Add model

README.md

@@ -0,0 +1,199 @@
+---
+library_name: transformers
+tags: []
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## 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:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]

config.json

@@ -0,0 +1,51 @@
+{
+  "architectures": [
+    "HyperCLOVAXForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attention_multiplier": 0.0078125,
+  "attn_pdrop": 0.0,
+  "auto_map": {
+    "AutoConfig": "configuration_hyperclovax.HyperCLOVAXConfig",
+    "AutoModel": "modeling_hyperclovax.HyperCLOVAXModel",
+    "AutoModelForCausalLM": "modeling_hyperclovax.HyperCLOVAXForCausalLM"
+  },
+  "bos_token_id": 100257,
+  "deepconf_disable": false,
+  "deepconf_enable": null,
+  "deepconf_threshold": -3.5,
+  "deepconf_top_r": 5,
+  "deepconf_warmup_tokens": 0,
+  "deepconf_window": 512,
+  "embd_pdrop": 0.0,
+  "embedding_multiplier": 10.0,
+  "end_token_id": 100257,
+  "eos_token_id": 100257,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 6144,
+  "initializer_range": 0.012727922061357854,
+  "intermediate_size": 14336,
+  "logits_scaling": 0.125,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "hyperclovax",
+  "num_attention_heads": 48,
+  "num_hidden_layers": 38,
+  "num_key_value_heads": 8,
+  "pad_token_id": 100257,
+  "pretraining_tp": 1,
+  "resid_pdrop": 0.0,
+  "residual_multiplier": 1.0,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 100000000,
+  "summary_first_dropout": 0.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.52.4",
+  "use_cache": false,
+  "use_post_norm": true,
+  "vocab_size": 110592
+}

configuration_hyperclovax.py

@@ -0,0 +1,250 @@
+# coding=utf-8
+# This file was created for the HyperCLOVA X SEED 14B Think architecture.
+# partially copied and modified from https://github.com/huggingface/transformers
+# Copyright 2022 EleutherAI and the HuggingFace Inc. team. All rights reserved.
+#
+# This code is based on EleutherAI's GPT-NeoX library and the GPT-NeoX
+# and OPT implementations in this library. It has been modified from its
+# original forms to accommodate minor architectural differences compared
+# to GPT-NeoX and OPT used by the Meta AI team that trained the model.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+"""HyperCLOVAX model configuration"""
+
+from transformers.configuration_utils import PretrainedConfig
+from typing import Optional
+
+class HyperCLOVAXConfig(PretrainedConfig):
+    r"""
+    This is the configuration class to store the configuration of a [`HyperCLOVAXModel`]. It is used to instantiate an HyperCLOVAX
+    model according to the specified arguments, defining the model architecture. Instantiating a configuration with the
+    defaults will yield a similar configuration to that of the HyperCLOVAX.
+
+    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 32000):
+            Vocabulary size of the HyperCLOVAX model. Defines the number of different tokens that can be represented by the
+            `inputs_ids` passed when calling [`HyperCLOVAXModel`]
+        hidden_size (`int`, *optional*, defaults to 4096):
+            Dimension of the hidden representations.
+        intermediate_size (`int`, *optional*, defaults to 11008):
+            Dimension of the MLP representations.
+        num_hidden_layers (`int`, *optional*, defaults to 32):
+            Number of hidden layers in the Transformer decoder.
+        num_attention_heads (`int`, *optional*, defaults to 32):
+            Number of attention heads for each attention layer in the Transformer decoder.
+        num_key_value_heads (`int`, *optional*):
+            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
+            `num_attention_heads`.
+        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 2048):
+            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`.
+        pad_token_id (`int`, *optional*):
+            Padding token id.
+        bos_token_id (`int`, *optional*, defaults to 1):
+            Beginning of stream token id.
+        eos_token_id (`int`, *optional*, defaults to 2):
+            End of stream token id.
+        pretraining_tp (`int`, *optional*, defaults to 1):
+            Experimental feature. Tensor parallelism rank used during pretraining. Please refer to [this
+            document](https://huggingface.co/docs/transformers/main/perf_train_gpu_many#tensor-parallelism) to
+            understand more about it. This value is necessary to ensure exact reproducibility of the pretraining
+            results. Please refer to [this issue](https://github.com/pytorch/pytorch/issues/76232).
+        tie_word_embeddings (`bool`, *optional*, defaults to `False`):
+            Whether to tie weight embeddings
+        rope_theta (`float`, *optional*, defaults to 10000.0):
+            The base period of the RoPE embeddings.
+        rope_scaling (`Dict`, *optional*):
+            Dictionary containing the scaling configuration for the RoPE embeddings. NOTE: if you apply new rope type
+            and you expect the model to work on longer `max_position_embeddings`, we recommend you to update this value
+            accordingly.
+            Expected contents:
+                `rope_type` (`str`):
+                    The sub-variant of RoPE to use. Can be one of ['default', 'linear', 'dynamic', 'yarn', 'longrope',
+                    'llama3'], with 'default' being the original RoPE implementation.
+                `factor` (`float`, *optional*):
+                    Used with all rope types except 'default'. The scaling factor to apply to the RoPE embeddings. In
+                    most scaling types, a `factor` of x will enable the model to handle sequences of length x *
+                    original maximum pre-trained length.
+                `original_max_position_embeddings` (`int`, *optional*):
+                    Used with 'dynamic', 'longrope' and 'llama3'. The original max position embeddings used during
+                    pretraining.
+                `attention_factor` (`float`, *optional*):
+                    Used with 'yarn' and 'longrope'. The scaling factor to be applied on the attention
+                    computation. If unspecified, it defaults to value recommended by the implementation, using the
+                    `factor` field to infer the suggested value.
+                `beta_fast` (`float`, *optional*):
+                    Only used with 'yarn'. Parameter to set the boundary for extrapolation (only) in the linear
+                    ramp function. If unspecified, it defaults to 32.
+                `beta_slow` (`float`, *optional*):
+                    Only used with 'yarn'. Parameter to set the boundary for interpolation (only) in the linear
+                    ramp function. If unspecified, it defaults to 1.
+                `short_factor` (`List[float]`, *optional*):
+                    Only used with 'longrope'. The scaling factor to be applied to short contexts (<
+                    `original_max_position_embeddings`). Must be a list of numbers with the same length as the hidden
+                    size divided by the number of attention heads divided by 2
+                `long_factor` (`List[float]`, *optional*):
+                    Only used with 'longrope'. The scaling factor to be applied to long contexts (<
+                    `original_max_position_embeddings`). Must be a list of numbers with the same length as the hidden
+                    size divided by the number of attention heads divided by 2
+                `low_freq_factor` (`float`, *optional*):
+                    Only used with 'llama3'. Scaling factor applied to low frequency components of the RoPE
+                `high_freq_factor` (`float`, *optional*):
+                    Only used with 'llama3'. Scaling factor applied to high frequency components of the RoPE
+        attention_bias (`bool`, *optional*, defaults to `False`):
+            Whether to use a bias in the query, key, value and output projection layers during self-attention.
+        attention_dropout (`float`, *optional*, defaults to 0.0):
+            The dropout ratio for the attention probabilities.
+        mlp_bias (`bool`, *optional*, defaults to `False`):
+            Whether to use a bias in up_proj, down_proj and gate_proj layers in the MLP layers.
+        head_dim (`int`, *optional*):
+            The attention head dimension. If None, it will default to hidden_size // num_heads
+        embedding_multiplier (`float, *optional*, defaults to `None`):
+            Multiplier applied to the embedding weights. If `None`, it is equivalent to `1.0`.
+        logits_scaling (`float, *optional*, defaults to `None`):
+            Scaling factor for logits. If `None`, it is equivalent to `1.0`.
+        attention_multiplier (`float, *optional*, defaults to `None`):
+            Multiplier applied to the attention weights. If `None`, it is equivalent to `self.head_dim ** -0.5`.
+        residual_multiplier (`float, *optional*, defaults to `None`):
+            Scaling factor for residual connections. If `None`, it is equivalent to `1.0`.
+        use_post_norm (`bool`, *optional*, defaults to `False`):
+            Determines whether to apply Peri-Layer Normalization. Set to True to enable this feature.
+
+    ```python
+    >>> from transformers import HyperCLOVAXModel, HyperCLOVAXConfig
+
+    >>> # Initializing a HyperCLOVAX HyperCLOVAX style configuration
+    >>> configuration = HyperCLOVAXConfig()
+
+    >>> # Initializing a model from the HyperCLOVAX style configuration
+    >>> model = HyperCLOVAXModel(configuration)
+
+    >>> # Accessing the model configuration
+    >>> configuration = model.config
+    ```"""
+
+    model_type = "hyperclovax"
+    keys_to_ignore_at_inference = ["past_key_values"]
+
+    def __init__(
+        self,
+        vocab_size=32000,
+        hidden_size=4096,
+        intermediate_size=11008,
+        num_hidden_layers=32,
+        num_attention_heads=32,
+        num_key_value_heads=None,
+        hidden_act="silu",
+        max_position_embeddings=2048,
+        initializer_range=0.02,
+        rms_norm_eps=1e-6,
+        use_cache=True,
+        pad_token_id=None,
+        bos_token_id=1,
+        eos_token_id=2,
+        pretraining_tp=1,
+        tie_word_embeddings=False,
+        rope_theta=10000.0,
+        rope_scaling=None,
+        attention_bias=False,
+        attention_dropout=0.0,
+        mlp_bias=False,
+        head_dim=None,
+        embedding_multiplier=None, # MuP
+        logits_scaling=None, # MuP
+        attention_multiplier=None, # MuP
+        residual_multiplier=None, # MuP
+        use_post_norm=False, # Peri-LN (post-norm)
+        # ---- DeepConf (online early-stop) options ----
+        deepconf_enable: Optional[bool] = None,   # None=unset(keeps default ON), True/False=explicitly set
+        deepconf_disable: bool = False,           # True to force OFF (overrides enable)
+        deepconf_window: int = 512,
+        deepconf_top_r: int = 5,
+        deepconf_threshold: float = -3.5,
+        deepconf_warmup_tokens: int = 0,
+        auto_map={
+            "AutoConfig": "configuration_hyperclovax.HyperCLOVAXConfig",
+            "AutoModel": "modeling_hyperclovax.HyperCLOVAXModel",
+            "AutoModelForCausalLM": "modeling_hyperclovax.HyperCLOVAXForCausalLM"
+        },
+        **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
+
+        # 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.pretraining_tp = pretraining_tp
+        self.use_cache = use_cache
+        self.rope_theta = rope_theta
+        self.rope_scaling = rope_scaling
+        self.attention_bias = attention_bias
+        self.attention_dropout = attention_dropout
+        self.mlp_bias = mlp_bias
+        self.head_dim = head_dim if head_dim is not None else self.hidden_size // self.num_attention_heads
+        # Validate the correctness of rotary position embeddings parameters
+        # BC: if there is a 'type' field, copy it it to 'rope_type'.
+        if self.rope_scaling is not None and "type" in self.rope_scaling:
+            self.rope_scaling["rope_type"] = self.rope_scaling["type"]
+        # rope_config_validation(self)
+
+        # MuP
+        self.embedding_multiplier = embedding_multiplier if embedding_multiplier is not None else 1.0
+        self.logits_scaling = logits_scaling if logits_scaling is not None else 1.0
+        self.attention_multiplier = attention_multiplier if attention_multiplier is not None else self.head_dim ** -0.5
+        self.residual_multiplier = residual_multiplier if residual_multiplier is not None else 1.0
+
+        # Peri-LN (post-norm)
+        self.use_post_norm = use_post_norm
+        # DeepConf (store defaults; ENV vars will take precedence in the modeling file)
+        self.deepconf_enable = deepconf_enable
+        self.deepconf_disable = deepconf_disable
+        self.deepconf_window = int(deepconf_window)
+        self.deepconf_top_r = int(deepconf_top_r)
+        self.deepconf_threshold = float(deepconf_threshold)
+        self.deepconf_warmup_tokens = int(deepconf_warmup_tokens)
+
+        super().__init__(
+            pad_token_id=pad_token_id,
+            bos_token_id=bos_token_id,
+            eos_token_id=eos_token_id,
+            tie_word_embeddings=tie_word_embeddings,
+            auto_map=auto_map,
+            **kwargs,
+        )

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 100257,
+  "eos_token_id": 100257,
+  "pad_token_id": 100257,
+  "transformers_version": "4.52.4",
+  "use_cache": false
+}

model-00001-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:305362a08287f1a07c8901b17569030003342501439732b35372f141488e624d
+size 4831938472

model-00002-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff239283211a4d509ae03a47d26eb81981a1e6629b8593e7fea6f7bc982cc7ee
+size 4932899128

model-00003-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a87408267364edb5e0ad365c01d33272ecd767eef3a59dcae20b5c4e2b80d2d9
+size 4932800744

model-00004-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34be38a9cd94474e2145567c0d8d8e772e38811a6b7cc7ff21ad32b78cd82e28
+size 4932899160

model-00005-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04b93ef8634259a055d34eda87bc7f0c07493be1729979da93c7fd0b63b4cfc8
+size 4932800784

model-00006-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0166c99db8788a872fe9677d88095116586807e61466caeffb1b317815025485
+size 4932899168

model-00007-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3091a6c988544d07a79a12ac4e6327d0b80802af7463f657fa55706760a7b16
+size 4932800784

model-00008-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:437804c0b8b0ac88e24253304a7c0d27c0e94ee54fdba2d6b6474f0fcfd71f77
+size 4932899168

model-00009-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2bae7aa1fb3ec4ac0d8a9046a15b8674d80b1165ec423b66c3429416846bd076
+size 4932800784

model-00010-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17ec60ba7881c3afa594a584bde88d806582eab0f7768a70549d377b06544c27
+size 4932899168

model-00011-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c2e182da134b1702e84be4f6bff0157182bb8870963b470da45acc4fd9102f5
+size 4932800784

model-00012-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ced46cb6d54cc2ace518803b1d350211b110560a7d841412b61d22b09f55e
+size 4832061536

model.safetensors.index.json

@@ -0,0 +1,428 @@
+{
+  "metadata": {
+    "total_size": 58992451584
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00012-of-00012.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00012.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00012.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00012.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00012.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00012.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00012.safetensors",
+    "model.layers.0.post_norm1.weight": "model-00001-of-00012.safetensors",
+    "model.layers.0.post_norm2.weight": "model-00001-of-00012.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00012.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00002-of-00012.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00012.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00012.safetensors",
+    "model.layers.1.post_norm1.weight": "model-00002-of-00012.safetensors",
+    "model.layers.1.post_norm2.weight": "model-00002-of-00012.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00012.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00004-of-00012.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00012.safetensors",
+    "model.layers.10.post_norm1.weight": "model-00004-of-00012.safetensors",
+    "model.layers.10.post_norm2.weight": "model-00004-of-00012.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00004-of-00012.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00012.safetensors",
+    "model.layers.11.post_norm1.weight": "model-00004-of-00012.safetensors",
+    "model.layers.11.post_norm2.weight": "model-00004-of-00012.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00005-of-00012.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00005-of-00012.safetensors",
+    "model.layers.12.post_norm1.weight": "model-00005-of-00012.safetensors",
+    "model.layers.12.post_norm2.weight": "model-00005-of-00012.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00005-of-00012.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00005-of-00012.safetensors",
+    "model.layers.13.post_norm1.weight": "model-00005-of-00012.safetensors",
+    "model.layers.13.post_norm2.weight": "model-00005-of-00012.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00005-of-00012.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00005-of-00012.safetensors",
+    "model.layers.14.post_norm1.weight": "model-00005-of-00012.safetensors",
+    "model.layers.14.post_norm2.weight": "model-00005-of-00012.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00006-of-00012.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00006-of-00012.safetensors",
+    "model.layers.15.post_norm1.weight": "model-00006-of-00012.safetensors",
+    "model.layers.15.post_norm2.weight": "model-00006-of-00012.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00006-of-00012.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00006-of-00012.safetensors",
+    "model.layers.16.post_norm1.weight": "model-00006-of-00012.safetensors",
+    "model.layers.16.post_norm2.weight": "model-00006-of-00012.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00006-of-00012.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00006-of-00012.safetensors",
+    "model.layers.17.post_norm1.weight": "model-00006-of-00012.safetensors",
+    "model.layers.17.post_norm2.weight": "model-00006-of-00012.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00006-of-00012.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00006-of-00012.safetensors",
+    "model.layers.18.post_norm1.weight": "model-00006-of-00012.safetensors",
+    "model.layers.18.post_norm2.weight": "model-00006-of-00012.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00007-of-00012.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00007-of-00012.safetensors",
+    "model.layers.19.post_norm1.weight": "model-00007-of-00012.safetensors",
+    "model.layers.19.post_norm2.weight": "model-00007-of-00012.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00002-of-00012.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00012.safetensors",
+    "model.layers.2.post_norm1.weight": "model-00002-of-00012.safetensors",
+    "model.layers.2.post_norm2.weight": "model-00002-of-00012.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00007-of-00012.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00007-of-00012.safetensors",
+    "model.layers.20.post_norm1.weight": "model-00007-of-00012.safetensors",
+    "model.layers.20.post_norm2.weight": "model-00007-of-00012.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00007-of-00012.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00007-of-00012.safetensors",
+    "model.layers.21.post_norm1.weight": "model-00007-of-00012.safetensors",
+    "model.layers.21.post_norm2.weight": "model-00007-of-00012.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00008-of-00012.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00008-of-00012.safetensors",
+    "model.layers.22.post_norm1.weight": "model-00008-of-00012.safetensors",
+    "model.layers.22.post_norm2.weight": "model-00008-of-00012.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00008-of-00012.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00008-of-00012.safetensors",
+    "model.layers.23.post_norm1.weight": "model-00008-of-00012.safetensors",
+    "model.layers.23.post_norm2.weight": "model-00008-of-00012.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00008-of-00012.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00008-of-00012.safetensors",
+    "model.layers.24.post_norm1.weight": "model-00008-of-00012.safetensors",
+    "model.layers.24.post_norm2.weight": "model-00008-of-00012.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00008-of-00012.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00008-of-00012.safetensors",
+    "model.layers.25.post_norm1.weight": "model-00008-of-00012.safetensors",
+    "model.layers.25.post_norm2.weight": "model-00008-of-00012.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00009-of-00012.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00009-of-00012.safetensors",
+    "model.layers.26.post_norm1.weight": "model-00009-of-00012.safetensors",
+    "model.layers.26.post_norm2.weight": "model-00009-of-00012.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00009-of-00012.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00009-of-00012.safetensors",
+    "model.layers.27.post_norm1.weight": "model-00009-of-00012.safetensors",
+    "model.layers.27.post_norm2.weight": "model-00009-of-00012.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00009-of-00012.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00009-of-00012.safetensors",
+    "model.layers.28.post_norm1.weight": "model-00009-of-00012.safetensors",
+    "model.layers.28.post_norm2.weight": "model-00009-of-00012.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00010-of-00012.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00010-of-00012.safetensors",
+    "model.layers.29.post_norm1.weight": "model-00010-of-00012.safetensors",
+    "model.layers.29.post_norm2.weight": "model-00010-of-00012.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00012.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00012.safetensors",
+    "model.layers.3.post_norm1.weight": "model-00002-of-00012.safetensors",
+    "model.layers.3.post_norm2.weight": "model-00002-of-00012.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00010-of-00012.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00010-of-00012.safetensors",
+    "model.layers.30.post_norm1.weight": "model-00010-of-00012.safetensors",
+    "model.layers.30.post_norm2.weight": "model-00010-of-00012.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00010-of-00012.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00010-of-00012.safetensors",
+    "model.layers.31.post_norm1.weight": "model-00010-of-00012.safetensors",
+    "model.layers.31.post_norm2.weight": "model-00010-of-00012.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00010-of-00012.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00010-of-00012.safetensors",
+    "model.layers.32.post_norm1.weight": "model-00010-of-00012.safetensors",
+    "model.layers.32.post_norm2.weight": "model-00010-of-00012.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00011-of-00012.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00011-of-00012.safetensors",
+    "model.layers.33.post_norm1.weight": "model-00011-of-00012.safetensors",
+    "model.layers.33.post_norm2.weight": "model-00011-of-00012.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00011-of-00012.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00011-of-00012.safetensors",
+    "model.layers.34.post_norm1.weight": "model-00011-of-00012.safetensors",
+    "model.layers.34.post_norm2.weight": "model-00011-of-00012.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00011-of-00012.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00011-of-00012.safetensors",
+    "model.layers.35.post_norm1.weight": "model-00011-of-00012.safetensors",
+    "model.layers.35.post_norm2.weight": "model-00011-of-00012.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00012-of-00012.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00012-of-00012.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00012-of-00012.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00012-of-00012.safetensors",
+    "model.layers.36.post_norm1.weight": "model-00012-of-00012.safetensors",
+    "model.layers.36.post_norm2.weight": "model-00012-of-00012.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00012-of-00012.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00012-of-00012.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00012-of-00012.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00012-of-00012.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00012-of-00012.safetensors",
+    "model.layers.37.post_norm1.weight": "model-00012-of-00012.safetensors",
+    "model.layers.37.post_norm2.weight": "model-00012-of-00012.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00012-of-00012.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00012-of-00012.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00012-of-00012.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00012-of-00012.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00012.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00012.safetensors",
+    "model.layers.4.post_norm1.weight": "model-00002-of-00012.safetensors",
+    "model.layers.4.post_norm2.weight": "model-00002-of-00012.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00003-of-00012.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00012.safetensors",
+    "model.layers.5.post_norm1.weight": "model-00003-of-00012.safetensors",
+    "model.layers.5.post_norm2.weight": "model-00003-of-00012.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00003-of-00012.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00012.safetensors",
+    "model.layers.6.post_norm1.weight": "model-00003-of-00012.safetensors",
+    "model.layers.6.post_norm2.weight": "model-00003-of-00012.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00003-of-00012.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00012.safetensors",
+    "model.layers.7.post_norm1.weight": "model-00003-of-00012.safetensors",
+    "model.layers.7.post_norm2.weight": "model-00003-of-00012.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00004-of-00012.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00004-of-00012.safetensors",
+    "model.layers.8.post_norm1.weight": "model-00004-of-00012.safetensors",
+    "model.layers.8.post_norm2.weight": "model-00004-of-00012.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00004-of-00012.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00004-of-00012.safetensors",
+    "model.layers.9.post_norm1.weight": "model-00004-of-00012.safetensors",
+    "model.layers.9.post_norm2.weight": "model-00004-of-00012.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00004-of-00012.safetensors",
+    "model.norm.weight": "model-00012-of-00012.safetensors"
+  }
+}