modify forward to accept batch

.gitattributes

@@ -1,35 +0,0 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text

BranchyModel.py

@@ -303,6 +303,15 @@ class BranchyCausalModel(PreTrainedModel):
         is_early_exited = False
         next_decoder_cache = None
         
+        batch_size = hidden_states.shape[0]
+        seq_length = hidden_states.shape[1]
+        device = hidden_states.device
+
+        # Track which samples have exited early
+        early_exit_mask = torch.zeros(batch_size, dtype=torch.bool, device=device)
+        exit_layer = torch.full((batch_size,), self.num_layers, dtype=torch.long, device=device)
+        final_logits = torch.zeros((batch_size, seq_length, self.vocab_size), device=device)
+
         for layer, decoder_layer in enumerate(self.model.layers):
             if output_hidden_states:
                 all_hidden_states += (hidden_states,)
@@ -326,32 +335,36 @@ class BranchyCausalModel(PreTrainedModel):
                     output_attentions=output_attentions,
                     use_cache=use_cache,
                 )
-                hidden_states = layer_outputs[0]
+                
                 if layer in self.config.branch_locations:
-                    logits = self.branches[self.config.branch_locations.index(layer)](layer_outputs[0])
+                    branch_logits = self.branches[self.config.branch_locations.index(layer)](layer_outputs[0])
                     if not self.training:
                         # During inference, calculate score on the fly to decide if we should early exit
-                        score = self.confidence_metric_fn(logits)[..., -1] # score for the classified token TODO migth be interesting to take score from whole vector ?
-                        if score > self.head_thresholds[self.config.branch_locations.index(layer)]:
-                            is_early_exited = True
-                            logger.debug(f"Early exit at layer {layer} with score {score}")
-                            break
+                        scores = self.confidence_metric_fn(branch_logits)[..., -1]
+                        exit_samples = (scores > self.head_thresholds[self.config.branch_locations.index(layer)]) & ~early_exit_mask
+                        early_exit_mask |= exit_samples
+                        exit_layer[exit_samples] = layer
+                        final_logits[exit_samples] = branch_logits[exit_samples]
+
+                        if early_exit_mask.all():
+                            break  # All samples have exited early
                     else:
                         # if in training we return full logits
-                        all_logits += (logits,)
+                        all_logits += (branch_logits,)
 
-            
+                hidden_states = layer_outputs[0]
 
             if use_cache:
                 next_decoder_cache = layer_outputs[2 if output_attentions else 1]
 
             if output_attentions:
                 all_self_attns += (layer_outputs[1],)
-        if not is_early_exited:
-            logger.debug(f"No early exit")
-            hidden_states = self.model.final_layernorm(hidden_states)
-            logits = self.lm_head(hidden_states)
-            logits = logits.float()
+                
+        if not early_exit_mask.all():
+            remaining_hidden_states = hidden_states[~early_exit_mask]
+            remaining_hidden_states = self.model.final_layernorm(remaining_hidden_states)
+            remaining_logits = self.lm_head(remaining_hidden_states)
+            final_logits[~early_exit_mask] = remaining_logits
         
         if output_hidden_states:
             all_hidden_states += (hidden_states,)
@@ -366,17 +379,18 @@ class BranchyCausalModel(PreTrainedModel):
             )
         if not return_dict:
             raise NotImplementedError("return_dict=False is not implemented")
+        
         return CausalBranchyLLMOutputWithPast(
             loss=loss[0],
             head_loss=loss[1],
             entropies=loss[2],
             entropy=loss[3],
-            logits=logits, # shape (batch_size, seq_len, vocab_size)
-            head_logits=all_logits, # shape (num_branches, batch_size, seq_len, vocab_size)
+            logits=final_logits,
+            head_logits=all_logits,
             past_key_values=next_cache,
             hidden_states=all_hidden_states,
             attentions=all_self_attns,
-            head_indices=layer,
+            head_indices=exit_layer,
         )
         
     def compute_self_supervision_loss(self,

BranchyModelConfig.py

@@ -1,78 +0,0 @@
-from typing import List, Optional
-from transformers import PretrainedConfig
-import logging
-
-logger = logging.getLogger(__name__)
-
-class BranchyModelConfig(PretrainedConfig):
-    """
-    Configuration class for BranchyModel. This class extends the PretrainedConfig class from the Transformers
-    library, providing configuration specific to models with branch functionality.
-
-    Attributes:
-        branch_locations (List[int]): Specifies the indices of layers after which branches are added. These indices
-            start from 0, and each index represents a layer in the underlying transformer model.
-        penalty_weight (Optional[float]): The weight of the penalty term used in the "penalized_cross_entropy" loss.
-            This parameter is required and must be greater than 0
-        window_size (int): Determines the number of tokens each branch considers from the input sequence. This allows
-            for reducing the computational load by limiting the context size each branch processes.
-
-    Example:
-        config = BranchyModelConfig(
-            branch_locations=[2, 4, 6],
-            window_size=512
-        )
-
-    Note:
-        This configuration class is specifically designed for use with the BranchyModel class, enabling flexible
-        and customizable branching within transformer models.
-    """
-    model_type = "branchy"  # Optional, but useful for identifying the model type in the Transformers library
-
-    def __init__(
-        self,
-        model_str: str = None,
-        head_thresholds: Optional[List[float]] = None,
-        confidence_metric: Optional[str] = "breaking_ties",
-        branch_locations: Optional[List[int]] = None,
-        branch_number: Optional[int] = 3,
-        penalty_weight: Optional[float] = 0,
-        head_window_size: int = 512,
-        copy_lm_head: Optional[bool] = False,
-        **kwargs
-    ):
-        """
-        Initializes the BranchyModelConfig.
-
-        Args:
-            model_str (str): The model string to be used for the model. From Huggingface's model hub.
-            branch_locations (List[int], optional): Locations of the branches. Defaults to None, indicating no branches.
-            branch_number (Optional[int], optional): Number of branches if branch_locations is not provided. Defaults to 3.
-            penalty_weight (Optional[float], optional): Weight for the penalty in loss calculation.
-                . Defaults to None.
-            head_window_size (int, optional): Number of tokens each branch can see. Defaults to 512.
-        """
-        self.model_str = model_str
-        self.head_thresholds = head_thresholds
-        self.confidence_metric = confidence_metric
-        assert self.confidence_metric in ["breaking_ties", "max"], "confidence_metric must be 'breaking_ties' or 'max'. It should depend on how you found the thresholds."
-        self.branch_locations = branch_locations 
-        self.penalty_weight = penalty_weight
-        self.head_window_size = head_window_size
-        if branch_locations is not None and branch_number is not None:
-            logger.warning("Both branch_locations and branch_number are provided. Using branch_locations.")
-        self.branch_number = branch_number if branch_locations is None else len(branch_locations)
-        self.copy_lm_head = copy_lm_head
-        #assert self.model_str is not None, "model_str must be provided."
-        assert self.branch_number > 0, "branch_number must be a positive integer."
-        assert isinstance(self.penalty_weight, float) or isinstance(self.penalty_weight, int), "penalty_weight must be a float or an integer."
-        assert self.penalty_weight >= 0 and self.penalty_weight <= 1, "penalty_weight must be in the range [0, 1]."
-        if branch_locations is not None:
-            assert all([isinstance(loc, int) for loc in self.branch_locations]), "Branch locations must be integers."
-            assert all([loc >= 0 for loc in self.branch_locations]), "Branch locations must be non-negative."
-        if self.head_window_size is not None:
-            assert self.head_window_size > 0 , "head_window_size must be a positive integer or None."
-        if type(self.head_thresholds) == list:
-            assert len(self.head_thresholds) == self.branch_number, "Number of thresholds must match number of branches."
-            assert all([isinstance(threshold, float) for threshold in self.head_thresholds]), "Thresholds must be floats."
-        super().__init__(**kwargs)  # Initialize with base class parameters

README.md

@@ -1,82 +0,0 @@
----
-language:
-- en
-license: mit
-library_name: transformers
-pipeline_tag: text-generation
----
-
-# Model Card for Model ID
-
-Phi-2 is a Transformer with **2.7 billion** parameters. It was trained using the same data sources as [Phi-1.5](https://huggingface.co/microsoft/phi-1.5), augmented with a new data source that consists of various NLP synthetic texts and filtered websites (for safety and educational value). When assessed against benchmarks testing common sense, language understanding, and logical reasoning, Phi-2 showcased a nearly state-of-the-art performance among models with less than 13 billion parameters.
-
-This version of Phi-2 is one with added Early Exit in order to accelerate inference. Each Early Exit was trained using self-supervised technique from model outputs.
-
-### Model Description
-
-This model provides trained head to make Phi-2 a Early exit model.
-
-- **Developed by:** Florian Valade
-- **Shared by:** Florian Valade
-- **Model type:** Text generation
-- **License:** MIT
-- **Finetuned from model :** https://huggingface.co/microsoft/phi-2
-
-### Model Sources
-
-- **Repository:** [TBD]
-- **Paper:** [TBD]
-- **Demo:** [TBD]
-
-## Uses
-
-When used as provided, the model does not use Early Exits. One needs to set head_thresholds in the configuration in order to use inference acceleration.
-
-different head_thresholds for different ε :
-
-| ε            | head_thresholds                                                                     |
-| ------------ | ----------------------------------------------------------------------------------- |
-| 0.4          | [1.0307843685150146, 0.8693032264709473, 0.6637287139892578, 0.3111608028411865]    |
-| 0.5          | [1.505380630493164, 1.5712471008300781, 1.1971790790557861, 0.6908178329467773]     |
-| 0.6          | [2.0270779132843018, 1.8969502449035645, 1.4789371490478516, 0.9875392913818359]    |
-| 0.7          | [2.506962537765503, 2.656052589416504, 1.924393653869629, 1.4434680938720703]       |
-| 0.8          | [3.3786778450012207, 2.568857192993164, 2.5665550231933594, 2.006620407104492]      |
-| 0.9          | [3.187114715576172, 3.442272663116455, 2.636230945587158, 2.460529088973999]        |
-
-When you have selected the thresholds you can use :
-
-```python
-import torch
-from transformers import AutoModelForCausalLM, AutoTokenizer
-
-model = AutoModelForCausalLM.from_pretrained("valcore/branchy_phi-2_base", trust_remote_code=True, device_map="cpu")
-tokenizer = AutoTokenizer.from_pretrained("microsoft/Phi-2")
-
-model.eval()
-
-inputs = tokenizer('''def print_prime(n):
-   """
-   Print all primes between 1 and n
-   """''', return_tensors="pt", return_attention_mask=False)
-# Put here the selected thresholds :
-model.head_thresholds = torch.tensor([3.187114715576172, 3.442272663116455, 2.636230945587158, 2.460529088973999])
-
-outputs = model.generate(**inputs, max_length=200)
-text = tokenizer.batch_decode(outputs)[0]
-print(text)
-
-
-```
-
-## Citation [optional]
-
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
-
-**BibTeX:**
-
-TBD
-
-
-## Model Card Contact
-
-Florian Valade

config.json

@@ -1,30 +0,0 @@
-{
-  "architectures": [
-    "BranchyCausalModel"
-  ],
-  "auto_map": {
-    "AutoConfig": "BranchyModelConfig.BranchyModelConfig",
-    "AutoModelForCausalLM": "BranchyModel.BranchyCausalModel"
-  },
-  "branch_locations": [
-    6,
-    12,
-    18,
-    24
-  ],
-  "branch_number": 4,
-  "confidence_metric": "breaking_ties",
-  "copy_lm_head": false,
-  "head_thresholds": [
-    10.0,
-    10.0,
-    10.0,
-    10.0
-  ],
-  "head_window_size": 512,
-  "model_str": "microsoft/phi-2",
-  "model_type": "branchy",
-  "penalty_weight": 0.9,
-  "torch_dtype": "float32",
-  "transformers_version": "4.40.2"
-}

generation_config.json

@@ -1,4 +0,0 @@
-{
-  "_from_model_config": true,
-  "transformers_version": "4.40.2"
-}

model-00001-of-00003.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:de9690424cd10d30cc5bbbf31b5ba7149fe2d1b4d1c9b3e28378c37496dfddcc
-size 4982355512

model-00002-of-00003.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:526f616bb5753775548b200b2d5afffa862bf3a17cf53c004b1ba8d702fb5890
-size 4982541984

model-00003-of-00003.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:963120cc9ecfbdd250e505d8a33ef881aa1cc393b06fe3bc9a7b7be286c3c242
-size 3251942344

model.safetensors.index.json

@@ -1,476 +0,0 @@
-{
-  "metadata": {
-    "total_size": 13216788480
-  },
-  "weight_map": {
-    "branches.0.layernorm.bias": "model-00003-of-00003.safetensors",
-    "branches.0.layernorm.weight": "model-00003-of-00003.safetensors",
-    "branches.0.lm_head.bias": "model-00003-of-00003.safetensors",
-    "branches.0.lm_head.weight": "model-00003-of-00003.safetensors",
-    "branches.1.layernorm.bias": "model-00003-of-00003.safetensors",
-    "branches.1.layernorm.weight": "model-00003-of-00003.safetensors",
-    "branches.1.lm_head.bias": "model-00003-of-00003.safetensors",
-    "branches.1.lm_head.weight": "model-00003-of-00003.safetensors",
-    "branches.2.layernorm.bias": "model-00003-of-00003.safetensors",
-    "branches.2.layernorm.weight": "model-00003-of-00003.safetensors",
-    "branches.2.lm_head.bias": "model-00003-of-00003.safetensors",
-    "branches.2.lm_head.weight": "model-00003-of-00003.safetensors",
-    "branches.3.layernorm.bias": "model-00003-of-00003.safetensors",
-    "branches.3.layernorm.weight": "model-00003-of-00003.safetensors",
-    "branches.3.lm_head.bias": "model-00003-of-00003.safetensors",
-    "branches.3.lm_head.weight": "model-00003-of-00003.safetensors",
-    "lm_head.bias": "model-00003-of-00003.safetensors",
-    "lm_head.weight": "model-00003-of-00003.safetensors",
-    "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
-    "model.final_layernorm.bias": "model-00003-of-00003.safetensors",
-    "model.final_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.0.input_layernorm.bias": "model-00001-of-00003.safetensors",
-    "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.0.mlp.fc1.bias": "model-00001-of-00003.safetensors",
-    "model.layers.0.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "model.layers.0.mlp.fc2.bias": "model-00001-of-00003.safetensors",
-    "model.layers.0.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "model.layers.0.self_attn.dense.bias": "model-00001-of-00003.safetensors",
-    "model.layers.0.self_attn.dense.weight": "model-00001-of-00003.safetensors",
-    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
-    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
-    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
-    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.input_layernorm.bias": "model-00001-of-00003.safetensors",
-    "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.mlp.fc1.bias": "model-00001-of-00003.safetensors",
-    "model.layers.1.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.mlp.fc2.bias": "model-00001-of-00003.safetensors",
-    "model.layers.1.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.self_attn.dense.bias": "model-00001-of-00003.safetensors",
-    "model.layers.1.self_attn.dense.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
-    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
-    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
-    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.10.input_layernorm.bias": "model-00001-of-00003.safetensors",
-    "model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.10.mlp.fc1.bias": "model-00001-of-00003.safetensors",
-    "model.layers.10.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "model.layers.10.mlp.fc2.bias": "model-00001-of-00003.safetensors",
-    "model.layers.10.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "model.layers.10.self_attn.dense.bias": "model-00001-of-00003.safetensors",
-    "model.layers.10.self_attn.dense.weight": "model-00001-of-00003.safetensors",
-    "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
-    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
-    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
-    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.11.input_layernorm.bias": "model-00001-of-00003.safetensors",
-    "model.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.11.mlp.fc1.bias": "model-00001-of-00003.safetensors",
-    "model.layers.11.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "model.layers.11.mlp.fc2.bias": "model-00001-of-00003.safetensors",
-    "model.layers.11.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "model.layers.11.self_attn.dense.bias": "model-00001-of-00003.safetensors",
-    "model.layers.11.self_attn.dense.weight": "model-00001-of-00003.safetensors",
-    "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
-    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
-    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
-    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.12.input_layernorm.bias": "model-00001-of-00003.safetensors",
-    "model.layers.12.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.12.mlp.fc1.bias": "model-00001-of-00003.safetensors",
-    "model.layers.12.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "model.layers.12.mlp.fc2.bias": "model-00001-of-00003.safetensors",
-    "model.layers.12.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "model.layers.12.self_attn.dense.bias": "model-00001-of-00003.safetensors",
-    "model.layers.12.self_attn.dense.weight": "model-00001-of-00003.safetensors",
-    "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
-    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
-    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
-    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.13.input_layernorm.bias": "model-00001-of-00003.safetensors",
-    "model.layers.13.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.13.mlp.fc1.bias": "model-00001-of-00003.safetensors",
-    "model.layers.13.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "model.layers.13.mlp.fc2.bias": "model-00001-of-00003.safetensors",
-    "model.layers.13.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "model.layers.13.self_attn.dense.bias": "model-00001-of-00003.safetensors",
-    "model.layers.13.self_attn.dense.weight": "model-00001-of-00003.safetensors",
-    "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
-    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
-    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
-    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.14.input_layernorm.bias": "model-00002-of-00003.safetensors",
-    "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.mlp.fc1.bias": "model-00002-of-00003.safetensors",
-    "model.layers.14.mlp.fc1.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.mlp.fc2.bias": "model-00002-of-00003.safetensors",
-    "model.layers.14.mlp.fc2.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.self_attn.dense.bias": "model-00002-of-00003.safetensors",
-    "model.layers.14.self_attn.dense.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
-    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
-    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.input_layernorm.bias": "model-00002-of-00003.safetensors",
-    "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.mlp.fc1.bias": "model-00002-of-00003.safetensors",
-    "model.layers.15.mlp.fc1.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.mlp.fc2.bias": "model-00002-of-00003.safetensors",
-    "model.layers.15.mlp.fc2.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.self_attn.dense.bias": "model-00002-of-00003.safetensors",
-    "model.layers.15.self_attn.dense.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.input_layernorm.bias": "model-00002-of-00003.safetensors",
-    "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.mlp.fc1.bias": "model-00002-of-00003.safetensors",
-    "model.layers.16.mlp.fc1.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.mlp.fc2.bias": "model-00002-of-00003.safetensors",
-    "model.layers.16.mlp.fc2.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.self_attn.dense.bias": "model-00002-of-00003.safetensors",
-    "model.layers.16.self_attn.dense.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.input_layernorm.bias": "model-00002-of-00003.safetensors",
-    "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.mlp.fc1.bias": "model-00002-of-00003.safetensors",
-    "model.layers.17.mlp.fc1.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.mlp.fc2.bias": "model-00002-of-00003.safetensors",
-    "model.layers.17.mlp.fc2.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.self_attn.dense.bias": "model-00002-of-00003.safetensors",
-    "model.layers.17.self_attn.dense.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.input_layernorm.bias": "model-00002-of-00003.safetensors",
-    "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.mlp.fc1.bias": "model-00002-of-00003.safetensors",
-    "model.layers.18.mlp.fc1.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.mlp.fc2.bias": "model-00002-of-00003.safetensors",
-    "model.layers.18.mlp.fc2.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.self_attn.dense.bias": "model-00002-of-00003.safetensors",
-    "model.layers.18.self_attn.dense.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.19.input_layernorm.bias": "model-00002-of-00003.safetensors",
-    "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.19.mlp.fc1.bias": "model-00002-of-00003.safetensors",
-    "model.layers.19.mlp.fc1.weight": "model-00002-of-00003.safetensors",
-    "model.layers.19.mlp.fc2.bias": "model-00002-of-00003.safetensors",
-    "model.layers.19.mlp.fc2.weight": "model-00002-of-00003.safetensors",
-    "model.layers.19.self_attn.dense.bias": "model-00002-of-00003.safetensors",
-    "model.layers.19.self_attn.dense.weight": "model-00002-of-00003.safetensors",
-    "model.layers.19.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.19.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.19.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.2.input_layernorm.bias": "model-00001-of-00003.safetensors",
-    "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.2.mlp.fc1.bias": "model-00001-of-00003.safetensors",
-    "model.layers.2.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "model.layers.2.mlp.fc2.bias": "model-00001-of-00003.safetensors",
-    "model.layers.2.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "model.layers.2.self_attn.dense.bias": "model-00001-of-00003.safetensors",
-    "model.layers.2.self_attn.dense.weight": "model-00001-of-00003.safetensors",
-    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
-    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
-    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
-    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.20.input_layernorm.bias": "model-00002-of-00003.safetensors",
-    "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.20.mlp.fc1.bias": "model-00002-of-00003.safetensors",
-    "model.layers.20.mlp.fc1.weight": "model-00002-of-00003.safetensors",
-    "model.layers.20.mlp.fc2.bias": "model-00002-of-00003.safetensors",
-    "model.layers.20.mlp.fc2.weight": "model-00002-of-00003.safetensors",
-    "model.layers.20.self_attn.dense.bias": "model-00002-of-00003.safetensors",
-    "model.layers.20.self_attn.dense.weight": "model-00002-of-00003.safetensors",
-    "model.layers.20.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.20.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.20.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.21.input_layernorm.bias": "model-00002-of-00003.safetensors",
-    "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.21.mlp.fc1.bias": "model-00002-of-00003.safetensors",
-    "model.layers.21.mlp.fc1.weight": "model-00002-of-00003.safetensors",
-    "model.layers.21.mlp.fc2.bias": "model-00002-of-00003.safetensors",
-    "model.layers.21.mlp.fc2.weight": "model-00002-of-00003.safetensors",
-    "model.layers.21.self_attn.dense.bias": "model-00002-of-00003.safetensors",
-    "model.layers.21.self_attn.dense.weight": "model-00002-of-00003.safetensors",
-    "model.layers.21.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.21.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.21.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.22.input_layernorm.bias": "model-00002-of-00003.safetensors",
-    "model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.22.mlp.fc1.bias": "model-00002-of-00003.safetensors",
-    "model.layers.22.mlp.fc1.weight": "model-00002-of-00003.safetensors",
-    "model.layers.22.mlp.fc2.bias": "model-00002-of-00003.safetensors",
-    "model.layers.22.mlp.fc2.weight": "model-00002-of-00003.safetensors",
-    "model.layers.22.self_attn.dense.bias": "model-00002-of-00003.safetensors",
-    "model.layers.22.self_attn.dense.weight": "model-00002-of-00003.safetensors",
-    "model.layers.22.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.22.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.22.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.23.input_layernorm.bias": "model-00002-of-00003.safetensors",
-    "model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.23.mlp.fc1.bias": "model-00002-of-00003.safetensors",
-    "model.layers.23.mlp.fc1.weight": "model-00002-of-00003.safetensors",
-    "model.layers.23.mlp.fc2.bias": "model-00002-of-00003.safetensors",
-    "model.layers.23.mlp.fc2.weight": "model-00002-of-00003.safetensors",
-    "model.layers.23.self_attn.dense.bias": "model-00002-of-00003.safetensors",
-    "model.layers.23.self_attn.dense.weight": "model-00002-of-00003.safetensors",
-    "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.24.input_layernorm.bias": "model-00002-of-00003.safetensors",
-    "model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.24.mlp.fc1.bias": "model-00002-of-00003.safetensors",
-    "model.layers.24.mlp.fc1.weight": "model-00002-of-00003.safetensors",
-    "model.layers.24.mlp.fc2.bias": "model-00002-of-00003.safetensors",
-    "model.layers.24.mlp.fc2.weight": "model-00002-of-00003.safetensors",
-    "model.layers.24.self_attn.dense.bias": "model-00002-of-00003.safetensors",
-    "model.layers.24.self_attn.dense.weight": "model-00002-of-00003.safetensors",
-    "model.layers.24.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.24.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.24.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.25.input_layernorm.bias": "model-00002-of-00003.safetensors",
-    "model.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.25.mlp.fc1.bias": "model-00002-of-00003.safetensors",
-    "model.layers.25.mlp.fc1.weight": "model-00002-of-00003.safetensors",
-    "model.layers.25.mlp.fc2.bias": "model-00002-of-00003.safetensors",
-    "model.layers.25.mlp.fc2.weight": "model-00002-of-00003.safetensors",
-    "model.layers.25.self_attn.dense.bias": "model-00002-of-00003.safetensors",
-    "model.layers.25.self_attn.dense.weight": "model-00002-of-00003.safetensors",
-    "model.layers.25.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.25.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.25.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.26.input_layernorm.bias": "model-00002-of-00003.safetensors",
-    "model.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.26.mlp.fc1.bias": "model-00002-of-00003.safetensors",
-    "model.layers.26.mlp.fc1.weight": "model-00002-of-00003.safetensors",
-    "model.layers.26.mlp.fc2.bias": "model-00002-of-00003.safetensors",
-    "model.layers.26.mlp.fc2.weight": "model-00002-of-00003.safetensors",
-    "model.layers.26.self_attn.dense.bias": "model-00002-of-00003.safetensors",
-    "model.layers.26.self_attn.dense.weight": "model-00002-of-00003.safetensors",
-    "model.layers.26.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.26.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.26.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.27.input_layernorm.bias": "model-00002-of-00003.safetensors",
-    "model.layers.27.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.27.mlp.fc1.bias": "model-00002-of-00003.safetensors",
-    "model.layers.27.mlp.fc1.weight": "model-00002-of-00003.safetensors",
-    "model.layers.27.mlp.fc2.bias": "model-00002-of-00003.safetensors",
-    "model.layers.27.mlp.fc2.weight": "model-00002-of-00003.safetensors",
-    "model.layers.27.self_attn.dense.bias": "model-00002-of-00003.safetensors",
-    "model.layers.27.self_attn.dense.weight": "model-00002-of-00003.safetensors",
-    "model.layers.27.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.27.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.27.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.28.input_layernorm.bias": "model-00002-of-00003.safetensors",
-    "model.layers.28.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.28.mlp.fc1.bias": "model-00002-of-00003.safetensors",
-    "model.layers.28.mlp.fc1.weight": "model-00002-of-00003.safetensors",
-    "model.layers.28.mlp.fc2.bias": "model-00002-of-00003.safetensors",
-    "model.layers.28.mlp.fc2.weight": "model-00002-of-00003.safetensors",
-    "model.layers.28.self_attn.dense.bias": "model-00002-of-00003.safetensors",
-    "model.layers.28.self_attn.dense.weight": "model-00002-of-00003.safetensors",
-    "model.layers.28.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.28.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.28.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.29.input_layernorm.bias": "model-00002-of-00003.safetensors",
-    "model.layers.29.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.29.mlp.fc1.bias": "model-00002-of-00003.safetensors",
-    "model.layers.29.mlp.fc1.weight": "model-00002-of-00003.safetensors",
-    "model.layers.29.mlp.fc2.bias": "model-00002-of-00003.safetensors",
-    "model.layers.29.mlp.fc2.weight": "model-00002-of-00003.safetensors",
-    "model.layers.29.self_attn.dense.bias": "model-00002-of-00003.safetensors",
-    "model.layers.29.self_attn.dense.weight": "model-00002-of-00003.safetensors",
-    "model.layers.29.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.29.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.29.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.3.input_layernorm.bias": "model-00001-of-00003.safetensors",
-    "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.3.mlp.fc1.bias": "model-00001-of-00003.safetensors",
-    "model.layers.3.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "model.layers.3.mlp.fc2.bias": "model-00001-of-00003.safetensors",
-    "model.layers.3.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "model.layers.3.self_attn.dense.bias": "model-00001-of-00003.safetensors",
-    "model.layers.3.self_attn.dense.weight": "model-00001-of-00003.safetensors",
-    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
-    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
-    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
-    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.30.input_layernorm.bias": "model-00003-of-00003.safetensors",
-    "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.30.mlp.fc1.bias": "model-00003-of-00003.safetensors",
-    "model.layers.30.mlp.fc1.weight": "model-00003-of-00003.safetensors",
-    "model.layers.30.mlp.fc2.bias": "model-00003-of-00003.safetensors",
-    "model.layers.30.mlp.fc2.weight": "model-00003-of-00003.safetensors",
-    "model.layers.30.self_attn.dense.bias": "model-00003-of-00003.safetensors",
-    "model.layers.30.self_attn.dense.weight": "model-00003-of-00003.safetensors",
-    "model.layers.30.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
-    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.30.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
-    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.30.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
-    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.31.input_layernorm.bias": "model-00003-of-00003.safetensors",
-    "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.31.mlp.fc1.bias": "model-00003-of-00003.safetensors",
-    "model.layers.31.mlp.fc1.weight": "model-00003-of-00003.safetensors",
-    "model.layers.31.mlp.fc2.bias": "model-00003-of-00003.safetensors",
-    "model.layers.31.mlp.fc2.weight": "model-00003-of-00003.safetensors",
-    "model.layers.31.self_attn.dense.bias": "model-00003-of-00003.safetensors",
-    "model.layers.31.self_attn.dense.weight": "model-00003-of-00003.safetensors",
-    "model.layers.31.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
-    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.31.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
-    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.31.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
-    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.4.input_layernorm.bias": "model-00001-of-00003.safetensors",
-    "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.4.mlp.fc1.bias": "model-00001-of-00003.safetensors",
-    "model.layers.4.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "model.layers.4.mlp.fc2.bias": "model-00001-of-00003.safetensors",
-    "model.layers.4.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "model.layers.4.self_attn.dense.bias": "model-00001-of-00003.safetensors",
-    "model.layers.4.self_attn.dense.weight": "model-00001-of-00003.safetensors",
-    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
-    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
-    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
-    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.5.input_layernorm.bias": "model-00001-of-00003.safetensors",
-    "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.5.mlp.fc1.bias": "model-00001-of-00003.safetensors",
-    "model.layers.5.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "model.layers.5.mlp.fc2.bias": "model-00001-of-00003.safetensors",
-    "model.layers.5.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "model.layers.5.self_attn.dense.bias": "model-00001-of-00003.safetensors",
-    "model.layers.5.self_attn.dense.weight": "model-00001-of-00003.safetensors",
-    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
-    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
-    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
-    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.6.input_layernorm.bias": "model-00001-of-00003.safetensors",
-    "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.6.mlp.fc1.bias": "model-00001-of-00003.safetensors",
-    "model.layers.6.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "model.layers.6.mlp.fc2.bias": "model-00001-of-00003.safetensors",
-    "model.layers.6.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "model.layers.6.self_attn.dense.bias": "model-00001-of-00003.safetensors",
-    "model.layers.6.self_attn.dense.weight": "model-00001-of-00003.safetensors",
-    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
-    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
-    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
-    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.7.input_layernorm.bias": "model-00001-of-00003.safetensors",
-    "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.7.mlp.fc1.bias": "model-00001-of-00003.safetensors",
-    "model.layers.7.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "model.layers.7.mlp.fc2.bias": "model-00001-of-00003.safetensors",
-    "model.layers.7.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "model.layers.7.self_attn.dense.bias": "model-00001-of-00003.safetensors",
-    "model.layers.7.self_attn.dense.weight": "model-00001-of-00003.safetensors",
-    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
-    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
-    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
-    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.8.input_layernorm.bias": "model-00001-of-00003.safetensors",
-    "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.8.mlp.fc1.bias": "model-00001-of-00003.safetensors",
-    "model.layers.8.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "model.layers.8.mlp.fc2.bias": "model-00001-of-00003.safetensors",
-    "model.layers.8.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "model.layers.8.self_attn.dense.bias": "model-00001-of-00003.safetensors",
-    "model.layers.8.self_attn.dense.weight": "model-00001-of-00003.safetensors",
-    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
-    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
-    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
-    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.9.input_layernorm.bias": "model-00001-of-00003.safetensors",
-    "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.9.mlp.fc1.bias": "model-00001-of-00003.safetensors",
-    "model.layers.9.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "model.layers.9.mlp.fc2.bias": "model-00001-of-00003.safetensors",
-    "model.layers.9.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "model.layers.9.self_attn.dense.bias": "model-00001-of-00003.safetensors",
-    "model.layers.9.self_attn.dense.weight": "model-00001-of-00003.safetensors",
-    "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
-    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
-    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
-    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors"
-  }
-}