add index.json

configuration_dolphin.py

@@ -19,7 +19,119 @@ from transformers.utils import logging
 
 logger = logging.get_logger(__name__)
 
-# We can also consider to pass the encoder config dict to the Qwen2Config config as well.
+class DolphinConfig(PretrainedConfig):
+    r"""
+    This is the configuration class to store the configuration of a [`DolphinModel`]. It is used to instantiate a
+    Qwen2 model according to the specified arguments, defining the model architecture. Instantiating a configuration
+    with the defaults will yield a similar configuration to that of
+    Qwen2-7B-beta [Qwen/Qwen2-7B-beta](https://huggingface.co/Qwen/Qwen2-7B-beta).
+
+    Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
+    documentation from [`PretrainedConfig`] for more information.
+
+
+    Args:
+        vocab_size (`int`, *optional*, defaults to 151936):
+            Vocabulary size of the Qwen2 model. Defines the number of different tokens that can be represented by the
+            `inputs_ids` passed when calling [`DolphinModel`]
+        hidden_size (`int`, *optional*, defaults to 4096):
+            Dimension of the hidden representations.
+        intermediate_size (`int`, *optional*, defaults to 22016):
+            Dimension of the MLP representations.
+        num_hidden_layers (`int`, *optional*, defaults to 32):
+            Number of hidden layers in the Transformer encoder.
+        num_attention_heads (`int`, *optional*, defaults to 32):
+            Number of attention heads for each attention layer in the Transformer encoder.
+        num_key_value_heads (`int`, *optional*, defaults to 32):
+            This is the number of key_value heads that should be used to implement Grouped Query Attention. If
+            `num_key_value_heads=num_attention_heads`, the model will use Multi Head Attention (MHA), if
+            `num_key_value_heads=1` the model will use Multi Query Attention (MQA) otherwise GQA is used. When
+            converting a multi-head checkpoint to a GQA checkpoint, each group key and value head should be constructed
+            by meanpooling all the original heads within that group. For more details checkout [this
+            paper](https://arxiv.org/pdf/2305.13245.pdf). If it is not specified, will default to `32`.
+        hidden_act (`str` or `function`, *optional*, defaults to `"silu"`):
+            The non-linear activation function (function or string) in the decoder.
+        max_position_embeddings (`int`, *optional*, defaults to 32768):
+            The maximum sequence length that this model might ever be used with.
+        initializer_range (`float`, *optional*, defaults to 0.02):
+            The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
+        rms_norm_eps (`float`, *optional*, defaults to 1e-06):
+            The epsilon used by the rms normalization layers.
+        use_cache (`bool`, *optional*, defaults to `True`):
+            Whether or not the model should return the last key/values attentions (not used by all models). Only
+            relevant if `config.is_decoder=True`.
+        tie_word_embeddings (`bool`, *optional*, defaults to `False`):
+            Whether the model's input and output word embeddings should be tied.
+        rope_theta (`float`, *optional*, defaults to 10000.0):
+            The base period of the RoPE embeddings.
+        use_sliding_window (`bool`, *optional*, defaults to `False`):
+            Whether to use sliding window attention.
+        sliding_window (`int`, *optional*, defaults to 4096):
+            Sliding window attention (SWA) window size. If not specified, will default to `4096`.
+        max_window_layers (`int`, *optional*, defaults to 28):
+            The number of layers that use SWA (Sliding Window Attention). The bottom layers use SWA while the top use full attention.
+        attention_dropout (`float`, *optional*, defaults to 0.0):
+            The dropout ratio for the attention probabilities.
+    ```"""
+
+    # The `model_type` attribute in the `DolphinConfig` class is a string variable that specifies the
+    # type of model configuration. In this case, it is set to "qwen2", indicating that the
+    # configuration is specifically designed for a Qwen2 model. This attribute helps identify the type
+    # of model configuration being used and can be useful for distinguishing between different model
+    # configurations or types within a codebase.
+    model_type = "dolphin"
+    keys_to_ignore_at_inference = ["past_key_values"]
+
+    def __init__(
+        self,
+        vocab_size=151936,
+        hidden_size=4096,
+        intermediate_size=22016,
+        num_hidden_layers=32,
+        num_attention_heads=32,
+        num_key_value_heads=32,
+        hidden_act="silu",
+        max_position_embeddings=32768,
+        initializer_range=0.02,
+        rms_norm_eps=1e-6,
+        use_cache=True,
+        tie_word_embeddings=False,
+        rope_theta=10000.0,
+        use_sliding_window=False,
+        sliding_window=4096,
+        max_window_layers=28,
+        attention_dropout=0.0,
+        encoder_config=None,
+        **kwargs,
+    ):
+        self.vocab_size = vocab_size
+        self.max_position_embeddings = max_position_embeddings
+        self.hidden_size = hidden_size
+        self.intermediate_size = intermediate_size
+        self.num_hidden_layers = num_hidden_layers
+        self.num_attention_heads = num_attention_heads
+        self.use_sliding_window = use_sliding_window
+        self.sliding_window = sliding_window
+        self.max_window_layers = max_window_layers
+
+        # for backward compatibility
+        if num_key_value_heads is None:
+            num_key_value_heads = num_attention_heads
+
+        self.num_key_value_heads = num_key_value_heads
+        self.hidden_act = hidden_act
+        self.initializer_range = initializer_range
+        self.rms_norm_eps = rms_norm_eps
+        self.use_cache = use_cache
+        self.rope_theta = rope_theta
+        self.attention_dropout = attention_dropout
+        self.encoder_config = encoder_config
+
+        super().__init__(
+            tie_word_embeddings=tie_word_embeddings,
+            **kwargs,
+        )
+
 encoder_config_dict = {
     "_name_or_path": "alexchen4ai/Qwen2-0.5B",
     "add_cross_attention": False,

model.safetensors.index.json

@@ -0,0 +1,638 @@
+{
+    "metadata": {
+      "total_size": 16225728256
+    },
+    "weight_map": {
+      "lm_head.weight": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.embed_tokens.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.0.input_layernorm.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.0.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.0.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.0.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.0.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.0.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.0.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.0.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.0.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.0.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.0.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.0.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.1.input_layernorm.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.1.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.1.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.1.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.1.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.1.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.1.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.1.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.1.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.1.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.1.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.1.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.10.input_layernorm.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.10.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.10.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.10.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.10.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.10.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.10.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.10.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.10.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.10.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.10.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.10.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.11.input_layernorm.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.11.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.11.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.11.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.11.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.11.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.11.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.11.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.11.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.11.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.11.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.11.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.12.input_layernorm.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.12.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.12.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.12.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.12.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.12.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.12.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.12.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.12.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.12.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.12.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.12.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.13.input_layernorm.weight": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.13.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.13.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.13.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.13.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.13.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.13.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.13.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.13.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.13.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.13.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.13.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.14.input_layernorm.weight": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.14.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.14.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.14.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.14.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.14.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.14.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.14.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.14.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.14.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.14.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.14.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.15.input_layernorm.weight": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.15.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.15.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.15.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.15.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.15.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.15.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.15.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.15.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.15.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.15.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.15.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.16.input_layernorm.weight": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.16.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.16.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.16.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.16.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.16.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.16.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.16.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.16.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.16.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.16.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.16.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.17.input_layernorm.weight": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.17.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.17.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.17.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.17.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.17.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.17.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.17.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.17.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.17.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.17.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.17.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.18.input_layernorm.weight": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.18.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.18.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.18.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.18.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.18.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.18.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.18.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.18.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.18.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.18.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.18.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.19.input_layernorm.weight": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.19.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.19.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.19.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.19.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.19.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.19.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.19.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.19.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.19.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.19.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.19.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.2.input_layernorm.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.2.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.2.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.2.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.2.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.2.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.2.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.2.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.2.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.2.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.2.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.2.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.20.input_layernorm.weight": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.20.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.20.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.20.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.20.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.20.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.20.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.20.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.20.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.20.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.20.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.20.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.21.input_layernorm.weight": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.21.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.21.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.21.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.21.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.21.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.21.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.21.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.21.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.21.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.21.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.21.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.22.input_layernorm.weight": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.22.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.22.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.22.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.22.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.22.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.22.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.22.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.22.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.22.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.22.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.22.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.23.input_layernorm.weight": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.23.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.23.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.23.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.23.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.23.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.23.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.23.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.23.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.23.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.23.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.23.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.3.input_layernorm.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.3.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.3.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.3.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.3.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.3.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.3.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.3.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.3.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.3.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.3.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.3.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.4.input_layernorm.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.4.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.4.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.4.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.4.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.4.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.4.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.4.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.4.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.4.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.4.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.4.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.5.input_layernorm.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.5.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.5.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.5.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.5.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.5.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.5.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.5.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.5.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.5.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.5.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.5.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.6.input_layernorm.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.6.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.6.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.6.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.6.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.6.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.6.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.6.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.6.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.6.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.6.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.6.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.7.input_layernorm.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.7.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.7.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.7.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.7.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.7.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.7.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.7.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.7.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.7.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.7.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.7.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.8.input_layernorm.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.8.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.8.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.8.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.8.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.8.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.8.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.8.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.8.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.8.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.8.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.8.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.9.input_layernorm.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.9.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.9.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.9.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.9.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.9.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.9.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.9.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.9.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.9.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.9.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.layers.9.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+      "model.context_encoder.encoder.model.norm.weight": "model-00004-of-00004.safetensors",
+      "model.context_encoder.projector.context_projection.bias": "model-00004-of-00004.safetensors",
+      "model.context_encoder.projector.context_projection.weight": "model-00004-of-00004.safetensors",
+      "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+      "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+      "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+      "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+      "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+      "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+      "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+      "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+      "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+      "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+      "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+      "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+      "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+      "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+      "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+      "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+      "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+      "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+      "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+      "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+      "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+      "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+      "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+      "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+      "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+      "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+      "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+      "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+      "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+      "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+      "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+      "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+      "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+      "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+      "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+      "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+      "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+      "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+      "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+      "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+      "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+      "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+      "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+      "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+      "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+      "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+      "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+      "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+      "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+      "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+      "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+      "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+      "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+      "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+      "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+      "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+      "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+      "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+      "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+      "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+      "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+      "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+      "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+      "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+      "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+      "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+      "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+      "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+      "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+      "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+      "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+      "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+      "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+      "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+      "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+      "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+      "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+      "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+      "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+      "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+      "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+      "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+      "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+      "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+      "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+      "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+      "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+      "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+      "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+      "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+      "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+      "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+      "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+      "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+      "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+      "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+      "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+      "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+      "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+      "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+      "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+      "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+      "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+      "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+      "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+      "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+      "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+      "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+      "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+      "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+      "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+      "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+      "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+      "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+      "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+      "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+      "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+      "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+      "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+      "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+      "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+      "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
+      "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+      "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+      "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+      "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+      "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+      "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+      "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+      "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+      "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+      "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+      "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+      "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
+      "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+      "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+      "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+      "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+      "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+      "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+      "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+      "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+      "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+      "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+      "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+      "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+      "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+      "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+      "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+      "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+      "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+      "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+      "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+      "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+      "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+      "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+      "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+      "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+      "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+      "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+      "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+      "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+      "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+      "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+      "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+      "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+      "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+      "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+      "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+      "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+      "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+      "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+      "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+      "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+      "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+      "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+      "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+      "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+      "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+      "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+      "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+      "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+      "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+      "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+      "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+      "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+      "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+      "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+      "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+      "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+      "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+      "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+      "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+      "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+      "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+      "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+      "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+      "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+      "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+      "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+      "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+      "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+      "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+      "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+      "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+      "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+      "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+      "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+      "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+      "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+      "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+      "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+      "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+      "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+      "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+      "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+      "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+      "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+      "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+      "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+      "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+      "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+      "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+      "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+      "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+      "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+      "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+      "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+      "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+      "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+      "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+      "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+      "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+      "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+      "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+      "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+      "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+      "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+      "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+      "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+      "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+      "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+      "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+      "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+      "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+      "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+      "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+      "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+      "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+      "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+      "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+      "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+      "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+      "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+      "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+      "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+      "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+      "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+      "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+      "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+      "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+      "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+      "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+      "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+      "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+      "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+      "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+      "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+      "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+      "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+      "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+      "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+      "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+      "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+      "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+      "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+      "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+      "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+      "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+      "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+      "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+      "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+      "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+      "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+      "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+      "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+      "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+      "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+      "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+      "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+      "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+      "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+      "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+      "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+      "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+      "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+      "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+      "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+      "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+      "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+      "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+      "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+      "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+      "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+      "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+      "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+      "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+      "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+      "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+      "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+      "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+      "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+      "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+      "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+      "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+      "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+      "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+      "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+      "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+      "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+      "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+      "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+      "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+      "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+      "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+      "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+      "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+      "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+      "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+      "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+      "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+      "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+      "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+      "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+      "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+      "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+      "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+      "model.norm.weight": "model-00003-of-00004.safetensors"
+    }
+  }

modeling_dolphin.py

@@ -11,6 +11,9 @@ from transformers.cache_utils import Cache, DynamicCache, StaticCache
 from transformers.models.qwen2.modeling_qwen2 import (
     Qwen2PreTrainedModel, Qwen2Model, Qwen2RMSNorm
 )
+from transformers.modeling_attn_mask_utils import (
+    AttentionMaskConverter,
+)
 from transformers.models.qwen2.modeling_qwen2 import Qwen2DecoderLayer
 import torch
 import torch.nn as nn
@@ -182,6 +185,7 @@ class DolphinModel(Qwen2PreTrainedModel):
     Args:
         config: DolphinModel
     """
+    config_class = DolphinConfig
 
     def __init__(self, config: Qwen2Config):
         super().__init__(config)
@@ -514,6 +518,7 @@ class DolphinModel(Qwen2PreTrainedModel):
 
 
 class DolphinForCausalLM(Qwen2PreTrainedModel):
+    config_class = DolphinConfig
     _tied_weights_keys = ["lm_head.weight"]
 
     def __init__(self, config):
@@ -727,9 +732,16 @@ class DolphinForCausalLM(Qwen2PreTrainedModel):
         return reordered_past
 
 if __name__ == "__main__":
-    config = Qwen2Config(encoder_config=encoder_config_dict)
-    dolphin_model = DolphinModel(config)
-    # AutoConfig.register("dolphin", Qwen2Config)
-    AutoModelForCausalLM.register(Qwen2Config, DolphinForCausalLM)
-    tokenizer = AutoTokenizer.from_pretrained('nexa-collaboration/dolphin_instruct_1M_0805', trust_remote_code=True)
-    model = AutoModelForCausalLM.from_pretrained('nexa-collaboration/dolphin_instruct_1M_0805', trust_remote_code=True)
+    # Register your configuration and model
+    AutoConfig.register("dolphin", DolphinConfig)
+    AutoModelForCausalLM.register(DolphinConfig, DolphinForCausalLM)
+
+    # Ensure that your config is loaded with the correct model type
+    config = DolphinConfig(encoder_config=encoder_config_dict)
+
+    # Save the configuration (if needed)
+    config.save_pretrained("dolphin")
+
+    # Load the tokenizer and model
+    tokenizer = AutoTokenizer.from_pretrained('NexaAIDev/Dolphin', trust_remote=True)
+    model = AutoModelForCausalLM.from_pretrained('NexaAIDev/Dolphin', config=config, trust_remote=True)