Upload ChatGLMForConditionalGeneration

config.json

@@ -0,0 +1,47 @@
+{
+  "_name_or_path": "THUDM/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",
+    "AutoModelForCausalLM": "THUDM/chatglm2-6b--modeling_chatglm.ChatGLMForConditionalGeneration",
+    "AutoModelForSeq2SeqLM": "THUDM/chatglm2-6b--modeling_chatglm.ChatGLMForConditionalGeneration",
+    "AutoModelForSequenceClassification": "THUDM/chatglm2-6b--modeling_chatglm.ChatGLMForSequenceClassification"
+  },
+  "bias_dropout_fusion": true,
+  "classifier_dropout": null,
+  "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,
+  "model_type": "chatglm",
+  "multi_query_attention": true,
+  "multi_query_group_num": 2,
+  "num_attention_heads": 32,
+  "num_layers": 28,
+  "original_rope": true,
+  "pad_token_id": 0,
+  "padded_vocab_size": 65024,
+  "post_layer_norm": true,
+  "pre_seq_len": null,
+  "prefix_projection": false,
+  "quantization_bit": 0,
+  "rmsnorm": true,
+  "seq_length": 32768,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.30.2",
+  "use_cache": true,
+  "vocab_size": 65024
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.30.2"
+}

pytorch_model-00001-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4c3196b1ed4a73b9eb86574442fe0c42a532a663cdd62c2d51a959eac58c7cb
+size 9986267434

pytorch_model-00002-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b04dcfe3caafa2bc12e82fd7c2d94af70003fcc0bbc9d7b147ea43c0c12109bf
+size 2500976490

pytorch_model.bin.index.json

@@ -0,0 +1,207 @@
+{
+  "metadata": {
+    "total_size": 12487168064
+  },
+  "weight_map": {
+    "transformer.embedding.word_embeddings.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.final_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.encoder.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.0.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.0.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.0.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.0.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.0.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.1.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.1.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.1.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.1.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.1.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.10.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.10.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.10.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.10.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.10.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.11.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.11.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.11.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.11.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.11.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.12.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.12.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.12.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.12.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.12.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.13.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.13.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.13.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.13.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.13.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.14.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.14.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.14.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.14.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.14.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.15.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.15.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.15.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.15.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.15.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.15.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.15.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.16.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.16.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.16.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.16.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.16.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.16.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.16.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.17.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.17.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.17.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.17.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.17.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.17.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.17.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.18.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.18.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.18.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.18.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.18.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.18.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.18.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.19.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.19.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.19.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.19.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.19.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.19.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.19.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.2.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.2.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.2.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.2.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.2.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.20.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.20.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.20.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.20.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.20.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.20.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.20.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.21.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.21.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.21.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.21.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.21.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.21.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.21.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.22.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.22.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.22.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.22.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.22.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.22.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.22.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.23.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.23.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.encoder.layers.23.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.encoder.layers.23.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.23.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.23.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.23.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.encoder.layers.24.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.encoder.layers.24.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.encoder.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.encoder.layers.24.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.encoder.layers.24.self_attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.encoder.layers.24.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.encoder.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.encoder.layers.25.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.encoder.layers.25.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.encoder.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.encoder.layers.25.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.encoder.layers.25.self_attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.encoder.layers.25.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.encoder.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.encoder.layers.26.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.encoder.layers.26.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.encoder.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.encoder.layers.26.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.encoder.layers.26.self_attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.encoder.layers.26.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.encoder.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.encoder.layers.27.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.encoder.layers.27.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.encoder.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.encoder.layers.27.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.encoder.layers.27.self_attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.encoder.layers.27.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.encoder.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.3.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.3.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.3.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.3.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.3.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.4.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.4.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.4.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.4.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.4.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.5.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.5.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.5.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.5.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.5.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.6.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.6.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.6.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.6.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.6.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.7.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.7.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.7.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.7.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.7.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.8.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.8.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.8.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.8.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.8.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.9.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.9.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.9.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.9.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.encoder.layers.9.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.output_layer.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.rotary_pos_emb.inv_freq": "pytorch_model-00001-of-00002.bin"
+  }
+}