Upload 5 files

config.json

@@ -0,0 +1,50 @@
+{
+  "_name_or_path": "/root/workspace/models/models--THUDM--glm-4-voice-9b/snapshots/352e5a64063448d5e46394753fb65bf1dbab975b",
+  "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": "configuration_chatglm.ChatGLMConfig",
+    "AutoModel": "modeling_chatglm.ChatGLMForConditionalGeneration",
+    "AutoModelForCausalLM": "modeling_chatglm.ChatGLMForConditionalGeneration",
+    "AutoModelForSeq2SeqLM": "modeling_chatglm.ChatGLMForConditionalGeneration",
+    "AutoModelForSequenceClassification": "modeling_chatglm.ChatGLMForSequenceClassification"
+  },
+  "bias_dropout_fusion": true,
+  "classifier_dropout": null,
+  "eos_token_id": [
+    151329,
+    151336,
+    151338
+  ],
+  "ffn_hidden_size": 13696,
+  "fp32_residual_connection": false,
+  "hidden_dropout": 0.0,
+  "hidden_size": 4096,
+  "kv_channels": 128,
+  "layernorm_epsilon": 3.90625e-08,
+  "model_type": "chatglm",
+  "multi_query_attention": true,
+  "multi_query_group_num": 2,
+  "num_attention_heads": 32,
+  "num_hidden_layers": 40,
+  "num_layers": 40,
+  "original_rope": true,
+  "pad_token_id": 151329,
+  "padded_vocab_size": 168960,
+  "post_layer_norm": true,
+  "rmsnorm": true,
+  "rope_ratio": 1,
+  "seq_length": 8192,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.47.0",
+  "use_cache": true,
+  "vocab_size": 168960
+}

configuration_chatglm.py

@@ -0,0 +1,58 @@
+from transformers import PretrainedConfig
+
+
+class ChatGLMConfig(PretrainedConfig):
+    model_type = "chatglm"
+
+    def __init__(
+            self,
+            num_layers=28,
+            padded_vocab_size=65024,
+            hidden_size=4096,
+            ffn_hidden_size=13696,
+            kv_channels=128,
+            num_attention_heads=32,
+            seq_length=2048,
+            hidden_dropout=0.0,
+            classifier_dropout=None,
+            attention_dropout=0.0,
+            layernorm_epsilon=1e-5,
+            rmsnorm=True,
+            apply_residual_connection_post_layernorm=False,
+            post_layer_norm=True,
+            add_bias_linear=False,
+            add_qkv_bias=False,
+            bias_dropout_fusion=True,
+            multi_query_attention=False,
+            multi_query_group_num=1,
+            rope_ratio=1,
+            apply_query_key_layer_scaling=True,
+            attention_softmax_in_fp32=True,
+            fp32_residual_connection=False,
+            **kwargs
+    ):
+        self.num_layers = num_layers
+        self.vocab_size = padded_vocab_size
+        self.padded_vocab_size = padded_vocab_size
+        self.hidden_size = hidden_size
+        self.ffn_hidden_size = ffn_hidden_size
+        self.kv_channels = kv_channels
+        self.num_attention_heads = num_attention_heads
+        self.seq_length = seq_length
+        self.hidden_dropout = hidden_dropout
+        self.classifier_dropout = classifier_dropout
+        self.attention_dropout = attention_dropout
+        self.layernorm_epsilon = layernorm_epsilon
+        self.rmsnorm = rmsnorm
+        self.apply_residual_connection_post_layernorm = apply_residual_connection_post_layernorm
+        self.post_layer_norm = post_layer_norm
+        self.add_bias_linear = add_bias_linear
+        self.add_qkv_bias = add_qkv_bias
+        self.bias_dropout_fusion = bias_dropout_fusion
+        self.multi_query_attention = multi_query_attention
+        self.multi_query_group_num = multi_query_group_num
+        self.rope_ratio = rope_ratio
+        self.apply_query_key_layer_scaling = apply_query_key_layer_scaling
+        self.attention_softmax_in_fp32 = attention_softmax_in_fp32
+        self.fp32_residual_connection = fp32_residual_connection
+        super().__init__(**kwargs)

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "device": "cuda",
+  "do_sample": true,
+  "eos_token_id": [
+    151329,
+    151336,
+    151338
+  ],
+  "max_length": 128000,
+  "pad_token_id": 151329,
+  "temperature": 0.8,
+  "top_p": 0.8,
+  "transformers_version": "4.47.0"
+}

model.safetensors.index.json

@@ -0,0 +1,291 @@
+{
+  "metadata": {
+    "total_size": 19085115456
+  },
+  "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-00003-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-00003-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-00003-of-00004.safetensors",
+    "transformer.encoder.layers.21.self_attention.dense.weight": "model-00003-of-00004.safetensors",
+    "transformer.encoder.layers.21.self_attention.query_key_value.bias": "model-00003-of-00004.safetensors",
+    "transformer.encoder.layers.21.self_attention.query_key_value.weight": "model-00003-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-00004-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-00004-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-00004-of-00004.safetensors",
+    "transformer.encoder.layers.33.self_attention.dense.weight": "model-00004-of-00004.safetensors",
+    "transformer.encoder.layers.33.self_attention.query_key_value.bias": "model-00004-of-00004.safetensors",
+    "transformer.encoder.layers.33.self_attention.query_key_value.weight": "model-00004-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-00002-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-00002-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-00002-of-00004.safetensors",
+    "transformer.encoder.layers.9.self_attention.dense.weight": "model-00002-of-00004.safetensors",
+    "transformer.encoder.layers.9.self_attention.query_key_value.bias": "model-00002-of-00004.safetensors",
+    "transformer.encoder.layers.9.self_attention.query_key_value.weight": "model-00002-of-00004.safetensors",
+    "transformer.output_layer.weight": "model-00004-of-00004.safetensors",
+    "transformer.rotary_pos_emb.inv_freq": "model-00001-of-00004.safetensors"
+  }
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a547769d3e82c44004d601eba53c036673df7222df024e677c6cb430baaa6e5c
+size 5240