "model-00002-of-00004.safetensors",
-    "transformer.encoder.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "transformer.encoder.layers.18.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
-    "transformer.encoder.layers.18.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
-    "transformer.encoder.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "transformer.encoder.layers.18.self_attention.dense.weight": "model-00002-of-00004.safetensors",
-    "transformer.encoder.layers.18.self_attention.query_key_value.bias": "model-00002-of-00004.safetensors",
-    "transformer.encoder.layers.18.self_attention.query_key_value.weight": "model-00002-of-00004.safetensors",
-    "transformer.encoder.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "transformer.encoder.layers.19.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
-    "transformer.encoder.layers.19.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
-    "transformer.encoder.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "transformer.encoder.layers.19.self_attention.dense.weight": "model-00002-of-00004.safetensors",
-    "transformer.encoder.layers.19.self_attention.query_key_value.bias": "model-00002-of-00004.safetensors",
-    "transformer.encoder.layers.19.self_attention.query_key_value.weight": "model-00002-of-00004.safetensors",
-    "transformer.encoder.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "transformer.encoder.layers.2.mlp.dense_4h_to_h.weight": "model-00001-of-00004.safetensors",
-    "transformer.encoder.layers.2.mlp.dense_h_to_4h.weight": "model-00001-of-00004.safetensors",
-    "transformer.encoder.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "transformer.encoder.layers.2.self_attention.dense.weight": "model-00001-of-00004.safetensors",
-    "transformer.encoder.layers.2.self_attention.query_key_value.bias": "model-00001-of-00004.safetensors",
-    "transformer.encoder.layers.2.self_attention.query_key_value.weight": "model-00001-of-00004.safetensors",
-    "transformer.encoder.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "transformer.encoder.layers.20.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
-    "transformer.encoder.layers.20.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
-    "transformer.encoder.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "transformer.encoder.layers.20.self_attention.dense.weight": "model-00002-of-00004.safetensors",
-    "transformer.encoder.layers.20.self_attention.query_key_value.bias": "model-00002-of-00004.safetensors",
-    "transformer.encoder.layers.20.self_attention.query_key_value.weight": "model-00002-of-00004.safetensors",
-    "transformer.encoder.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "transformer.encoder.layers.21.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
-    "transformer.encoder.layers.21.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
-    "transformer.encoder.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "transformer.encoder.layers.21.self_attention.dense.weight": "model-00002-of-00004.safetensors",
-    "transformer.encoder.layers.21.self_attention.query_key_value.bias": "model-00002-of-00004.safetensors",
-    "transformer.encoder.layers.21.self_attention.query_key_value.weight": "model-00002-of-00004.safetensors",
-    "transformer.encoder.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "transformer.encoder.layers.22.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
-    "transformer.encoder.layers.22.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
-    "transformer.encoder.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "transformer.encoder.layers.22.self_attention.dense.weight": "model-00003-of-00004.safetensors",
-    "transformer.encoder.layers.22.self_attention.query_key_value.bias": "model-00003-of-00004.safetensors",
-    "transformer.encoder.layers.22.self_attention.query_key_value.weight": "model-00003-of-00004.safetensors",
-    "transformer.encoder.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "transformer.encoder.layers.23.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
-    "transformer.encoder.layers.23.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
-    "transformer.encoder.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "transformer.encoder.layers.23.self_attention.dense.weight": "model-00003-of-00004.safetensors",
-    "transformer.encoder.layers.23.self_attention.query_key_value.bias": "model-00003-of-00004.safetensors",
-    "transformer.encoder.layers.23.self_attention.query_key_value.weight": "model-00003-of-00004.safetensors",
-    "transformer.encoder.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "transformer.encoder.layers.24.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
-    "transformer.encoder.layers.24.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
-    "transformer.encoder.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "transformer.encoder.layers.24.self_attention.dense.weight": "model-00003-of-00004.safetensors",
-    "transformer.encoder.layers.24.self_attention.query_key_value.bias": "model-00003-of-00004.safetensors",
-    "transformer.encoder.layers.24.self_attention.query_key_value.weight": "model-00003-of-00004.safetensors",
-    "transformer.encoder.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "transformer.encoder.layers.25.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
-    "transformer.encoder.layers.25.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
-    "transformer.encoder.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "transformer.encoder.layers.25.self_attention.dense.weight": "model-00003-of-00004.safetensors",
-    "transformer.encoder.layers.25.self_attention.query_key_value.bias": "model-00003-of-00004.safetensors",
-    "transformer.encoder.layers.25.self_attention.query_key_value.weight": "model-00003-of-00004.safetensors",
-    "transformer.encoder.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "transformer.encoder.layers.26.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
-    "transformer.encoder.layers.26.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
-    "transformer.encoder.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "transformer.encoder.layers.26.self_attention.dense.weight": "model-00003-of-00004.safetensors",
-    "transformer.encoder.layers.26.self_attention.query_key_value.bias": "model-00003-of-00004.safetensors",
-    "transformer.encoder.layers.26.self_attention.query_key_value.weight": "model-00003-of-00004.safetensors",
-    "transformer.encoder.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "transformer.encoder.layers.27.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
-    "transformer.encoder.layers.27.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
-    "transformer.encoder.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "transformer.encoder.layers.27.self_attention.dense.weight": "model-00003-of-00004.safetensors",
-    "transformer.encoder.layers.27.self_attention.query_key_value.bias": "model-00003-of-00004.safetensors",
-    "transformer.encoder.layers.27.self_attention.query_key_value.weight": "model-00003-of-00004.safetensors",
-    "transformer.encoder.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "transformer.encoder.layers.28.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
-    "transformer.encoder.layers.28.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
-    "transformer.encoder.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "transformer.encoder.layers.28.self_attention.dense.weight": "model-00003-of-00004.safetensors",
-    "transformer.encoder.layers.28.self_attention.query_key_value.bias": "model-00003-of-00004.safetensors",
-    "transformer.encoder.layers.28.self_attention.query_key_value.weight": "model-00003-of-00004.safetensors",
-    "transformer.encoder.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "transformer.encoder.layers.29.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
-    "transformer.encoder.layers.29.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
-    "transformer.encoder.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "transformer.encoder.layers.29.self_attention.dense.weight": "model-00003-of-00004.safetensors",
-    "transformer.encoder.layers.29.self_attention.query_key_value.bias": "model-00003-of-00004.safetensors",
-    "transformer.encoder.layers.29.self_attention.query_key_value.weight": "model-00003-of-00004.safetensors",
-    "transformer.encoder.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "transformer.encoder.layers.3.mlp.dense_4h_to_h.weight": "model-00001-of-00004.safetensors",
-    "transformer.encoder.layers.3.mlp.dense_h_to_4h.weight": "model-00001-of-00004.safetensors",
-    "transformer.encoder.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "transformer.encoder.layers.3.self_attention.dense.weight": "model-00001-of-00004.safetensors",
-    "transformer.encoder.layers.3.self_attention.query_key_value.bias": "model-00001-of-00004.safetensors",
-    "transformer.encoder.layers.3.self_attention.query_key_value.weight": "model-00001-of-00004.safetensors",
-    "transformer.encoder.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "transformer.encoder.layers.30.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
-    "transformer.encoder.layers.30.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
-    "transformer.encoder.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "transformer.encoder.layers.30.self_attention.dense.weight": "model-00003-of-00004.safetensors",
-    "transformer.encoder.layers.30.self_attention.query_key_value.bias": "model-00003-of-00004.safetensors",
-    "transformer.encoder.layers.30.self_attention.query_key_value.weight": "model-00003-of-00004.safetensors",
-    "transformer.encoder.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "transformer.encoder.layers.31.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
-    "transformer.encoder.layers.31.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
-    "transformer.encoder.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "transformer.encoder.layers.31.self_attention.dense.weight": "model-00003-of-00004.safetensors",
-    "transformer.encoder.layers.31.self_attention.query_key_value.bias": "model-00003-of-00004.safetensors",
-    "transformer.encoder.layers.31.self_attention.query_key_value.weight": "model-00003-of-00004.safetensors",
-    "transformer.encoder.layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "transformer.encoder.layers.32.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
-    "transformer.encoder.layers.32.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
-    "transformer.encoder.layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "transformer.encoder.layers.32.self_attention.dense.weight": "model-00003-of-00004.safetensors",
-    "transformer.encoder.layers.32.self_attention.query_key_value.bias": "model-00003-of-00004.safetensors",
-    "transformer.encoder.layers.32.self_attention.query_key_value.weight": "model-00003-of-00004.safetensors",
-    "transformer.encoder.layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "transformer.encoder.layers.33.mlp.dense_4h_to_h.weight": "model-00004-of-00004.safetensors",
-    "transformer.encoder.layers.33.mlp.dense_h_to_4h.weight": "model-00004-of-00004.safetensors",
-    "transformer.encoder.layers.33.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "transformer.encoder.layers.33.self_attention.dense.weight": "model-00003-of-00004.safetensors",
-    "transformer.encoder.layers.33.self_attention.query_key_value.bias": "model-00003-of-00004.safetensors",
-    "transformer.encoder.layers.33.self_attention.query_key_value.weight": "model-00003-of-00004.safetensors",
-    "transformer.encoder.layers.34.input_layernorm.weight": "model-00004-of-00004.safetensors",
-    "transformer.encoder.layers.34.mlp.dense_4h_to_h.weight": "model-00004-of-00004.safetensors",
-    "transformer.encoder.layers.34.mlp.dense_h_to_4h.weight": "model-00004-of-00004.safetensors",
-    "transformer.encoder.layers.34.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
-    "transformer.encoder.layers.34.self_attention.dense.weight": "model-00004-of-00004.safetensors",
-    "transformer.encoder.layers.34.self_attention.query_key_value.bias": "model-00004-of-00004.safetensors",
-    "transformer.encoder.layers.34.self_attention.query_key_value.weight": "model-00004-of-00004.safetensors",
-    "transformer.encoder.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors",
-    "transformer.encoder.layers.35.mlp.dense_4h_to_h.weight": "model-00004-of-00004.safetensors",
-    "transformer.encoder.layers.35.mlp.dense_h_to_4h.weight": "model-00004-of-00004.safetensors",
-    "transformer.encoder.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
-    "transformer.encoder.layers.35.self_attention.dense.weight": "model-00004-of-00004.safetensors",
-    "transformer.encoder.layers.35.self_attention.query_key_value.bias": "model-00004-of-00004.safetensors",
-    "transformer.encoder.layers.35.self_attention.query_key_value.weight": "model-00004-of-00004.safetensors",
-    "transformer.encoder.layers.36.input_layernorm.weight": "model-00004-of-00004.safetensors",
-    "transformer.encoder.layers.36.mlp.dense_4h_to_h.weight": "model-00004-of-00004.safetensors",
-    "transformer.encoder.layers.36.mlp.dense_h_to_4h.weight": "model-00004-of-00004.safetensors",
-    "transformer.encoder.layers.36.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
-    "transformer.encoder.layers.36.self_attention.dense.weight": "model-00004-of-00004.safetensors",
-    "transformer.encoder.layers.36.self_attention.query_key_value.bias": "model-00004-of-00004.safetensors",
-    "transformer.encoder.layers.36.self_attention.query_key_value.weight": "model-00004-of-00004.safetensors",
-    "transformer.encoder.layers.37.input_layernorm.weight": "model-00004-of-00004.safetensors",
-    "transformer.encoder.layers.37.mlp.dense_4h_to_h.weight": "model-00004-of-00004.safetensors",
-    "transformer.encoder.layers.37.mlp.dense_h_to_4h.weight": "model-00004-of-00004.safetensors",
-    "transformer.encoder.layers.37.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
-    "transformer.encoder.layers.37.self_attention.dense.weight": "model-00004-of-00004.safetensors",
-    "transformer.encoder.layers.37.self_attention.query_key_value.bias": "model-00004-of-00004.safetensors",
-    "transformer.encoder.layers.37.self_attention.query_key_value.weight": "model-00004-of-00004.safetensors",
-    "transformer.encoder.layers.38.input_layernorm.weight": "model-00004-of-00004.safetensors",
-    "transformer.encoder.layers.38.mlp.dense_4h_to_h.weight": "model-00004-of-00004.safetensors",
-    "transformer.encoder.layers.38.mlp.dense_h_to_4h.weight": "model-00004-of-00004.safetensors",
-    "transformer.encoder.layers.38.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
-    "transformer.encoder.layers.38.self_attention.dense.weight": "model-00004-of-00004.safetensors",
-    "transformer.encoder.layers.38.self_attention.query_key_value.bias": "model-00004-of-00004.safetensors",
-    "transformer.encoder.layers.38.self_attention.query_key_value.weight": "model-00004-of-00004.safetensors",
-    "transformer.encoder.layers.39.input_layernorm.weight": "model-00004-of-00004.safetensors",
-    "transformer.encoder.layers.39.mlp.dense_4h_to_h.weight": "model-00004-of-00004.safetensors",
-    "transformer.encoder.layers.39.mlp.dense_h_to_4h.weight": "model-00004-of-00004.safetensors",
-    "transformer.encoder.layers.39.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
-    "transformer.encoder.layers.39.self_attention.dense.weight": "model-00004-of-00004.safetensors",
-    "transformer.encoder.layers.39.self_attention.query_key_value.bias": "model-00004-of-00004.safetensors",
-    "transformer.encoder.layers.39.self_attention.query_key_value.weight": "model-00004-of-00004.safetensors",
-    "transformer.encoder.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "transformer.encoder.layers.4.mlp.dense_4h_to_h.weight": "model-00001-of-00004.safetensors",
-    "transformer.encoder.layers.4.mlp.dense_h_to_4h.weight": "model-00001-of-00004.safetensors",
-    "transformer.encoder.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "transformer.encoder.layers.4.self_attention.dense.weight": "model-00001-of-00004.safetensors",
-    "transformer.encoder.layers.4.self_attention.query_key_value.bias": "model-00001-of-00004.safetensors",
-    "transformer.encoder.layers.4.self_attention.query_key_value.weight": "model-00001-of-00004.safetensors",
-    "transformer.encoder.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "transformer.encoder.layers.5.mlp.dense_4h_to_h.weight": "model-00001-of-00004.safetensors",
-    "transformer.encoder.layers.5.mlp.dense_h_to_4h.weight": "model-00001-of-00004.safetensors",
-    "transformer.encoder.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "transformer.encoder.layers.5.self_attention.dense.weight": "model-00001-of-00004.safetensors",
-    "transformer.encoder.layers.5.self_attention.query_key_value.bias": "model-00001-of-00004.safetensors",
-    "transformer.encoder.layers.5.self_attention.query_key_value.weight": "model-00001-of-00004.safetensors",
-    "transformer.encoder.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "transformer.encoder.layers.6.mlp.dense_4h_to_h.weight": "model-00001-of-00004.safetensors",
-    "transformer.encoder.layers.6.mlp.dense_h_to_4h.weight": "model-00001-of-00004.safetensors",
-    "transformer.encoder.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "transformer.encoder.layers.6.self_attention.dense.weight": "model-00001-of-00004.safetensors",
-    "transformer.encoder.layers.6.self_attention.query_key_value.bias": "model-00001-of-00004.safetensors",
-    "transformer.encoder.layers.6.self_attention.query_key_value.weight": "model-00001-of-00004.safetensors",
-    "transformer.encoder.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "transformer.encoder.layers.7.mlp.dense_4h_to_h.weight": "model-00001-of-00004.safetensors",
-    "transformer.encoder.layers.7.mlp.dense_h_to_4h.weight": "model-00001-of-00004.safetensors",
-    "transformer.encoder.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "transformer.encoder.layers.7.self_attention.dense.weight": "model-00001-of-00004.safetensors",
-    "transformer.encoder.layers.7.self_attention.query_key_value.bias": "model-00001-of-00004.safetensors",
-    "transformer.encoder.layers.7.self_attention.query_key_value.weight": "model-00001-of-00004.safetensors",
-    "transformer.encoder.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "transformer.encoder.layers.8.mlp.dense_4h_to_h.weight": "model-00001-of-00004.safetensors",
-    "transformer.encoder.layers.8.mlp.dense_h_to_4h.weight": "model-00001-of-00004.safetensors",
-    "transformer.encoder.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "transformer.encoder.layers.8.self_attention.dense.weight": "model-00001-of-00004.safetensors",
-    "transformer.encoder.layers.8.self_attention.query_key_value.bias": "model-00001-of-00004.safetensors",
-    "transformer.encoder.layers.8.self_attention.query_key_value.weight": "model-00001-of-00004.safetensors",
-    "transformer.encoder.layers.9.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "transformer.encoder.layers.9.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
-    "transformer.encoder.layers.9.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
-    "transformer.encoder.layers.9.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "transformer.encoder.layers.9.self_attention.dense.weight": "model-00001-of-00004.safetensors",
-    "transformer.encoder.layers.9.self_attention.query_key_value.bias": "model-00001-of-00004.safetensors",
-    "transformer.encoder.layers.9.self_attention.query_key_value.weight": "model-00001-of-00004.safetensors",
-    "transformer.output_layer.weight": "model-00004-of-00004.safetensors",
-    "transformer.rotary_pos_emb.inv_freq": "model-00001-of-00004.safetensors"
+    "transformer.embedding.word_embeddings.weight": "model-00001-of-00022.safetensors",
+    "transformer.encoder.final_layernorm.weight": "model-00021-of-00022.safetensors",
+    "transformer.encoder.layers.0.input_layernorm.weight": "model-00002-of-00022.safetensors",
+    "transformer.encoder.layers.0.mlp.dense_4h_to_h.weight": "model-00002-of-00022.safetensors",
+    "transformer.encoder.layers.0.mlp.dense_h_to_4h.weight": "model-00002-of-00022.safetensors",
+    "transformer.encoder.layers.0.post_attention_layernorm.weight": "model-00002-of-00022.safetensors",
+    "transformer.encoder.layers.0.self_attention.dense.weight": "model-00002-of-00022.safetensors",
+    "transformer.encoder.layers.0.self_attention.query_key_value.bias": "model-00002-of-00022.safetensors",
+    "transformer.encoder.layers.0.self_attention.query_key_value.weight": "model-00002-of-00022.safetensors",
+    "transformer.encoder.layers.1.input_layernorm.weight": "model-00002-of-00022.safetensors",
+    "transformer.encoder.layers.1.mlp.dense_4h_to_h.weight": "model-00002-of-00022.safetensors",
+    "transformer.encoder.layers.1.mlp.dense_h_to_4h.weight": "model-00002-of-00022.safetensors",
+    "transformer.encoder.layers.1.post_attention_layernorm.weight": "model-00002-of-00022.safetensors",
+    "transformer.encoder.layers.1.self_attention.dense.weight": "model-00002-of-00022.safetensors",
+    "transformer.encoder.layers.1.self_attention.query_key_value.bias": "model-00002-of-00022.safetensors",
+    "transformer.encoder.layers.1.self_attention.query_key_value.weight": "model-00002-of-00022.safetensors",
+    "transformer.encoder.layers.10.input_layernorm.weight": "model-00006-of-00022.safetensors",
+    "transformer.encoder.layers.10.mlp.dense_4h_to_h.weight": "model-00007-of-00022.safetensors",
+    "transformer.encoder.layers.10.mlp.dense_h_to_4h.weight": "model-00007-of-00022.safetensors",
+    "transformer.encoder.layers.10.post_attention_layernorm.weight": "model-00006-of-00022.safetensors",
+    "transformer.encoder.layers.10.self_attention.dense.weight": "model-00006-of-00022.safetensors",
+    "transformer.encoder.layers.10.self_attention.query_key_value.bias": "model-00006-of-00022.safetensors",
+    "transformer.encoder.layers.10.self_attention.query_key_value.weight": "model-00006-of-00022.safetensors",
+    "transformer.encoder.layers.11.input_layernorm.weight": "model-00007-of-00022.safetensors",
+    "transformer.encoder.layers.11.mlp.dense_4h_to_h.weight": "model-00007-of-00022.safetensors",
+    "transformer.encoder.layers.11.mlp.dense_h_to_4h.weight": "model-00007-of-00022.safetensors",
+    "transformer.encoder.layers.11.post_attention_layernorm.weight": "model-00007-of-00022.safetensors",
+    "transformer.encoder.layers.11.self_attention.dense.weight": "model-00007-of-00022.safetensors",
+    "transformer.encoder.layers.11.self_attention.query_key_value.bias": "model-00007-of-00022.safetensors",
+    "transformer.encoder.layers.11.self_attention.query_key_value.weight": "model-00007-of-00022.safetensors",
+    "transformer.encoder.layers.12.input_layernorm.weight": "model-00007-of-00022.safetensors",
+    "transformer.encoder.layers.12.mlp.dense_4h_to_h.weight": "model-00008-of-00022.safetensors",
+    "transformer.encoder.layers.12.mlp.dense_h_to_4h.weight": "model-00008-of-00022.safetensors",
+    "transformer.encoder.layers.12.post_attention_layernorm.weight": "model-00007-of-00022.safetensors",
+    "transformer.encoder.layers.12.self_attention.dense.weight": "model-00007-of-00022.safetensors",
+    "transformer.encoder.layers.12.self_attention.query_key_value.bias": "model-00007-of-00022.safetensors",
+    "transformer.encoder.layers.12.self_attention.query_key_value.weight": "model-00007-of-00022.safetensors",
+    "transformer.encoder.layers.13.input_layernorm.weight": "model-00008-of-00022.safetensors",
+    "transformer.encoder.layers.13.mlp.dense_4h_to_h.weight": "model-00008-of-00022.safetensors",
+    "transformer.encoder.layers.13.mlp.dense_h_to_4h.weight": "model-00008-of-00022.safetensors",
+    "transformer.encoder.layers.13.post_attention_layernorm.weight": "model-00008-of-00022.safetensors",
+    "transformer.encoder.layers.13.self_attention.dense.weight": "model-00008-of-00022.safetensors",
+    "transformer.encoder.layers.13.self_attention.query_key_value.bias": "model-00008-of-00022.safetensors",
+    "transformer.encoder.layers.13.self_attention.query_key_value.weight": "model-00008-of-00022.safetensors",
+    "transformer.encoder.layers.14.input_layernorm.weight": "model-00008-of-00022.safetensors",
+    "transformer.encoder.layers.14.mlp.dense_4h_to_h.weight": "model-00009-of-00022.safetensors",
+    "transformer.encoder.layers.14.mlp.dense_h_to_4h.weight": "model-00009-of-00022.safetensors",
+    "transformer.encoder.layers.14.post_attention_layernorm.weight": "model-00008-of-00022.safetensors",
+    "transformer.encoder.layers.14.self_attention.dense.weight": "model-00008-of-00022.safetensors",
+    "transformer.encoder.layers.14.self_attention.query_key_value.bias": "model-00008-of-00022.safetensors",
+    "transformer.encoder.layers.14.self_attention.query_key_value.weight": "model-00008-of-00022.safetensors",
+    "transformer.encoder.layers.15.input_layernorm.weight": "model-00009-of-00022.safetensors",
+    "transformer.encoder.layers.15.mlp.dense_4h_to_h.weight": "model-00009-of-00022.safetensors",
+    "transformer.encoder.layers.15.mlp.dense_h_to_4h.weight": "model-00009-of-00022.safetensors",
+    "transformer.encoder.layers.15.post_attention_layernorm.weight": "model-00009-of-00022.safetensors",
+    "transformer.encoder.layers.15.self_attention.dense.weight": "model-00009-of-00022.safetensors",
+    "transformer.encoder.layers.15.self_attention.query_key_value.bias": "model-00009-of-00022.safetensors",
+    "transformer.encoder.layers.15.self_attention.query_key_value.weight": "model-00009-of-00022.safetensors",
+    "transformer.encoder.layers.16.input_layernorm.weight": "model-00009-of-00022.safetensors",
+    "transformer.encoder.layers.16.mlp.dense_4h_to_h.weight": "model-00010-of-00022.safetensors",
+    "transformer.encoder.layers.16.mlp.dense_h_to_4h.weight": "model-00010-of-00022.safetensors",
+    "transformer.encoder.layers.16.post_attention_layernorm.weight": "model-00009-of-00022.safetensors",
+    "transformer.encoder.layers.16.self_attention.dense.weight": "model-00009-of-00022.safetensors",
+    "transformer.encoder.layers.16.self_attention.query_key_value.bias": "model-00009-of-00022.safetensors",
+    "transformer.encoder.layers.16.self_attention.query_key_value.weight": "model-00009-of-00022.safetensors",
+    "transformer.encoder.layers.17.input_layernorm.weight": "model-00010-of-00022.safetensors",
+    "transformer.encoder.layers.17.mlp.dense_4h_to_h.weight": "model-00010-of-00022.safetensors",
+    "transformer.encoder.layers.17.mlp.dense_h_to_4h.weight": "model-00010-of-00022.safetensors",
+    "transformer.encoder.layers.17.post_attention_layernorm.weight": "model-00010-of-00022.safetensors",
+    "transformer.encoder.layers.17.self_attention.dense.weight": "model-00010-of-00022.safetensors",
+    "transformer.encoder.layers.17.self_attention.query_key_value.bias": "model-00010-of-00022.safetensors",
+    "transformer.encoder.layers.17.self_attention.query_key_value.weight": "model-00010-of-00022.safetensors",
+    "transformer.encoder.layers.18.input_layernorm.weight": "model-00010-of-00022.safetensors",
+    "transformer.encoder.layers.18.mlp.dense_4h_to_h.weight": "model-00011-of-00022.safetensors",
+    "transformer.encoder.layers.18.mlp.dense_h_to_4h.weight": "model-00011-of-00022.safetensors",
+    "transformer.encoder.layers.18.post_attention_layernorm.weight": "model-00010-of-00022.safetensors",
+    "transformer.encoder.layers.18.self_attention.dense.weight": "model-00010-of-00022.safetensors",
+    "transformer.encoder.layers.18.self_attention.query_key_value.bias": "model-00010-of-00022.safetensors",
+    "transformer.encoder.layers.18.self_attention.query_key_value.weight": "model-00010-of-00022.safetensors",
+    "transformer.encoder.layers.19.input_layernorm.weight": "model-00011-of-00022.safetensors",
+    "transformer.encoder.layers.19.mlp.dense_4h_to_h.weight": "model-00011-of-00022.safetensors",
+    "transformer.encoder.layers.19.mlp.dense_h_to_4h.weight": "model-00011-of-00022.safetensors",
+    "transformer.encoder.layers.19.post_attention_layernorm.weight": "model-00011-of-00022.safetensors",
+    "transformer.encoder.layers.19.self_attention.dense.weight": "model-00011-of-00022.safetensors",
+    "transformer.encoder.layers.19.self_attention.query_key_value.bias": "model-00011-of-00022.safetensors",
+    "transformer.encoder.layers.19.self_attention.query_key_value.weight": "model-00011-of-00022.safetensors",
+    "transformer.encoder.layers.2.input_layernorm.weight": "model-00002-of-00022.safetensors",
+    "transformer.encoder.layers.2.mlp.dense_4h_to_h.weight": "model-00003-of-00022.safetensors",
+    "transformer.encoder.layers.2.mlp.dense_h_to_4h.weight": "model-00003-of-00022.safetensors",
+    "transformer.encoder.layers.2.post_attention_layernorm.weight": "model-00002-of-00022.safetensors",
+    "transformer.encoder.layers.2.self_attention.dense.weight": "model-00002-of-00022.safetensors",
+    "transformer.encoder.layers.2.self_attention.query_key_value.bias": "model-00002-of-00022.safetensors",
+    "transformer.encoder.layers.2.self_attention.query_key_value.weight": "model-00002-of-00022.safetensors",
+    "transformer.encoder.layers.20.input_layernorm.weight": "model-00011-of-00022.safetensors",
+    "transformer.encoder.layers.20.mlp.dense_4h_to_h.weight": "model-00012-of-00022.safetensors",
+    "transformer.encoder.layers.20.mlp.dense_h_to_4h.weight": "model-00012-of-00022.safetensors",
+    "transformer.encoder.layers.20.post_attention_layernorm.weight": "model-00011-of-00022.safetensors",
+    "transformer.encoder.layers.20.self_attention.dense.weight": "model-00011-of-00022.safetensors",
+    "transformer.encoder.layers.20.self_attention.query_key_value.bias": "model-00011-of-00022.safetensors",
+    "transformer.encoder.layers.20.self_attention.query_key_value.weight": "model-00011-of-00022.safetensors",
+    "transformer.encoder.layers.21.input_layernorm.weight": "model-00012-of-00022.safetensors",
+    "transformer.encoder.layers.21.mlp.dense_4h_to_h.weight": "model-00012-of-00022.safetensors",
+    "transformer.encoder.layers.21.mlp.dense_h_to_4h.weight": "model-00012-of-00022.safetensors",
+    "transformer.encoder.layers.21.post_attention_layernorm.weight": "model-00012-of-00022.safetensors",
+    "transformer.encoder.layers.21.self_attention.dense.weight": "model-00012-of-00022.safetensors",
+    "transformer.encoder.layers.21.self_attention.query_key_value.bias": "model-00012-of-00022.safetensors",
+    "transformer.encoder.layers.21.self_attention.query_key_value.weight": "model-00012-of-00022.safetensors",
+    "transformer.encoder.layers.22.input_layernorm.weight": "model-00012-of-00022.safetensors",
+    "transformer.encoder.layers.22.mlp.dense_4h_to_h.weight": "model-00013-of-00022.safetensors",
+    "transformer.encoder.layers.22.mlp.dense_h_to_4h.weight": "model-00013-of-00022.safetensors",
+    "transformer.encoder.layers.22.post_attention_layernorm.weight": "model-00012-of-00022.safetensors",
+    "transformer.encoder.layers.22.self_attention.dense.weight": "model-00012-of-00022.safetensors",
+    "transformer.encoder.layers.22.self_attention.query_key_value.bias": "model-00012-of-00022.safetensors",
+    "transformer.encoder.layers.22.self_attention.query_key_value.weight": "model-00012-of-00022.safetensors",
+    "transformer.encoder.layers.23.input_layernorm.weight": "model-00013-of-00022.safetensors",
+    "transformer.encoder.layers.23.mlp.dense_4h_to_h.weight": "model-00013-of-00022.safetensors",
+    "transformer.encoder.layers.23.mlp.dense_h_to_4h.weight": "model-00013-of-00022.safetensors",
+    "transformer.encoder.layers.23.post_attention_layernorm.weight": "model-00013-of-00022.safetensors",
+    "transformer.encoder.layers.23.self_attention.dense.weight": "model-00013-of-00022.safetensors",
+    "transformer.encoder.layers.23.self_attention.query_key_value.bias": "model-00013-of-00022.safetensors",
+    "transformer.encoder.layers.23.self_attention.query_key_value.weight": "model-00013-of-00022.safetensors",
+    "transformer.encoder.layers.24.input_layernorm.weight": "model-00013-of-00022.safetensors",
+    "transformer.encoder.layers.24.mlp.dense_4h_to_h.weight": "model-00014-of-00022.safetensors",
+    "transformer.encoder.layers.24.mlp.dense_h_to_4h.weight": "model-00014-of-00022.safetensors",
+    "transformer.encoder.layers.24.post_attention_layernorm.weight": "model-00013-of-00022.safetensors",
+    "transformer.encoder.layers.24.self_attention.dense.weight": "model-00013-of-00022.safetensors",
+    "transformer.encoder.layers.24.self_attention.query_key_value.bias": "model-00013-of-00022.safetensors",
+    "transformer.encoder.layers.24.self_attention.query_key_value.weight": "model-00013-of-00022.safetensors",
+    "transformer.encoder.layers.25.input_layernorm.weight": "model-00014-of-00022.safetensors",
+    "transformer.encoder.layers.25.mlp.dense_4h_to_h.weight": "model-00014-of-00022.safetensors",
+    "transformer.encoder.layers.25.mlp.dense_h_to_4h.weight": "model-00014-of-00022.safetensors",
+    "transformer.encoder.layers.25.post_attention_layernorm.weight": "model-00014-of-00022.safetensors",
+    "transformer.encoder.layers.25.self_attention.dense.weight": "model-00014-of-00022.safetensors",
+    "transformer.encoder.layers.25.self_attention.query_key_value.bias": "model-00014-of-00022.safetensors",
+    "transformer.encoder.layers.25.self_attention.query_key_value.weight": "model-00014-of-00022.safetensors",
+    "transformer.encoder.layers.26.input_layernorm.weight": "model-00014-of-00022.safetensors",
+    "transformer.encoder.layers.26.mlp.dense_4h_to_h.weight": "model-00015-of-00022.safetensors",
+    "transformer.encoder.layers.26.mlp.dense_h_to_4h.weight": "model-00015-of-00022.safetensors",
+    "transformer.encoder.layers.26.post_attention_layernorm.weight": "model-00014-of-00022.safetensors",
+    "transformer.encoder.layers.26.self_attention.dense.weight": "model-00014-of-00022.safetensors",
+    "transformer.encoder.layers.26.self_attention.query_key_value.bias": "model-00014-of-00022.safetensors",
+    "transformer.encoder.layers.26.self_attention.query_key_value.weight": "model-00014-of-00022.safetensors",
+    "transformer.encoder.layers.27.input_layernorm.weight": "model-00015-of-00022.safetensors",
+    "transformer.encoder.layers.27.mlp.dense_4h_to_h.weight": "model-00015-of-00022.safetensors",
+    "transformer.encoder.layers.27.mlp.dense_h_to_4h.weight": "model-00015-of-00022.safetensors",
+    "transformer.encoder.layers.27.post_attention_layernorm.weight": "model-00015-of-00022.safetensors",
+    "transformer.encoder.layers.27.self_attention.dense.weight": "model-00015-of-00022.safetensors",
+    "transformer.encoder.layers.27.self_attention.query_key_value.bias": "model-00015-of-00022.safetensors",
+    "transformer.encoder.layers.27.self_attention.query_key_value.weight": "model-00015-of-00022.safetensors",
+    "transformer.encoder.layers.28.input_layernorm.weight": "model-00015-of-00022.safetensors",
+    "transformer.encoder.layers.28.mlp.dense_4h_to_h.weight": "model-00016-of-00022.safetensors",
+    "transformer.encoder.layers.28.mlp.dense_h_to_4h.weight": "model-00016-of-00022.safetensors",
+    "transformer.encoder.layers.28.post_attention_layernorm.weight": "model-00015-of-00022.safetensors",
+    "transformer.encoder.layers.28.self_attention.dense.weight": "model-00015-of-00022.safetensors",
+    "transformer.encoder.layers.28.self_attention.query_key_value.bias": "model-00015-of-00022.safetensors",
+    "transformer.encoder.layers.28.self_attention.query_key_value.weight": "model-00015-of-00022.safetensors",
+    "transformer.encoder.layers.29.input_layernorm.weight": "model-00016-of-00022.safetensors",
+    "transformer.encoder.layers.29.mlp.dense_4h_to_h.weight": "model-00016-of-00022.safetensors",
+    "transformer.encoder.layers.29.mlp.dense_h_to_4h.weight": "model-00016-of-00022.safetensors",
+    "transformer.encoder.layers.29.post_attention_layernorm.weight": "model-00016-of-00022.safetensors",
+    "transformer.encoder.layers.29.self_attention.dense.weight": "model-00016-of-00022.safetensors",
+    "transformer.encoder.layers.29.self_attention.query_key_value.bias": "model-00016-of-00022.safetensors",
+    "transformer.encoder.layers.29.self_attention.query_key_value.weight": "model-00016-of-00022.safetensors",
+    "transformer.encoder.layers.3.input_layernorm.weight": "model-00003-of-00022.safetensors",
+    "transformer.encoder.layers.3.mlp.dense_4h_to_h.weight": "model-00003-of-00022.safetensors",
+    "transformer.encoder.layers.3.mlp.dense_h_to_4h.weight": "model-00003-of-00022.safetensors",
+    "transformer.encoder.layers.3.post_attention_layernorm.weight": "model-00003-of-00022.safetensors",
+    "transformer.encoder.layers.3.self_attention.dense.weight": "model-00003-of-00022.safetensors",
+    "transformer.encoder.layers.3.self_attention.query_key_value.bias": "model-00003-of-00022.safetensors",
+    "transformer.encoder.layers.3.self_attention.query_key_value.weight": "model-00003-of-00022.safetensors",
+    "transformer.encoder.layers.30.input_layernorm.weight": "model-00016-of-00022.safetensors",
+    "transformer.encoder.layers.30.mlp.dense_4h_to_h.weight": "model-00017-of-00022.safetensors",
+    "transformer.encoder.layers.30.mlp.dense_h_to_4h.weight": "model-00017-of-00022.safetensors",
+    "transformer.encoder.layers.30.post_attention_layernorm.weight": "model-00016-of-00022.safetensors",
+    "transformer.encoder.layers.30.self_attention.dense.weight": "model-00016-of-00022.safetensors",
+    "transformer.encoder.layers.30.self_attention.query_key_value.bias": "model-00016-of-00022.safetensors",
+    "transformer.encoder.layers.30.self_attention.query_key_value.weight": "model-00016-of-00022.safetensors",
+    "transformer.encoder.layers.31.input_layernorm.weight": "model-00017-of-00022.safetensors",
+    "transformer.encoder.layers.31.mlp.dense_4h_to_h.weight": "model-00017-of-00022.safetensors",
+    "transformer.encoder.layers.31.mlp.dense_h_to_4h.weight": "model-00017-of-00022.safetensors",
+    "transformer.encoder.layers.31.post_attention_layernorm.weight": "model-00017-of-00022.safetensors",
+    "transformer.encoder.layers.31.self_attention.dense.weight": "model-00017-of-00022.safetensors",
+    "transformer.encoder.layers.31.self_attention.query_key_value.bias": "model-00017-of-00022.safetensors",
+    "transformer.encoder.layers.31.self_attention.query_key_value.weight": "model-00017-of-00022.safetensors",
+    "transformer.encoder.layers.32.input_layernorm.weight": "model-00017-of-00022.safetensors",
+    "transformer.encoder.layers.32.mlp.dense_4h_to_h.weight": "model-00018-of-00022.safetensors",
+    "transformer.encoder.layers.32.mlp.dense_h_to_4h.weight": "model-00018-of-00022.safetensors",
+    "transformer.encoder.layers.32.post_attention_layernorm.weight": "model-00017-of-00022.safetensors",
+    "transformer.encoder.layers.32.self_attention.dense.weight": "model-00017-of-00022.safetensors",
+    "transformer.encoder.layers.32.self_attention.query_key_value.bias": "model-00017-of-00022.safetensors",
+    "transformer.encoder.layers.32.self_attention.query_key_value.weight": "model-00017-of-00022.safetensors",
+    "transformer.encoder.layers.33.input_layernorm.weight": "model-00018-of-00022.safetensors",
+    "transformer.encoder.layers.33.mlp.dense_4h_to_h.weight": "model-00018-of-00022.safetensors",
+    "transformer.encoder.layers.33.mlp.dense_h_to_4h.weight": "model-00018-of-00022.safetensors",
+    "transformer.encoder.layers.33.post_attention_layernorm.weight": "model-00018-of-00022.safetensors",
+    "transformer.encoder.layers.33.self_attention.dense.weight": "model-00018-of-00022.safetensors",
+    "transformer.encoder.layers.33.self_attention.query_key_value.bias": "model-00018-of-00022.safetensors",
+    "transformer.encoder.layers.33.self_attention.query_key_value.weight": "model-00018-of-00022.safetensors",
+    "transformer.encoder.layers.34.input_layernorm.weight": "model-00018-of-00022.safetensors",
+    "transformer.encoder.layers.34.mlp.dense_4h_to_h.weight": "model-00019-of-00022.safetensors",
+    "transformer.encoder.layers.34.mlp.dense_h_to_4h.weight": "model-00019-of-00022.safetensors",
+    "transformer.encoder.layers.34.post_attention_layernorm.weight": "model-00018-of-00022.safetensors",
+    "transformer.encoder.layers.34.self_attention.dense.weight": "model-00018-of-00022.safetensors",
+    "transformer.encoder.layers.34.self_attention.query_key_value.bias": "model-00018-of-00022.safetensors",
+    "transformer.encoder.layers.34.self_attention.query_key_value.weight": "model-00018-of-00022.safetensors",
+    "transformer.encoder.layers.35.input_layernorm.weight": "model-00019-of-00022.safetensors",
+    "transformer.encoder.layers.35.mlp.dense_4h_to_h.weight": "model-00019-of-00022.safetensors",
+    "transformer.encoder.layers.35.mlp.dense_h_to_4h.weight": "model-00019-of-00022.safetensors",
+    "transformer.encoder.layers.35.post_attention_layernorm.weight": "model-00019-of-00022.safetensors",
+    "transformer.encoder.layers.35.self_attention.dense.weight": "model-00019-of-00022.safetensors",
+    "transformer.encoder.layers.35.self_attention.query_key_value.bias": "model-00019-of-00022.safetensors",
+    "transformer.encoder.layers.35.self_attention.query_key_value.weight": "model-00019-of-00022.safetensors",
+    "transformer.encoder.layers.36.input_layernorm.weight": "model-00019-of-00022.safetensors",
+    "transformer.encoder.layers.36.mlp.dense_4h_to_h.weight": "model-00020-of-00022.safetensors",
+    "transformer.encoder.layers.36.mlp.dense_h_to_4h.weight": "model-00020-of-00022.safetensors",
+    "transformer.encoder.layers.36.post_attention_layernorm.weight": "model-00019-of-00022.safetensors",
+    "transformer.encoder.layers.36.self_attention.dense.weight": "model-00019-of-00022.safetensors",
+    "transformer.encoder.layers.36.self_attention.query_key_value.bias": "model-00019-of-00022.safetensors",
+    "transformer.encoder.layers.36.self_attention.query_key_value.weight": "model-00019-of-00022.safetensors",
+    "transformer.encoder.layers.37.input_layernorm.weight": "model-00020-of-00022.safetensors",
+    "transformer.encoder.layers.37.mlp.dense_4h_to_h.weight": "model-00020-of-00022.safetensors",
+    "transformer.encoder.layers.37.mlp.dense_h_to_4h.weight": "model-00020-of-00022.safetensors",
+    "transformer.encoder.layers.37.post_attention_layernorm.weight": "model-00020-of-00022.safetensors",
+    "transformer.encoder.layers.37.self_attention.dense.weight": "model-00020-of-00022.safetensors",
+    "transformer.encoder.layers.37.self_attention.query_key_value.bias": "model-00020-of-00022.safetensors",
+    "transformer.encoder.layers.37.self_attention.query_key_value.weight": "model-00020-of-00022.safetensors",
+    "transformer.encoder.layers.38.input_layernorm.weight": "model-00020-of-00022.safetensors",
+    "transformer.encoder.layers.38.mlp.dense_4h_to_h.weight": "model-00021-of-00022.safetensors",
+    "transformer.encoder.layers.38.mlp.dense_h_to_4h.weight": "model-00021-of-00022.safetensors",
+    "transformer.encoder.layers.38.post_attention_layernorm.weight": "model-00020-of-00022.safetensors",
+    "transformer.encoder.layers.38.self_attention.dense.weight": "model-00020-of-00022.safetensors",
+    "transformer.encoder.layers.38.self_attention.query_key_value.bias": "model-00020-of-00022.safetensors",
+    "transformer.encoder.layers.38.self_attention.query_key_value.weight": "model-00020-of-00022.safetensors",
+    "transformer.encoder.layers.39.input_layernorm.weight": "model-00021-of-00022.safetensors",
+    "transformer.encoder.layers.39.mlp.dense_4h_to_h.weight": "model-00021-of-00022.safetensors",
+    "transformer.encoder.layers.39.mlp.dense_h_to_4h.weight": "model-00021-of-00022.safetensors",
+    "transformer.encoder.layers.39.post_attention_layernorm.weight": "model-00021-of-00022.safetensors",
+    "transformer.encoder.layers.39.self_attention.dense.weight": "model-00021-of-00022.safetensors",
+    "transformer.encoder.layers.39.self_attention.query_key_value.bias": "model-00021-of-00022.safetensors",
+    "transformer.encoder.layers.39.self_attention.query_key_value.weight": "model-00021-of-00022.safetensors",
+    "transformer.encoder.layers.4.input_layernorm.weight": "model-00003-of-00022.safetensors",
+    "transformer.encoder.layers.4.mlp.dense_4h_to_h.weight": "model-00004-of-00022.safetensors",
+    "transformer.encoder.layers.4.mlp.dense_h_to_4h.weight": "model-00004-of-00022.safetensors",
+    "transformer.encoder.layers.4.post_attention_layernorm.weight": "model-00003-of-00022.safetensors",
+    "transformer.encoder.layers.4.self_attention.dense.weight": "model-00003-of-00022.safetensors",
+    "transformer.encoder.layers.4.self_attention.query_key_value.bias": "model-00003-of-00022.safetensors",
+    "transformer.encoder.layers.4.self_attention.query_key_value.weight": "model-00003-of-00022.safetensors",
+    "transformer.encoder.layers.5.input_layernorm.weight": "model-00004-of-00022.safetensors",
+    "transformer.encoder.layers.5.mlp.dense_4h_to_h.weight": "model-00004-of-00022.safetensors",
+    "transformer.encoder.layers.5.mlp.dense_h_to_4h.weight": "model-00004-of-00022.safetensors",
+    "transformer.encoder.layers.5.post_attention_layernorm.weight": "model-00004-of-00022.safetensors",
+    "transformer.encoder.layers.5.self_attention.dense.weight": "model-00004-of-00022.safetensors",
+    "transformer.encoder.layers.5.self_attention.query_key_value.bias": "model-00004-of-00022.safetensors",
+    "transformer.encoder.layers.5.self_attention.query_key_value.weight": "model-00004-of-00022.safetensors",
+    "transformer.encoder.layers.6.input_layernorm.weight": "model-00004-of-00022.safetensors",
+    "transformer.encoder.layers.6.mlp.dense_4h_to_h.weight": "model-00005-of-00022.safetensors",
+    "transformer.encoder.layers.6.mlp.dense_h_to_4h.weight": "model-00005-of-00022.safetensors",
+    "transformer.encoder.layers.6.post_attention_layernorm.weight": "model-00004-of-00022.safetensors",
+    "transformer.encoder.layers.6.self_attention.dense.weight": "model-00004-of-00022.safetensors",
+    "transformer.encoder.layers.6.self_attention.query_key_value.bias": "model-00004-of-00022.safetensors",
+    "transformer.encoder.layers.6.self_attention.query_key_value.weight": "model-00004-of-00022.safetensors",
+    "transformer.encoder.layers.7.input_layernorm.weight": "model-00005-of-00022.safetensors",
+    "transformer.encoder.layers.7.mlp.dense_4h_to_h.weight": "model-00005-of-00022.safetensors",
+    "transformer.encoder.layers.7.mlp.dense_h_to_4h.weight": "model-00005-of-00022.safetensors",
+    "transformer.encoder.layers.7.post_attention_layernorm.weight": "model-00005-of-00022.safetensors",
+    "transformer.encoder.layers.7.self_attention.dense.weight": "model-00005-of-00022.safetensors",
+    "transformer.encoder.layers.7.self_attention.query_key_value.bias": "model-00005-of-00022.safetensors",
+    "transformer.encoder.layers.7.self_attention.query_key_value.weight": "model-00005-of-00022.safetensors",
+    "transformer.encoder.layers.8.input_layernorm.weight": "model-00005-of-00022.safetensors",
+    "transformer.encoder.layers.8.mlp.dense_4h_to_h.weight": "model-00006-of-00022.safetensors",
+    "transformer.encoder.layers.8.mlp.dense_h_to_4h.weight": "model-00006-of-00022.safetensors",
+    "transformer.encoder.layers.8.post_attention_layernorm.weight": "model-00005-of-00022.safetensors",
+    "transformer.encoder.layers.8.self_attention.dense.weight": "model-00005-of-00022.safetensors",
+    "transformer.encoder.layers.8.self_attention.query_key_value.bias": "model-00005-of-00022.safetensors",
+    "transformer.encoder.layers.8.self_attention.query_key_value.weight": "model-00005-of-00022.safetensors",
+    "transformer.encoder.layers.9.input_layernorm.weight": "model-00006-of-00022.safetensors",
+    "transformer.encoder.layers.9.mlp.dense_4h_to_h.weight": "model-00006-of-00022.safetensors",
+    "transformer.encoder.layers.9.mlp.dense_h_to_4h.weight": "model-00006-of-00022.safetensors",
+    "transformer.encoder.layers.9.post_attention_layernorm.weight": "model-00006-of-00022.safetensors",
+    "transformer.encoder.layers.9.self_attention.dense.weight": "model-00006-of-00022.safetensors",
+    "transformer.encoder.layers.9.self_attention.query_key_value.bias": "model-00006-of-00022.safetensors",
+    "transformer.encoder.layers.9.self_attention.query_key_value.weight": "model-00006-of-00022.safetensors",
+    "transformer.output_layer.weight": "model-00022-of-00022.safetensors",
+    "transformer.rotary_pos_emb.inv_freq": "model-00002-of-00022.safetensors"
   }
 }