Upload 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 +1,43 @@
+{
+  "_name_or_path": "/content/jais-arabic-math-tutor",
+  "activation_function": "swiglu",
+  "alibi_scaling": null,
+  "architectures": [
+    "JAISModel"
+  ],
+  "attn_pdrop": 0.0,
+  "auto_map": {
+    "AutoConfig": "configuration_jais.JAISConfig",
+    "AutoModel": "inceptionai/jais-family-1p3b-chat--modeling_jais.JAISModel",
+    "AutoModelForCausalLM": "inceptionai/jais-family-1p3b-chat--modeling_jais.JAISLMHeadModel",
+    "AutoModelForQuestionAnswering": "inceptionai/jais-family-1p3b-chat--modeling_jais.JAISForQuestionAnswering",
+    "AutoModelForSequenceClassification": "inceptionai/jais-family-1p3b-chat--modeling_jais.JAISForSequenceClassification",
+    "AutoModelForTokenClassification": "inceptionai/jais-family-1p3b-chat--modeling_jais.JAISForTokenClassification"
+  },
+  "bos_token_id": 0,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 0,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "jais",
+  "mup_embeddings_scale": 9.1705785388303,
+  "mup_output_alpha": 1.09518349815769,
+  "mup_scale_qk_dot_by_d": true,
+  "mup_width_scale": 0.125,
+  "n_embd": 2048,
+  "n_head": 16,
+  "n_inner": 5472,
+  "n_layer": 24,
+  "n_positions": 2048,
+  "pad_token_id": 0,
+  "position_embedding_type": "alibi",
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.0,
+  "rotary_dim": null,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.49.0",
+  "use_cache": true,
+  "vocab_size": 84992
+}

configuration_jais.py

@@ -0,0 +1,196 @@
+# coding=utf-8
+# Copyright 2023 The OpenAI Team Authors and HuggingFace Inc. team.
+# Copyright (c) 2018, NVIDIA CORPORATION.  All rights reserved.
+# Copyright 2023 Cerebras Systems.
+#
+# 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.
+""" JAIS configuration"""
+
+from transformers.configuration_utils import PretrainedConfig
+from transformers.utils import logging
+
+
+logger = logging.get_logger(__name__)
+
+class JAISConfig(PretrainedConfig):
+    """
+    This is the configuration class to store the configuration of a [`JAISModel`]. It is used to instantiate a JAIS
+    model according to the specified arguments, defining the model architecture.
+
+    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 50257):
+            Vocabulary size of the JAIS model. Defines the number of different tokens that can be represented by the
+            `inputs_ids` passed when calling [`JAISModel`].
+        n_positions (`int`, *optional*, defaults to 1024):
+            The maximum sequence length that this model might ever be used with. Typically set this to something large
+            just in case (e.g., 512 or 1024 or 2048).
+        n_embd (`int`, *optional*, defaults to 768):
+            Dimensionality of the embeddings and hidden states.
+        n_layer (`int`, *optional*, defaults to 12):
+            Number of hidden layers in the Transformer encoder.
+        n_head (`int`, *optional*, defaults to 12):
+            Number of attention heads for each attention layer in the Transformer encoder.
+        n_inner (`int`, *optional*, defaults to None):
+            Dimensionality of the inner feed-forward layers. `None` will set it to 4 times n_embd
+        activation_function (`str`, *optional*, defaults to `"gelu"`):
+            Activation function, to be selected in the list `["relu", "silu", "gelu", "tanh", "gelu_new", "swiglu"]`.
+        resid_pdrop (`float`, *optional*, defaults to 0.1):
+            The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.
+        embd_pdrop (`float`, *optional*, defaults to 0.1):
+            The dropout ratio for the embeddings.
+        attn_pdrop (`float`, *optional*, defaults to 0.1):
+            The dropout ratio for the attention.
+        layer_norm_epsilon (`float`, *optional*, defaults to 1e-5):
+            The epsilon to use in the layer normalization layers.
+        initializer_range (`float`, *optional*, defaults to 0.02):
+            The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
+        scale_attn_weights (`bool`, *optional*, defaults to `True`):
+            Scale attention weights by dividing by sqrt(hidden_size)..
+        use_cache (`bool`, *optional*, defaults to `True`):
+            Whether or not the model should return the last key/values attentions (not used by all models).
+        scale_attn_by_inverse_layer_idx (`bool`, *optional*, defaults to `False`):
+            Whether to additionally scale attention weights by `1 / layer_idx + 1`.
+        reorder_and_upcast_attn (`bool`, *optional*, defaults to `False`):
+            Whether to scale keys (K) prior to computing attention (dot-product) and upcast attention
+            dot-product/softmax to float() when training with mixed precision.
+        position_embedding_type (`str`, *optional*, defaults to `"learned"`):
+            Positional embedding can be either `"alibi"` or `"learned"`.
+        mup_width_scale (`float`, *optional*, defaults to 1.0):
+            muP parameter to scale learning rate and initializers. Calculated as (`d_model,0 / d_model`), where
+            `d_model` is the model's width and `d_model,0` is the proxy model's width.
+        mup_embeddings_scale (`float`, *optional*, defaults to 1.0):
+            muP parameter to scale token and position embeddings.
+        mup_output_alpha (`float`, *optional*, defaults to 1.0):
+            muP parameter to scale output logits (`output_logits_scale = mup_output_alpha * mup_width_scale`).
+        mup_scale_qk_dot_by_d (`bool`, *optional*, defaults to `False`):
+            Scale attention weights by dividing by hidden_size instead of sqrt(hidden_size). Need to set
+            scale_attn_weights to `True` as well.
+        alibi_scaling (`Dict`, *optional*):
+            Dictionary containing the scaling configuration for ALiBi embeddings. Currently only supports linear
+            scaling strategy. Can specify either the scaling `factor` (must be a float greater than 1) for fixed scaling 
+            or `train_seq_len` for dynamic scaling on input samples with sequence length > `train_seq_len`. The expected
+            formats are `{"type": strategy name, "factor": scaling factor}` or
+            `{"type": strategy name, "train_seq_len": training sequence length}`.
+
+    Example:
+
+    ```python
+    >>> from transformers import JAISConfig, JAISModel
+
+    >>> # Initializing a JAIS configuration
+    >>> configuration = JAISConfig()
+
+    >>> # Initializing a model (with random weights) from the configuration
+    >>> model = JAISModel(configuration)
+
+    >>> # Accessing the model configuration
+    >>> configuration = model.config
+    ```"""
+
+    model_type = "jais"
+    keys_to_ignore_at_inference = ["past_key_values"]
+    attribute_map = {
+        "hidden_size": "n_embd",
+        "max_position_embeddings": "n_positions",
+        "num_attention_heads": "n_head",
+        "num_hidden_layers": "n_layer",
+    }
+
+    def __init__(
+        self,
+        vocab_size=50257,
+        n_positions=1024,
+        n_embd=768,
+        n_layer=12,
+        n_head=12,
+        n_inner=None,
+        activation_function="gelu_new",
+        resid_pdrop=0.1,
+        embd_pdrop=0.1,
+        attn_pdrop=0.1,
+        layer_norm_epsilon=1e-5,
+        initializer_range=0.02,
+        scale_attn_weights=True,
+        use_cache=True,
+        bos_token_id=50256,
+        eos_token_id=50256,
+        scale_attn_by_inverse_layer_idx=False,
+        reorder_and_upcast_attn=False,
+        position_embedding_type="learned",
+        mup_width_scale=1.0,
+        mup_embeddings_scale=1.0,
+        mup_output_alpha=1.0,
+        mup_scale_qk_dot_by_d=False,
+        alibi_scaling=None,
+        **kwargs,
+    ):
+        self.vocab_size = vocab_size
+        self.n_positions = n_positions
+        self.n_embd = n_embd
+        self.n_layer = n_layer
+        self.n_head = n_head
+        self.n_inner = n_inner
+        self.activation_function = activation_function
+        self.resid_pdrop = resid_pdrop
+        self.embd_pdrop = embd_pdrop
+        self.attn_pdrop = attn_pdrop
+        self.layer_norm_epsilon = layer_norm_epsilon
+        self.initializer_range = initializer_range
+        self.scale_attn_weights = scale_attn_weights
+        self.use_cache = use_cache
+        self.scale_attn_by_inverse_layer_idx = scale_attn_by_inverse_layer_idx
+        self.reorder_and_upcast_attn = reorder_and_upcast_attn
+
+        self.bos_token_id = bos_token_id
+        self.eos_token_id = eos_token_id
+
+        self.position_embedding_type = position_embedding_type
+        self.mup_width_scale = mup_width_scale
+        self.mup_embeddings_scale = mup_embeddings_scale
+        self.mup_output_alpha = mup_output_alpha
+        self.mup_scale_qk_dot_by_d = mup_scale_qk_dot_by_d
+
+        self.alibi_scaling = alibi_scaling
+        self._alibi_scaling_validation()
+
+        super().__init__(bos_token_id=bos_token_id, eos_token_id=eos_token_id, **kwargs)
+
+    def _alibi_scaling_validation(self):
+        """
+        Validate the `alibi_scaling` configuration.
+        """
+        if self.alibi_scaling is None:
+            return
+
+        if not isinstance(self.alibi_scaling, dict) or len(self.alibi_scaling) != 2:
+            raise ValueError(
+                "`alibi_scaling` must be a dictionary with two fields, `type` and `factor` or `type` and `train_seq_len`, "
+                f"got {self.alibi_scaling}"
+            )
+        alibi_scaling_type = self.alibi_scaling.get("type", None)
+        alibi_scaling_factor = self.alibi_scaling.get("factor", None)
+        alibi_dynamic_scaling = self.alibi_scaling.get("train_seq_len", None)
+        if alibi_scaling_type is None or alibi_scaling_type != "linear":
+            raise ValueError(
+                f"`alibi_scaling`'s type field must be 'linear', got {alibi_scaling_type}"
+            )
+        if alibi_scaling_factor is not None:
+            if not isinstance(alibi_scaling_factor, float) or alibi_scaling_factor <= 1.0:
+                raise ValueError(f"`alibi_scaling`'s factor field must be a float > 1.0, got {alibi_scaling_factor}")
+        if alibi_dynamic_scaling is not None:
+            if not isinstance(alibi_dynamic_scaling, int) or alibi_dynamic_scaling <= 1:
+                raise ValueError(f"`alibi_scaling`'s `train_seq_len` field must be an integer > 1, got {alibi_dynamic_scaling}")

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70e4852297f6afe2b380df70f8cf1f60360a817b02e0ac006c10183ddfc2ed9f
+size 4999288080

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cca18b961eda21cdb208a556702a9b6b90a72753633de4fe5bc4d8cc9f4ac1ef
+size 537964176

model.safetensors.index.json

@@ -0,0 +1,347 @@
+{
+  "metadata": {
+    "total_size": 5537220672
+  },
+  "weight_map": {
+    "h.0.attn.c_attn.bias": "model-00001-of-00002.safetensors",
+    "h.0.attn.c_attn.weight": "model-00001-of-00002.safetensors",
+    "h.0.attn.c_proj.bias": "model-00001-of-00002.safetensors",
+    "h.0.attn.c_proj.weight": "model-00001-of-00002.safetensors",
+    "h.0.ln_1.bias": "model-00001-of-00002.safetensors",
+    "h.0.ln_1.weight": "model-00001-of-00002.safetensors",
+    "h.0.ln_2.bias": "model-00001-of-00002.safetensors",
+    "h.0.ln_2.weight": "model-00001-of-00002.safetensors",
+    "h.0.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "h.0.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "h.0.mlp.c_fc2.bias": "model-00001-of-00002.safetensors",
+    "h.0.mlp.c_fc2.weight": "model-00001-of-00002.safetensors",
+    "h.0.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "h.0.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "h.1.attn.c_attn.bias": "model-00001-of-00002.safetensors",
+    "h.1.attn.c_attn.weight": "model-00001-of-00002.safetensors",
+    "h.1.attn.c_proj.bias": "model-00001-of-00002.safetensors",
+    "h.1.attn.c_proj.weight": "model-00001-of-00002.safetensors",
+    "h.1.ln_1.bias": "model-00001-of-00002.safetensors",
+    "h.1.ln_1.weight": "model-00001-of-00002.safetensors",
+    "h.1.ln_2.bias": "model-00001-of-00002.safetensors",
+    "h.1.ln_2.weight": "model-00001-of-00002.safetensors",
+    "h.1.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "h.1.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "h.1.mlp.c_fc2.bias": "model-00001-of-00002.safetensors",
+    "h.1.mlp.c_fc2.weight": "model-00001-of-00002.safetensors",
+    "h.1.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "h.1.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "h.10.attn.c_attn.bias": "model-00001-of-00002.safetensors",
+    "h.10.attn.c_attn.weight": "model-00001-of-00002.safetensors",
+    "h.10.attn.c_proj.bias": "model-00001-of-00002.safetensors",
+    "h.10.attn.c_proj.weight": "model-00001-of-00002.safetensors",
+    "h.10.ln_1.bias": "model-00001-of-00002.safetensors",
+    "h.10.ln_1.weight": "model-00001-of-00002.safetensors",
+    "h.10.ln_2.bias": "model-00001-of-00002.safetensors",
+    "h.10.ln_2.weight": "model-00001-of-00002.safetensors",
+    "h.10.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "h.10.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "h.10.mlp.c_fc2.bias": "model-00001-of-00002.safetensors",
+    "h.10.mlp.c_fc2.weight": "model-00001-of-00002.safetensors",
+    "h.10.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "h.10.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "h.11.attn.c_attn.bias": "model-00001-of-00002.safetensors",
+    "h.11.attn.c_attn.weight": "model-00001-of-00002.safetensors",
+    "h.11.attn.c_proj.bias": "model-00001-of-00002.safetensors",
+    "h.11.attn.c_proj.weight": "model-00001-of-00002.safetensors",
+    "h.11.ln_1.bias": "model-00001-of-00002.safetensors",
+    "h.11.ln_1.weight": "model-00001-of-00002.safetensors",
+    "h.11.ln_2.bias": "model-00001-of-00002.safetensors",
+    "h.11.ln_2.weight": "model-00001-of-00002.safetensors",
+    "h.11.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "h.11.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "h.11.mlp.c_fc2.bias": "model-00001-of-00002.safetensors",
+    "h.11.mlp.c_fc2.weight": "model-00001-of-00002.safetensors",
+    "h.11.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "h.11.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "h.12.attn.c_attn.bias": "model-00001-of-00002.safetensors",
+    "h.12.attn.c_attn.weight": "model-00001-of-00002.safetensors",
+    "h.12.attn.c_proj.bias": "model-00001-of-00002.safetensors",
+    "h.12.attn.c_proj.weight": "model-00001-of-00002.safetensors",
+    "h.12.ln_1.bias": "model-00001-of-00002.safetensors",
+    "h.12.ln_1.weight": "model-00001-of-00002.safetensors",
+    "h.12.ln_2.bias": "model-00001-of-00002.safetensors",
+    "h.12.ln_2.weight": "model-00001-of-00002.safetensors",
+    "h.12.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "h.12.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "h.12.mlp.c_fc2.bias": "model-00001-of-00002.safetensors",
+    "h.12.mlp.c_fc2.weight": "model-00001-of-00002.safetensors",
+    "h.12.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "h.12.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "h.13.attn.c_attn.bias": "model-00001-of-00002.safetensors",
+    "h.13.attn.c_attn.weight": "model-00001-of-00002.safetensors",
+    "h.13.attn.c_proj.bias": "model-00001-of-00002.safetensors",
+    "h.13.attn.c_proj.weight": "model-00001-of-00002.safetensors",
+    "h.13.ln_1.bias": "model-00001-of-00002.safetensors",
+    "h.13.ln_1.weight": "model-00001-of-00002.safetensors",
+    "h.13.ln_2.bias": "model-00001-of-00002.safetensors",
+    "h.13.ln_2.weight": "model-00001-of-00002.safetensors",
+    "h.13.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "h.13.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "h.13.mlp.c_fc2.bias": "model-00001-of-00002.safetensors",
+    "h.13.mlp.c_fc2.weight": "model-00001-of-00002.safetensors",
+    "h.13.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "h.13.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "h.14.attn.c_attn.bias": "model-00001-of-00002.safetensors",
+    "h.14.attn.c_attn.weight": "model-00001-of-00002.safetensors",
+    "h.14.attn.c_proj.bias": "model-00001-of-00002.safetensors",
+    "h.14.attn.c_proj.weight": "model-00001-of-00002.safetensors",
+    "h.14.ln_1.bias": "model-00001-of-00002.safetensors",
+    "h.14.ln_1.weight": "model-00001-of-00002.safetensors",
+    "h.14.ln_2.bias": "model-00001-of-00002.safetensors",
+    "h.14.ln_2.weight": "model-00001-of-00002.safetensors",
+    "h.14.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "h.14.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "h.14.mlp.c_fc2.bias": "model-00001-of-00002.safetensors",
+    "h.14.mlp.c_fc2.weight": "model-00001-of-00002.safetensors",
+    "h.14.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "h.14.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "h.15.attn.c_attn.bias": "model-00001-of-00002.safetensors",
+    "h.15.attn.c_attn.weight": "model-00001-of-00002.safetensors",
+    "h.15.attn.c_proj.bias": "model-00001-of-00002.safetensors",
+    "h.15.attn.c_proj.weight": "model-00001-of-00002.safetensors",
+    "h.15.ln_1.bias": "model-00001-of-00002.safetensors",
+    "h.15.ln_1.weight": "model-00001-of-00002.safetensors",
+    "h.15.ln_2.bias": "model-00001-of-00002.safetensors",
+    "h.15.ln_2.weight": "model-00001-of-00002.safetensors",
+    "h.15.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "h.15.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "h.15.mlp.c_fc2.bias": "model-00001-of-00002.safetensors",
+    "h.15.mlp.c_fc2.weight": "model-00001-of-00002.safetensors",
+    "h.15.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "h.15.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "h.16.attn.c_attn.bias": "model-00001-of-00002.safetensors",
+    "h.16.attn.c_attn.weight": "model-00001-of-00002.safetensors",
+    "h.16.attn.c_proj.bias": "model-00001-of-00002.safetensors",
+    "h.16.attn.c_proj.weight": "model-00001-of-00002.safetensors",
+    "h.16.ln_1.bias": "model-00001-of-00002.safetensors",
+    "h.16.ln_1.weight": "model-00001-of-00002.safetensors",
+    "h.16.ln_2.bias": "model-00001-of-00002.safetensors",
+    "h.16.ln_2.weight": "model-00001-of-00002.safetensors",
+    "h.16.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "h.16.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "h.16.mlp.c_fc2.bias": "model-00001-of-00002.safetensors",
+    "h.16.mlp.c_fc2.weight": "model-00001-of-00002.safetensors",
+    "h.16.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "h.16.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "h.17.attn.c_attn.bias": "model-00001-of-00002.safetensors",
+    "h.17.attn.c_attn.weight": "model-00001-of-00002.safetensors",
+    "h.17.attn.c_proj.bias": "model-00001-of-00002.safetensors",
+    "h.17.attn.c_proj.weight": "model-00001-of-00002.safetensors",
+    "h.17.ln_1.bias": "model-00001-of-00002.safetensors",
+    "h.17.ln_1.weight": "model-00001-of-00002.safetensors",
+    "h.17.ln_2.bias": "model-00001-of-00002.safetensors",
+    "h.17.ln_2.weight": "model-00001-of-00002.safetensors",
+    "h.17.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "h.17.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "h.17.mlp.c_fc2.bias": "model-00001-of-00002.safetensors",
+    "h.17.mlp.c_fc2.weight": "model-00001-of-00002.safetensors",
+    "h.17.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "h.17.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "h.18.attn.c_attn.bias": "model-00001-of-00002.safetensors",
+    "h.18.attn.c_attn.weight": "model-00001-of-00002.safetensors",
+    "h.18.attn.c_proj.bias": "model-00001-of-00002.safetensors",
+    "h.18.attn.c_proj.weight": "model-00001-of-00002.safetensors",
+    "h.18.ln_1.bias": "model-00001-of-00002.safetensors",
+    "h.18.ln_1.weight": "model-00001-of-00002.safetensors",
+    "h.18.ln_2.bias": "model-00001-of-00002.safetensors",
+    "h.18.ln_2.weight": "model-00001-of-00002.safetensors",
+    "h.18.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "h.18.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "h.18.mlp.c_fc2.bias": "model-00001-of-00002.safetensors",
+    "h.18.mlp.c_fc2.weight": "model-00001-of-00002.safetensors",
+    "h.18.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "h.18.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "h.19.attn.c_attn.bias": "model-00001-of-00002.safetensors",
+    "h.19.attn.c_attn.weight": "model-00001-of-00002.safetensors",
+    "h.19.attn.c_proj.bias": "model-00001-of-00002.safetensors",
+    "h.19.attn.c_proj.weight": "model-00001-of-00002.safetensors",
+    "h.19.ln_1.bias": "model-00001-of-00002.safetensors",
+    "h.19.ln_1.weight": "model-00001-of-00002.safetensors",
+    "h.19.ln_2.bias": "model-00001-of-00002.safetensors",
+    "h.19.ln_2.weight": "model-00001-of-00002.safetensors",
+    "h.19.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "h.19.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "h.19.mlp.c_fc2.bias": "model-00001-of-00002.safetensors",
+    "h.19.mlp.c_fc2.weight": "model-00001-of-00002.safetensors",
+    "h.19.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "h.19.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "h.2.attn.c_attn.bias": "model-00001-of-00002.safetensors",
+    "h.2.attn.c_attn.weight": "model-00001-of-00002.safetensors",
+    "h.2.attn.c_proj.bias": "model-00001-of-00002.safetensors",
+    "h.2.attn.c_proj.weight": "model-00001-of-00002.safetensors",
+    "h.2.ln_1.bias": "model-00001-of-00002.safetensors",
+    "h.2.ln_1.weight": "model-00001-of-00002.safetensors",
+    "h.2.ln_2.bias": "model-00001-of-00002.safetensors",
+    "h.2.ln_2.weight": "model-00001-of-00002.safetensors",
+    "h.2.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "h.2.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "h.2.mlp.c_fc2.bias": "model-00001-of-00002.safetensors",
+    "h.2.mlp.c_fc2.weight": "model-00001-of-00002.safetensors",
+    "h.2.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "h.2.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "h.20.attn.c_attn.bias": "model-00001-of-00002.safetensors",
+    "h.20.attn.c_attn.weight": "model-00001-of-00002.safetensors",
+    "h.20.attn.c_proj.bias": "model-00001-of-00002.safetensors",
+    "h.20.attn.c_proj.weight": "model-00001-of-00002.safetensors",
+    "h.20.ln_1.bias": "model-00001-of-00002.safetensors",
+    "h.20.ln_1.weight": "model-00001-of-00002.safetensors",
+    "h.20.ln_2.bias": "model-00001-of-00002.safetensors",
+    "h.20.ln_2.weight": "model-00001-of-00002.safetensors",
+    "h.20.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "h.20.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "h.20.mlp.c_fc2.bias": "model-00001-of-00002.safetensors",
+    "h.20.mlp.c_fc2.weight": "model-00001-of-00002.safetensors",
+    "h.20.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "h.20.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "h.21.attn.c_attn.bias": "model-00001-of-00002.safetensors",
+    "h.21.attn.c_attn.weight": "model-00001-of-00002.safetensors",
+    "h.21.attn.c_proj.bias": "model-00001-of-00002.safetensors",
+    "h.21.attn.c_proj.weight": "model-00001-of-00002.safetensors",
+    "h.21.ln_1.bias": "model-00001-of-00002.safetensors",
+    "h.21.ln_1.weight": "model-00001-of-00002.safetensors",
+    "h.21.ln_2.bias": "model-00001-of-00002.safetensors",
+    "h.21.ln_2.weight": "model-00001-of-00002.safetensors",
+    "h.21.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "h.21.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "h.21.mlp.c_fc2.bias": "model-00002-of-00002.safetensors",
+    "h.21.mlp.c_fc2.weight": "model-00002-of-00002.safetensors",
+    "h.21.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "h.21.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "h.22.attn.c_attn.bias": "model-00002-of-00002.safetensors",
+    "h.22.attn.c_attn.weight": "model-00002-of-00002.safetensors",
+    "h.22.attn.c_proj.bias": "model-00002-of-00002.safetensors",
+    "h.22.attn.c_proj.weight": "model-00002-of-00002.safetensors",
+    "h.22.ln_1.bias": "model-00002-of-00002.safetensors",
+    "h.22.ln_1.weight": "model-00002-of-00002.safetensors",
+    "h.22.ln_2.bias": "model-00002-of-00002.safetensors",
+    "h.22.ln_2.weight": "model-00002-of-00002.safetensors",
+    "h.22.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "h.22.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "h.22.mlp.c_fc2.bias": "model-00002-of-00002.safetensors",
+    "h.22.mlp.c_fc2.weight": "model-00002-of-00002.safetensors",
+    "h.22.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "h.22.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "h.23.attn.c_attn.bias": "model-00002-of-00002.safetensors",
+    "h.23.attn.c_attn.weight": "model-00002-of-00002.safetensors",
+    "h.23.attn.c_proj.bias": "model-00002-of-00002.safetensors",
+    "h.23.attn.c_proj.weight": "model-00002-of-00002.safetensors",
+    "h.23.ln_1.bias": "model-00002-of-00002.safetensors",
+    "h.23.ln_1.weight": "model-00002-of-00002.safetensors",
+    "h.23.ln_2.bias": "model-00002-of-00002.safetensors",
+    "h.23.ln_2.weight": "model-00002-of-00002.safetensors",
+    "h.23.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "h.23.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "h.23.mlp.c_fc2.bias": "model-00002-of-00002.safetensors",
+    "h.23.mlp.c_fc2.weight": "model-00002-of-00002.safetensors",
+    "h.23.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "h.23.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "h.3.attn.c_attn.bias": "model-00001-of-00002.safetensors",
+    "h.3.attn.c_attn.weight": "model-00001-of-00002.safetensors",
+    "h.3.attn.c_proj.bias": "model-00001-of-00002.safetensors",
+    "h.3.attn.c_proj.weight": "model-00001-of-00002.safetensors",
+    "h.3.ln_1.bias": "model-00001-of-00002.safetensors",
+    "h.3.ln_1.weight": "model-00001-of-00002.safetensors",
+    "h.3.ln_2.bias": "model-00001-of-00002.safetensors",
+    "h.3.ln_2.weight": "model-00001-of-00002.safetensors",
+    "h.3.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "h.3.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "h.3.mlp.c_fc2.bias": "model-00001-of-00002.safetensors",
+    "h.3.mlp.c_fc2.weight": "model-00001-of-00002.safetensors",
+    "h.3.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "h.3.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "h.4.attn.c_attn.bias": "model-00001-of-00002.safetensors",
+    "h.4.attn.c_attn.weight": "model-00001-of-00002.safetensors",
+    "h.4.attn.c_proj.bias": "model-00001-of-00002.safetensors",
+    "h.4.attn.c_proj.weight": "model-00001-of-00002.safetensors",
+    "h.4.ln_1.bias": "model-00001-of-00002.safetensors",
+    "h.4.ln_1.weight": "model-00001-of-00002.safetensors",
+    "h.4.ln_2.bias": "model-00001-of-00002.safetensors",
+    "h.4.ln_2.weight": "model-00001-of-00002.safetensors",
+    "h.4.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "h.4.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "h.4.mlp.c_fc2.bias": "model-00001-of-00002.safetensors",
+    "h.4.mlp.c_fc2.weight": "model-00001-of-00002.safetensors",
+    "h.4.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "h.4.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "h.5.attn.c_attn.bias": "model-00001-of-00002.safetensors",
+    "h.5.attn.c_attn.weight": "model-00001-of-00002.safetensors",
+    "h.5.attn.c_proj.bias": "model-00001-of-00002.safetensors",
+    "h.5.attn.c_proj.weight": "model-00001-of-00002.safetensors",
+    "h.5.ln_1.bias": "model-00001-of-00002.safetensors",
+    "h.5.ln_1.weight": "model-00001-of-00002.safetensors",
+    "h.5.ln_2.bias": "model-00001-of-00002.safetensors",
+    "h.5.ln_2.weight": "model-00001-of-00002.safetensors",
+    "h.5.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "h.5.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "h.5.mlp.c_fc2.bias": "model-00001-of-00002.safetensors",
+    "h.5.mlp.c_fc2.weight": "model-00001-of-00002.safetensors",
+    "h.5.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "h.5.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "h.6.attn.c_attn.bias": "model-00001-of-00002.safetensors",
+    "h.6.attn.c_attn.weight": "model-00001-of-00002.safetensors",
+    "h.6.attn.c_proj.bias": "model-00001-of-00002.safetensors",
+    "h.6.attn.c_proj.weight": "model-00001-of-00002.safetensors",
+    "h.6.ln_1.bias": "model-00001-of-00002.safetensors",
+    "h.6.ln_1.weight": "model-00001-of-00002.safetensors",
+    "h.6.ln_2.bias": "model-00001-of-00002.safetensors",
+    "h.6.ln_2.weight": "model-00001-of-00002.safetensors",
+    "h.6.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "h.6.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "h.6.mlp.c_fc2.bias": "model-00001-of-00002.safetensors",
+    "h.6.mlp.c_fc2.weight": "model-00001-of-00002.safetensors",
+    "h.6.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "h.6.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "h.7.attn.c_attn.bias": "model-00001-of-00002.safetensors",
+    "h.7.attn.c_attn.weight": "model-00001-of-00002.safetensors",
+    "h.7.attn.c_proj.bias": "model-00001-of-00002.safetensors",
+    "h.7.attn.c_proj.weight": "model-00001-of-00002.safetensors",
+    "h.7.ln_1.bias": "model-00001-of-00002.safetensors",
+    "h.7.ln_1.weight": "model-00001-of-00002.safetensors",
+    "h.7.ln_2.bias": "model-00001-of-00002.safetensors",
+    "h.7.ln_2.weight": "model-00001-of-00002.safetensors",
+    "h.7.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "h.7.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "h.7.mlp.c_fc2.bias": "model-00001-of-00002.safetensors",
+    "h.7.mlp.c_fc2.weight": "model-00001-of-00002.safetensors",
+    "h.7.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "h.7.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "h.8.attn.c_attn.bias": "model-00001-of-00002.safetensors",
+    "h.8.attn.c_attn.weight": "model-00001-of-00002.safetensors",
+    "h.8.attn.c_proj.bias": "model-00001-of-00002.safetensors",
+    "h.8.attn.c_proj.weight": "model-00001-of-00002.safetensors",
+    "h.8.ln_1.bias": "model-00001-of-00002.safetensors",
+    "h.8.ln_1.weight": "model-00001-of-00002.safetensors",
+    "h.8.ln_2.bias": "model-00001-of-00002.safetensors",
+    "h.8.ln_2.weight": "model-00001-of-00002.safetensors",
+    "h.8.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "h.8.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "h.8.mlp.c_fc2.bias": "model-00001-of-00002.safetensors",
+    "h.8.mlp.c_fc2.weight": "model-00001-of-00002.safetensors",
+    "h.8.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "h.8.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "h.9.attn.c_attn.bias": "model-00001-of-00002.safetensors",
+    "h.9.attn.c_attn.weight": "model-00001-of-00002.safetensors",
+    "h.9.attn.c_proj.bias": "model-00001-of-00002.safetensors",
+    "h.9.attn.c_proj.weight": "model-00001-of-00002.safetensors",
+    "h.9.ln_1.bias": "model-00001-of-00002.safetensors",
+    "h.9.ln_1.weight": "model-00001-of-00002.safetensors",
+    "h.9.ln_2.bias": "model-00001-of-00002.safetensors",
+    "h.9.ln_2.weight": "model-00001-of-00002.safetensors",
+    "h.9.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "h.9.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "h.9.mlp.c_fc2.bias": "model-00001-of-00002.safetensors",
+    "h.9.mlp.c_fc2.weight": "model-00001-of-00002.safetensors",
+    "h.9.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "h.9.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "ln_f.bias": "model-00002-of-00002.safetensors",
+    "ln_f.weight": "model-00002-of-00002.safetensors",
+    "relative_pe.slopes": "model-00002-of-00002.safetensors",
+    "wte.weight": "model-00001-of-00002.safetensors"
+  }
+}