Upload folder using huggingface_hub

.gitattributes

@@ -0,0 +1,61 @@
+model-00001-of-00061.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00002-of-00061.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00003-of-00061.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00004-of-00061.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00005-of-00061.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00006-of-00061.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00007-of-00061.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00008-of-00061.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00009-of-00061.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00010-of-00061.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00011-of-00061.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00012-of-00061.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00013-of-00061.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00014-of-00061.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00015-of-00061.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00016-of-00061.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00017-of-00061.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00018-of-00061.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00019-of-00061.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00020-of-00061.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00021-of-00061.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00022-of-00061.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00023-of-00061.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00024-of-00061.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00025-of-00061.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00026-of-00061.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00027-of-00061.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00028-of-00061.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00029-of-00061.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00030-of-00061.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00031-of-00061.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00032-of-00061.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00033-of-00061.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00034-of-00061.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00035-of-00061.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00036-of-00061.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00037-of-00061.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00038-of-00061.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00039-of-00061.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00040-of-00061.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00041-of-00061.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00042-of-00061.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00043-of-00061.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00044-of-00061.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00045-of-00061.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00046-of-00061.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00047-of-00061.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00048-of-00061.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00049-of-00061.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00050-of-00061.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00051-of-00061.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00052-of-00061.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00053-of-00061.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00054-of-00061.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00055-of-00061.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00056-of-00061.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00057-of-00061.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00058-of-00061.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00059-of-00061.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00060-of-00061.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00061-of-00061.safetensors filter=lfs diff=lfs merge=lfs -text

LICENSE.txt

@@ -0,0 +1,176 @@
+Databricks Open Model License
+
+By using, reproducing, modifying, distributing, performing or displaying
+any portion or element of DBRX or DBRX Derivatives, or otherwise accepting
+the terms of this Agreement, you agree to be bound by this Agreement.
+
+Version Release Date: March 27, 2024
+
+
+Section 1: Definitions
+
+“Agreement” means these terms and conditions that govern the use, reproduction,
+modification, distribution, performance or display of DBRX and/or DBRX
+Derivatives and any terms and conditions incorporated by reference.
+
+“Databricks” or “we” means Databricks, Inc.
+
+“Licensee” or “you” means you, or your employer or any other person or entity
+(if you are entering into this Agreement on such person or entity’s behalf),
+of the age required under applicable laws, rules or regulations to provide
+legal consent and that has legal authority to bind your employer or such other
+person or entity if you are entering in this Agreement on their behalf.
+
+“DBRX Derivatives” means all (i) modifications to DBRX, (ii) works based on
+DBRX and (iii) any other derivative works thereof. Outputs are not deemed DBRX
+Derivatives.
+
+“DBRX” means the foundational large language models and software and
+algorithms, including machine-learning model code, trained model weights,
+inference-enabling code, training-enabling code, fine-tuning enabling code,
+documentation and other elements of the foregoing identified by Databricks at
+https://github.com/databricks/dbrx, regardless of the source that you obtained
+it from.
+
+“Output” means the results of operating DBRX or DBRX Derivatives.
+
+As used in this Agreement, “including” means “including without limitation.”
+
+
+Section 2: License Rights and Conditions on Use and Distribution
+
+2.1 Grant of Rights
+
+You are granted a non-exclusive, worldwide, non-transferable and royalty-free
+limited license under Databricks’ intellectual property or other rights owned
+by Databricks embodied in DBRX to use, reproduce, distribute, copy, modify,
+and create derivative works of DBRX in accordance with the terms of this
+Agreement.
+
+2.2 Reproduction and Distribution
+
+	1. All distributions of DBRX or DBRX Derivatives must be accompanied by a
+    "Notice" text file that contains the following notice: "DBRX is provided
+    under and subject to the Databricks Open Model License, Copyright ©
+    Databricks, Inc. All rights reserved."
+
+	2. If you distribute or make DBRX or DBRX Derivatives available to a third
+    party, you must provide a copy of this Agreement to such third party.
+
+	3. You must cause any modified files that you distribute to carry prominent
+    notices stating that you modified the files.
+
+You may add your own intellectual property statement to your modifications of
+DBRX and, except as set forth in this Section, may provide additional or
+different terms and conditions for use, reproduction, or distribution of DBRX
+or DBRX Derivatives as a whole, provided your use, reproduction, modification,
+distribution, performance, and display of DBRX or DBRX Derivatives otherwise
+complies with the terms and conditions of this Agreement. Any additional or
+different terms and conditions you impose must not conflict with the terms of
+this Agreement and in the event of a conflict, the terms and conditions of this
+Agreement shall govern over any such additional or different terms and conditions.
+
+2.3 Use Restrictions
+
+You will not use DBRX or DBRX Derivatives or any Output to improve any other
+large language model (excluding DBRX or DBRX Derivatives).
+
+You will not use DBRX or DBRX Derivatives:
+
+	1. for any restricted use set forth in the Databricks Open Model Acceptable
+    Use Policy identified at
+    https://www.databricks.com/legal/acceptable-use-policy-open-model
+    ("Acceptable Use Policy"), which is hereby incorporated by reference into
+    this Agreement; or
+
+	2. in violation of applicable laws and regulations.
+
+To the maximum extent permitted by law, Databricks reserves the right to
+restrict (remotely or otherwise) usage of DBRX or DBRX Derivatives that
+Databricks reasonably believes are in violation of this Agreement.
+
+
+Section 3: Additional Commercial Terms
+
+If, on the DBRX version release date, the monthly active users of the products
+or services made available by or for Licensee, or Licensee’s affiliates, is
+greater than 700 million monthly active users in the preceding calendar month,
+you must request a license from Databricks, which we may grant to you in our
+sole discretion, and you are not authorized to exercise any of the rights under
+this Agreement unless or until Databricks otherwise expressly grants you such
+rights.
+
+If you receive DBRX or DBRX Derivatives from a direct or indirect licensee as
+part of an integrated end user product, then this section (Section 3) of the
+Agreement will not apply to you.
+
+
+Section 4: Additional Provisions
+
+4.1 Updates
+
+Databricks may update DBRX from time to time, and you must make reasonable
+efforts to use the latest version of DBRX.
+
+4.2 Intellectual Property
+
+a. No trademark licenses are granted under this Agreement, and in connection
+with DBRX or DBRX Derivatives, neither Databricks nor Licensee may use any name
+or mark owned by or associated with the other or any of its affiliates, except
+as required for reasonable and customary use in describing and redistributing
+DBRX or DBRX Derivatives.
+
+b. Subject to Databricks’ ownership of DBRX and DRBX Derivatives made by or for
+Databricks, with respect to any DBRX Derivatives that are made by you, as
+between you and Databricks, you are and will be the owner of such DBRX
+Derivatives.
+
+c. Databricks claims no ownership rights in Outputs. You are responsible for
+Outputs and their subsequent uses.
+
+d. If you institute litigation or other proceedings against Databricks or any
+entity (including a cross-claim or counterclaim in a lawsuit) alleging that
+DBRX or Outputs or results therefrom, or any portion of any of the foregoing,
+constitutes infringement of intellectual property or other rights owned or
+licensable by you, then any licenses granted to you under this Agreement shall
+terminate as of the date such litigation or claim is filed or instituted. You
+will indemnify and hold harmless Databricks from and against any claim by any
+third party arising out of or related to your use or distribution of DBRX or
+DBRX Derivatives.
+
+4.3 DISCLAIMER OF WARRANTY
+
+UNLESS REQUIRED BY APPLICABLE LAW, DBRX AND ANY OUTPUT AND RESULTS THEREFROM
+ARE PROVIDED ON AN “AS IS” BASIS, WITHOUT WARRANTIES OF ANY KIND, EITHER
+EXPRESS OR IMPLIED, INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES OF TITLE,
+NON-INFRINGEMENT, MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE. YOU
+ARE SOLELY RESPONSIBLE FOR DETERMINING THE APPROPRIATENESS OF USING OR
+REDISTRIBUTING DBRX OR DBRX DERIVATIVES AND ANY OUTPUT AND ASSUME ANY RISKS
+ASSOCIATED WITH YOUR USE OF DBRX OR DBRX DERIVATIVES AND ANY OUTPUT AND RESULTS.
+
+4.4 LIMITATION OF LIABILITY
+
+IN NO EVENT WILL DATABRICKS OR ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF
+LIABILITY, WHETHER IN CONTRACT, TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR
+OTHERWISE, ARISING OUT OF THIS AGREEMENT, FOR ANY LOST PROFITS OR ANY INDIRECT,
+SPECIAL, CONSEQUENTIAL, INCIDENTAL, EXEMPLARY OR PUNITIVE DAMAGES, EVEN IF
+DATABRICKS OR ITS AFFILIATES HAVE BEEN ADVISED OF THE POSSIBILITY OF ANY OF THE
+FOREGOING.
+
+4.5 Term and Termination
+
+The term of this Agreement will commence upon your acceptance of this Agreement
+or access to DBRX or DBRX Derivatives and will continue in full force and
+effect until terminated in accordance with the terms and conditions herein.
+Databricks may terminate this Agreement if you are in breach of any term or
+condition of this Agreement. Upon termination of this Agreement, you shall
+delete and cease use of DBRX or any DBRX Derivatives. Sections 1, 4.2(d), 4.3,
+4.4, and 4.6 shall survive the termination of this Agreement.
+
+4.6 Governing Law and Jurisdiction
+
+This Agreement will be governed and construed under the laws of the State of
+California without regard to choice of law principles, and the UN Convention
+on Contracts for the International Sale of Goods does not apply to this
+Agreement. The courts of California shall have exclusive jurisdiction of any
+dispute arising out of this Agreement.

NOTICE.txt

@@ -0,0 +1 @@
+DBRX is provided under and subject to the Databricks Open Model License, Copyright © Databricks, Inc. All rights reserved.

README.md

@@ -170,4 +170,4 @@ Full evaluation details can be found in our [technical blog post](https://www.da
 ## Acknowledgements
 The DBRX models were made possible thanks in large part to the open-source community, especially:
 * The [MegaBlocks](https://arxiv.org/abs/2211.15841) library, which established a foundation for our MoE implementation.
-* [PyTorch FSDP](https://arxiv.org/abs/2304.11277), which we built on for distributed training.
+* [PyTorch FSDP](https://arxiv.org/abs/2304.11277), which we built on for distributed training.

config.json

@@ -0,0 +1,38 @@
+{
+  "architectures": [
+    "DbrxForCausalLM"
+  ],
+  "attn_config": {
+    "clip_qkv": 8,
+    "kv_n_heads": 8,
+    "model_type": "",
+    "rope_theta": 500000
+  },
+  "auto_map": {
+    "AutoConfig": "configuration_dbrx.DbrxConfig",
+    "AutoModelForCausalLM": "modeling_dbrx.DbrxForCausalLM"
+  },
+  "d_model": 6144,
+  "emb_pdrop": 0.0,
+  "ffn_config": {
+    "ffn_hidden_size": 10752,
+    "model_type": "",
+    "moe_jitter_eps": 0,
+    "moe_loss_weight": 0.05,
+    "moe_num_experts": 16,
+    "moe_top_k": 4
+  },
+  "initializer_range": 0.02,
+  "max_seq_len": 32768,
+  "model_type": "dbrx",
+  "n_heads": 48,
+  "n_layers": 40,
+  "output_router_logits": false,
+  "resid_pdrop": 0.0,
+  "router_aux_loss_coef": 0.05,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.38.2",
+  "use_cache": true,
+  "vocab_size": 100352
+}

configuration_dbrx.py

@@ -0,0 +1,264 @@
+"""Dbrx configuration."""
+from typing import Any, Optional
+
+from transformers.configuration_utils import PretrainedConfig
+from transformers.utils import logging
+
+logger = logging.get_logger(__name__)
+
+DBRX_PRETRAINED_CONFIG_ARCHIVE_MAP = {}
+
+
+class DbrxAttentionConfig(PretrainedConfig):
+    """Configuration class for Dbrx Attention.
+
+    [`DbrxAttention`] class. It is used to instantiate attention layers
+    according to the specified arguments, defining the layers architecture.
+
+    Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
+    documentation from [`PretrainedConfig`] for more information.
+
+    Args:
+        attn_pdrop (`float`, *optional*, defaults to 0.0):
+            The dropout probability for the attention layers.
+        clip_qkv (`float`, *optional*, defualts to None):
+            If not `None`, clip the queries, keys, and values in the attention layer to this value.
+        kv_n_heads (Optional[int]): For grouped_query_attention only, allow user to specify number of kv heads.
+        rope_theta (float): The base frequency for rope.
+    """
+
+    def __init__(
+        self,
+        attn_pdrop: float = 0,
+        clip_qkv: Optional[float] = None,
+        kv_n_heads: int = 1,
+        rope_theta: float = 10000.0,
+        **kwargs: Any,
+    ):
+        super().__init__(**kwargs)
+        self.attn_pdrop = attn_pdrop
+        self.clip_qkv = clip_qkv
+        self.kv_n_heads = kv_n_heads
+        self.rope_theta = rope_theta
+
+        for k in ['model_type']:
+            if k in kwargs:
+                kwargs.pop(k)
+        if len(kwargs) != 0:
+            raise ValueError(f'Found unknown {kwargs=}')
+
+    @classmethod
+    def from_pretrained(cls, pretrained_model_name_or_path: str,
+                        **kwargs: Any) -> 'PretrainedConfig':
+        cls._set_token_in_kwargs(kwargs)
+
+        config_dict, kwargs = cls.get_config_dict(pretrained_model_name_or_path,
+                                                  **kwargs)
+
+        if config_dict.get('model_type') == 'dbrx':
+            config_dict = config_dict['attn_config']
+
+        if 'model_type' in config_dict and hasattr(
+                cls,
+                'model_type') and config_dict['model_type'] != cls.model_type:
+            logger.warning(
+                f"You are using a model of type {config_dict['model_type']} to instantiate a model of type "
+                +
+                f'{cls.model_type}. This is not supported for all configurations of models and can yield errors.'
+            )
+
+        return cls.from_dict(config_dict, **kwargs)
+
+
+class DbrxFFNConfig(PretrainedConfig):
+    """Configuration class for Dbrx FFN.
+
+    [`DbrxFFN`] class. It is used to instantiate feedforward layers according to
+    the specified arguments, defining the layers architecture.
+
+    Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
+    documentation from [`PretrainedConfig`] for more information.
+
+    Args:
+        ffn_act_fn (dict, optional): A dict specifying activation function for the FFN.
+            The dict should have a key 'name' with the value being the name of
+            the activation function along with any additional keyword arguments.
+        ffn_hidden_size (int, optional): The hidden size of the feedforward network.
+        moe_num_experts (int, optional): The number of experts in the mixture of experts layer.
+        moe_top_k (int, optional): The number of experts to use in the mixture of experts layer.
+        moe_jitter_eps (float, optional): The jitter epsilon for the mixture of experts layer.
+        moe_loss_weight (float, optional): The loss weight for the mixture of experts layer.
+        moe_normalize_expert_weights (float, optional): The normalization factor for the expert weights.
+        uniform_expert_assignment (bool, optional): Whether to use uniform expert assignment.
+            This should only be used for benchmarking purposes.
+    """
+
+    def __init__(
+        self,
+        ffn_act_fn: Optional[dict] = None,
+        ffn_hidden_size: int = 3584,
+        moe_num_experts: int = 4,
+        moe_top_k: int = 1,
+        moe_jitter_eps: Optional[float] = None,
+        moe_loss_weight: float = 0.01,
+        moe_normalize_expert_weights: Optional[float] = 1,
+        uniform_expert_assignment: bool = False,
+        **kwargs: Any,
+    ):
+        super().__init__()
+        if ffn_act_fn is None:
+            ffn_act_fn = {'name': 'silu'}
+        self.ffn_act_fn = ffn_act_fn
+        self.ffn_hidden_size = ffn_hidden_size
+        self.moe_num_experts = moe_num_experts
+        self.moe_top_k = moe_top_k
+        self.moe_jitter_eps = moe_jitter_eps
+        self.moe_loss_weight = moe_loss_weight
+        self.moe_normalize_expert_weights = moe_normalize_expert_weights
+        self.uniform_expert_assignment = uniform_expert_assignment
+
+        for k in ['model_type']:
+            if k in kwargs:
+                kwargs.pop(k)
+        if len(kwargs) != 0:
+            raise ValueError(f'Found unknown {kwargs=}')
+
+    @classmethod
+    def from_pretrained(cls, pretrained_model_name_or_path: str,
+                        **kwargs: Any) -> 'PretrainedConfig':
+        cls._set_token_in_kwargs(kwargs)
+
+        config_dict, kwargs = cls.get_config_dict(pretrained_model_name_or_path,
+                                                  **kwargs)
+
+        if config_dict.get('model_type') == 'dbrx':
+            config_dict = config_dict['ffn_config']
+
+        if 'model_type' in config_dict and hasattr(
+                cls,
+                'model_type') and config_dict['model_type'] != cls.model_type:
+            logger.warning(
+                f"You are using a model of type {config_dict['model_type']} to instantiate a model of type "
+                +
+                f'{cls.model_type}. This is not supported for all configurations of models and can yield errors.'
+            )
+
+        return cls.from_dict(config_dict, **kwargs)
+
+
+class DbrxConfig(PretrainedConfig):
+    """Configuration class for Dbrx.
+
+    [`DbrxModel`]. It is used to instantiate a Dbrx 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:
+        d_model (`int`, *optional*, defaults to 6144):
+            Dimensionality of the embeddings and hidden states.
+        n_heads (`int`, *optional*, defaults to 48):
+            Number of attention heads for each attention layer in the Transformer encoder.
+        n_layers (`int`, *optional*, defaults to 40):
+            Number of hidden layers in the Transformer encoder.
+        max_seq_len (`int`, *optional*, defaults to 32768):
+            The maximum sequence length of the model.
+        vocab_size (`int`, *optional*, defaults to 100352):
+            Vocabulary size of the Dbrx model. Defines the maximum number of different tokens that can be represented by
+            the `inputs_ids` passed when calling [`DbrxModel`].
+        resid_pdrop (`float`, *optional*, defaults to 0.0):
+            The dropout probability applied to the attention output before combining with residual.
+        emb_pdrop (`float`, *optional*, defaults to 0.0):
+            The dropout probability for the embedding layer.
+        attn_config (`dict`, *optional*):
+            A dictionary used to configure the model's attention module.
+        ffn_config (`dict`, *optional*):
+            A dictionary used to configure the model's FFN module.
+        use_cache (`bool`, *optional*, defaults to `False`):
+            Whether or not the model should return the last key/values attentions (not used by all models).
+        initializer_range (`float`, *optional*, defaults to 0.02):
+            The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
+        output_router_logits (`bool`, *optional*, defaults to `False`):
+            Whether or not the router logits should be returned by the model. Enabling this will also
+            allow the model to output the auxiliary loss. See [here]() for more details
+        router_aux_loss_coef (`float`, *optional*, defaults to 0.001):
+            The aux loss factor for the total loss.
+
+
+    Example:
+    ```python
+    >>> from transformers import DbrxConfig, DbrxModel
+
+    >>> # Initializing a Dbrx configuration
+    >>> configuration = DbrxConfig()
+
+    >>> # Initializing a model (with random weights) from the configuration
+    >>> model = DbrxModel(configuration)
+
+    >>> # Accessing the model configuration
+    >>> configuration = model.config
+    ```
+    """
+
+    model_type = 'dbrx'
+    attribute_map = {
+        'num_attention_heads': 'n_heads',
+        'hidden_size': 'd_model',
+        'num_hidden_layers': 'n_layers',
+        'max_position_embeddings': 'max_seq_len'
+    }
+
+    def __init__(
+        self,
+        d_model: int = 2048,
+        n_heads: int = 16,
+        n_layers: int = 24,
+        max_seq_len: int = 2048,
+        vocab_size: int = 32000,
+        resid_pdrop: float = 0.0,
+        emb_pdrop: float = 0.0,
+        attn_config: Optional[DbrxAttentionConfig] = None,
+        ffn_config: Optional[DbrxFFNConfig] = None,
+        use_cache: bool = True,
+        initializer_range: float = 0.02,
+        output_router_logits: bool = False,
+        router_aux_loss_coef: float = 0.05,
+        **kwargs: Any,
+    ):
+        if attn_config is None:
+            self.attn_config = DbrxAttentionConfig()
+        elif isinstance(attn_config, dict):
+            self.attn_config = DbrxAttentionConfig(**attn_config)
+        else:
+            self.attn_config = attn_config
+
+        if ffn_config is None:
+            self.ffn_config = DbrxFFNConfig()
+        elif isinstance(ffn_config, dict):
+            self.ffn_config = DbrxFFNConfig(**ffn_config)
+        else:
+            self.ffn_config = ffn_config
+
+        self.d_model = d_model
+        self.n_heads = n_heads
+        self.n_layers = n_layers
+        self.max_seq_len = max_seq_len
+        self.vocab_size = vocab_size
+        self.resid_pdrop = resid_pdrop
+        self.emb_pdrop = emb_pdrop
+        self.use_cache = use_cache
+        self.initializer_range = initializer_range
+        self.output_router_logits = output_router_logits
+        self.router_aux_loss_coef = router_aux_loss_coef
+
+        tie_word_embeddings = kwargs.pop('tie_word_embeddings', False)
+        if tie_word_embeddings:
+            raise ValueError(
+                'tie_word_embeddings is not supported for Dbrx models.')
+
+        super().__init__(
+            tie_word_embeddings=tie_word_embeddings,
+            **kwargs,
+        )

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "eos_token_id": [
+    100257,
+    100279
+  ],
+  "transformers_version": "4.38.2"
+}

huggingface-metadata.txt

@@ -0,0 +1,65 @@
+url: https://huggingface.co/databricks/dbrx-instruct
+branch: main
+download date: 2024-03-29 03:50:30
+sha256sum:
+    3cfdb9ef2003544c6d3f8c6244883e76ca151bc60b13ac6f67693bd8baf864da model-00001-of-00061.safetensors
+    23b1468ea4f961710bc3241b52dbebf981aa8e1273a8e4b985915cf49dfa04af model-00002-of-00061.safetensors
+    eaf9bdd6896edda1c662ac7530a4053220d4a49da0c0361e90d8b7855141f251 model-00003-of-00061.safetensors
+    be29f3fa53a5cf878bd77a56440fa2537a0f00cccb8651ad5741ed654689e460 model-00004-of-00061.safetensors
+    0e6b9356183c8f24780675e281cb8ce0d1abac44008a79ed626abe72077a4e9d model-00005-of-00061.safetensors
+    8d06f6f69cc365df30371efea4514bca2bfc8a25ff31064d21e90995733f956b model-00006-of-00061.safetensors
+    9961227308e4e7212cab4eef4031e060512d55370aee3b911d80098f61cb096d model-00007-of-00061.safetensors
+    33941bb4a441d44870fed325e16ebfd88b31320e542e9e776d497c9d2d7f169e model-00008-of-00061.safetensors
+    47f5395b27077df7f4bcc94ec9dbf870e8fd0bdef35764e10e43017dcc13424f model-00009-of-00061.safetensors
+    5572004a402e03eb7b68630970417ffb1d8558984b448c24521bf36eaf1b9715 model-00010-of-00061.safetensors
+    8a2405a3e78cb765efbffc5f502c5db84921733ba5ab6a15a6b8810fe69e8031 model-00011-of-00061.safetensors
+    d1e0086fafd04d58ea6a61b7e7660f6bbe54a0380a6fa1f39464ac8be440e7d8 model-00012-of-00061.safetensors
+    a8f77cffc1ba5af4b6ed8a05a38bf1aa18ebbc3ed06861eb75925a84dba3672f model-00013-of-00061.safetensors
+    107ce690fec4aa202cb07507af6e8f3971c974dd31f697c6c5dc39afcc899b67 model-00014-of-00061.safetensors
+    a7d1cb9080dbf19ec925aff6beba736866ae505e334d5e852183468dc57188d0 model-00015-of-00061.safetensors
+    c160424dedae5f805f10b2981e9e2bf261d4aed49c0d0d85cfb803ef445559f4 model-00016-of-00061.safetensors
+    e498a7c62d501f649ca2dfa0f409f6fe188a359c31d91f2d209b23effe15b22f model-00017-of-00061.safetensors
+    24f9e0a148c17ae3fef677ae94a8290a562bd6a31a805e76e23f91c2dbbd9f18 model-00018-of-00061.safetensors
+    73b3af8d33ad09039d052d000d122fc904c5542a247e2e6d05bb6aae6f5bb916 model-00019-of-00061.safetensors
+    fe93ce5f12f216d9d9ca2b252eeabcfc47fb6d3785eb3b1ecf9a6c5c384ae3a5 model-00020-of-00061.safetensors
+    af7b81ca660ca1afde8b1a0f697724a788e7566214e7178492d0839e441819a4 model-00021-of-00061.safetensors
+    599a1d7323777aafe5edbaf22b8a56b8c84068f75ec20d382fc40e5c405bce38 model-00022-of-00061.safetensors
+    9223edff1a6c3a73c6dacab2b104d2bfa280be2a5f8a3965fa24bf586fb683ad model-00023-of-00061.safetensors
+    02350eeaa1d595bf65fc5c16c9ee3241f195fa0118d9dc9f983374b145bf35ea model-00024-of-00061.safetensors
+    a5779cb1a15c4d3e2d0302c3481f5e3d2cf74e4434e44824464c282ec724eee6 model-00025-of-00061.safetensors
+    65ce12b50281d2449f5eb5e43b7bef56e9ebd137b675f9649d31c0bffdd07ceb model-00026-of-00061.safetensors
+    1db31da422deb6f7098c79dd18a3fab823fe8d6ae95dfcd751e7bc7fa1650def model-00027-of-00061.safetensors
+    312da4cc278ab598b38ca994f70d453fc086fc560de6da851b55d602ef368ecc model-00028-of-00061.safetensors
+    d28d9280c500a9cbe5ce59df1043cf8bc07b531c0ddb8cc70365786b1a36900c model-00029-of-00061.safetensors
+    573a4ef61f3d9f1974f05612cc0299475c41f6a8d4e1ae530a0f21e8e6b04725 model-00030-of-00061.safetensors
+    d2bb381b92c8bdb37a780fc4369904406fc8fdabda0007325a0debf4ba103a26 model-00031-of-00061.safetensors
+    17a60f2ae29a04acead99434eedc40413954982cac787ca485378390c537ccb2 model-00032-of-00061.safetensors
+    d410b47d48eb572478b80a6ea1766da7ef7b5fdbb8e9e4e611208b2677cb81bd model-00033-of-00061.safetensors
+    8e5e894489b1da3cf744345022a9fd6d3fcf14f66a205b9931146769892999e7 model-00034-of-00061.safetensors
+    35b4937e5f449256f2e8277461af26d956c762a98f252f04445ca1852da30b7e model-00035-of-00061.safetensors
+    bc2d28e62edf58cf121924c4a57c172021a9dbe972d75cfdeb54180a1f21957b model-00036-of-00061.safetensors
+    3813a7e00dd6ed9129158314a92ac7229cea41f3562c186a6daee461f6bbbaa6 model-00037-of-00061.safetensors
+    b9f4014248e2087083843eaff448d0232230dbd8b5fa33cc54d7ebf5003c26b3 model-00038-of-00061.safetensors
+    1d6b612cb8b81dc0714c0f7db73e0e9b4e14eb463e7069b16f5387bd2673890a model-00039-of-00061.safetensors
+    8dde9e2e2bc8a1138d3801929b1fab01d301bf6e16c54be0094a9e1f407243ea model-00040-of-00061.safetensors
+    9730e3d757fd41b8cad918c66f041011a96e67c5e82d6e313d8b57cccb44bec0 model-00041-of-00061.safetensors
+    128e0433397f8e992cd174ea9b2931af49e25feeb78aef9c6cd5335da6e86e82 model-00042-of-00061.safetensors
+    e982d566cf1d966052f6365b655d26b38a34bfb3d0bdd75bbcc9d794fc485c32 model-00043-of-00061.safetensors
+    713866fbc89733b067d799c4368e2495d4316193e91ad2586440b9d97e549952 model-00044-of-00061.safetensors
+    8f8796101e5df9c327e6bcc376ffaba33191270a966be67cfa9d75ef1dbac695 model-00045-of-00061.safetensors
+    d793734c75efe71ffa500c3048fd8c6a21eed8c8b692371be76d068fb8c044e3 model-00046-of-00061.safetensors
+    53871e712da21c4ae6862e8fc546367a60572f9b336049b1f3b7cf0506437fbb model-00047-of-00061.safetensors
+    bcd0c10ef6ef58fbe5d59c81c0950022ce64b12c7534d162c5299a76776d5bc0 model-00048-of-00061.safetensors
+    b2fcb794b7df43e7cfede55e5722d0f53ab709751cb7efbde77b14522d094011 model-00049-of-00061.safetensors
+    48fd71f1e1b8ed9fd4ca47a621c9924d6485340d4e39749ed965f1f6ef045170 model-00050-of-00061.safetensors
+    c4e5c439153215ccddf1d0d00cb05ccf6557cbddf9a2c963c47b9556958ce506 model-00051-of-00061.safetensors
+    06b911989ad3040713c576ad78ddda8b34fa7509440aec61cace1a57263890c0 model-00052-of-00061.safetensors
+    709079f70f812d17a2fdf8e639fd99f4c0d572cf23f1a5e3e323cc00b50db6a2 model-00053-of-00061.safetensors
+    8bf788ff04aa4e73eec8abac378ebb4c765df0c6dc85e24522d24c0cca4aa344 model-00054-of-00061.safetensors
+    5163f3f77874a4ea7a8e76f74da330b0a87fd19c6ed9ef42d36a0b1269ca92de model-00055-of-00061.safetensors
+    6c880fae2c3d3a98b1b1bfea849512df7be84004f3569adec642c350e3c814bc model-00056-of-00061.safetensors
+    c0d24334da4eaea54d3094a171b698e796a4102f954a1c9e988808b9a3afc905 model-00057-of-00061.safetensors
+    70cab56497ef8b4bd74352678f4ac83ab5b5a0facf7aac394df2ae4669f5a57b model-00058-of-00061.safetensors
+    1ca70897eb949ac8871a9e0ac83d597c694d3f51c6e48a021231d3b749c5b667 model-00059-of-00061.safetensors
+    492fe0baed3f76704206d454994c377e8355ca1bec43ef4cd4968b5df8fb669e model-00060-of-00061.safetensors
+    00af0b1e9823022479242479f6f84ae3dfc543628acfe4e0e83e0b2034e4b220 model-00061-of-00061.safetensors

model-00001-of-00061.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c51a84ddbe9c6db4a3933f79dab41d5d296faea64e611f06987d3edf9a188de1
+size 3523439352

model-00002-of-00061.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bdd74964838d9c5ab140d3f00a31fc12081cff8ac3310aa66f6f1f75fddc443
+size 4404245144

model-00003-of-00061.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e72c1494f4bfa8409e1d0a74fb11b6d63107eabef89309392370ce7900929eb
+size 4227862560

model-00004-of-00061.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43bdcc149fc83b65e164e6fbeb02735309750ef043fc0fb7bc0de7f33ce05ac8
+size 4404245144

model-00005-of-00061.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c6d8e3d56f731ba3a05858b4d614e2fc4a51703100915280bf89c25a5d24b81
+size 4404245144

model-00006-of-00061.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c1b51cc32f2c535f528d69c43ddc4d48855ec3a8847b9e584e28c68f9efc786
+size 4227862560

model-00007-of-00061.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca4ad42049f29c5cfb3f375f0246562cf8d2e1606e851d438fea210c579a41d8
+size 4404245144

model-00008-of-00061.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d4ba5cef0b5a8d1b73756f1656f5247dc63c23161e5f6dca08479ccc10492f5
+size 4404245144

model-00009-of-00061.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7335c39b0e58a2e9e9a88e648effc97bdab49f5be42c7914bde7f039b6924f47
+size 4227862560

model-00010-of-00061.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:849318fb372f0aad14be50f74ecccf059e4236703f453c3380f72ad47680549f
+size 4404245144

model-00011-of-00061.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09193bc2a79bcf6017e1afce25dd3ece2f16509940ce50922cb1d1e54c7224b7
+size 4404245144

model-00012-of-00061.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f50c19c0c494a5bfa78403e4faa431a579f9d9ef353e88c3f8bac123e10e5b2
+size 4227862560

model-00013-of-00061.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8a958d323eedc75858514d4bf1e03b4f1be3dde553d40704f8a8b5e0d509a4c
+size 4404245144

model-00014-of-00061.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5ff6b686e2d67764473c62b3212530e2d5276716446da843e77ffa8092f5ada
+size 4404245144

model-00015-of-00061.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a659155cfb439471ef08e8aceb5dd9010ec1efb8f39e19342e81a9e40a8c9a7
+size 4227862560

model-00016-of-00061.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b630f37522a73766346162b70512a5d21db1ed331eae0a3c3c42cf5bb57dfcca
+size 4404245168

model-00017-of-00061.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8738f9ab6bcc6ff4dce364b48bd6e42d2fb8368b7c479cdc0477a8c892769f9d
+size 4404245184

model-00018-of-00061.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78dd6843d4539850acc3e2548bbe52726a50b09d05cc58984a0c11b78af6ed42
+size 4227862592

model-00019-of-00061.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74fcf7768f057fde24b7b2b992f709a771c7c1b283deda188af8a45a7171cf6f
+size 4404245184

model-00020-of-00061.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d4bc51b7850ba7cb99379d71b894a325785ef5d538d09a7c8780f4c4d5be50f
+size 4404245184

model-00021-of-00061.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4691ae48cb49b454351a8a4fed3ca0d0f1fef3a044d9ceb3ae538632ee22e0fb
+size 4227862592

model-00022-of-00061.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1ede5d2312fa979f629ecd9fe2ff0bfa4620d339afd07d350d773b93c2ee574
+size 4404245184

model-00023-of-00061.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a208b0c2743d0849cb0e8aed71e209a5e7972b63dff4615b0678ef40d77bd992
+size 4404245184

model-00024-of-00061.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f48f04d4622d45afb74f97837453d8f1eee3d897d83d7f936b2a0ea78acb8bbf
+size 4227862592

model-00025-of-00061.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:056e53c0e8f98ed7675a74f37766c60e7402f01d4ec3c89691cef5b345613d74
+size 4404245184

model-00026-of-00061.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd62fc675e8a92415ed0e60f8e9a25a065679f33b944b3bc8b529c9c4d2b2ea8
+size 4404245184

model-00027-of-00061.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3dfa7c1a7243967bdeed47b58e0a6798bfb6fc6debdce2eed1fe7b6a243d41b0
+size 4227862592

model-00028-of-00061.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d70c1f5c43efc4c9f4041ab48d2390dd275532376eaa5b33774956d08a363ad2
+size 4404245184

model-00029-of-00061.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:778c60430626f6b96e0dacec38b193d49afd4f74e6b38e2a70292d45ec3c7ef0
+size 4404245184

model-00030-of-00061.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34d8d6d24a74ebcd861bed5709bcb8ade5595734bb8f79d1e72e725bdebbc83a
+size 4227862592

model-00031-of-00061.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe8d09e32d3b5fd39e1f20c0e3c2aad1a5124331a160f75c9be018a3b03817b5
+size 4404245184

model-00032-of-00061.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ff026c683b608f73289ca170232eed5b66c04fc2e11c15878e6514a828d2d34
+size 4404245184

model-00033-of-00061.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e52a05f9a898caf58749aa641205ce316eefe3d8654c46b2c06271e27093b51
+size 4227862592

model-00034-of-00061.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2db17c4882119b0c3f28d4f2c5bd7fddee43b74d73928efcfca0bb7ede81a314
+size 4404245184

model-00035-of-00061.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0761a842b153ad1e6e78883cc2fc5a3e24dea543ddfa2c9fc03713d7c68f2e32
+size 4404245184

model-00036-of-00061.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79a15bc8adf90a283a34904d44df5c8631876651e3cc0323db3dafaef65ac6fd
+size 4227862592

model-00037-of-00061.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:002005c0596b8d0476fa6ab158ff0c9c22b33b76584d1f1857dff21e2bd9f737
+size 4404245184

model-00038-of-00061.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4971108c48eca76aa1020aa225c215026605d7967871b52d28803d8dc435a482
+size 4404245184

model-00039-of-00061.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bf53ce714b30cf246e5fbfee7c29a8e4a83539439d900984d03254321b9290a
+size 4227862592

model-00040-of-00061.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ea6e5518b2e08f81cbd52d8b0b4da7f77bba02dca96138bf5cb2d2f5bc4db84
+size 4404245184

model-00041-of-00061.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:249d9c556f32ff02ed6cfc7b96c62c0d86ad0cb1b99be9785840b40e9a5c7022
+size 4404245184

model-00042-of-00061.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d244c2975aa94e2827d6bb04854943b27c3c70e115fe8c743a840632c323b0d
+size 4227862592