New weights for the model

README.md

@@ -1,132 +0,0 @@
----
-license: apache-2.0
-language:
-- en
-library_name: transformers
-pipeline_tag: text2text-generation
-tags:
-- code
-- sql
-- text-to-sql
----
-
-Introducing Hrida-T2SQL-3B-128k-V0.1, our latest small language model (SLM) tailored for data scientists and industry professionals. This advanced model marks a significant upgrade from our previous release, now equipped with an expanded 128k token context window for handling even the most intricate data queries with precision. Powered by the Phi 3 architecture, it effortlessly converts natural language queries into precise SQL commands, enhancing data analysis efficiency and decision-making capabilities. 
-
-For full details of this model please read our [blog post](https://www.hridaai.com/blog/t2sql).
-
-
-## Prompt Template
-
-```txt
-### Instruction: 
-Provide the system prompt.
-
-### Dialect:
-Specify the SQL dialect (e.g., MySQL, PostgreSQL, SQL Server, etc.).
-
-### Context: 
-Provide the database schema including table names, column names, and data types.
-
-### Input: 
-User's query.
-
-### Response:
-Expected SQL query output based on the input and context.
-
-```
-
-- **Instruction (System Prompt)**: This guides the model on processing input to generate the SQL query response effectively.
-- **Dialect (Optional)**: Specify the SQL variant the model should use to ensure the generated query conforms to the correct syntax.
-- **Context**: Provide the database schema to the model for generating accurate SQL queries.
-- **Input**: Provide the user query for the model to comprehend and transform into an SQL query.
-- **Response**: Expected output from the model.
-
-
-## Chat Prompt Template
-
-```txt
-<s>
-<|system|>
-{ Instruction / System Prompt }
-<|user|>
-{ Context / User Query } <|end|>
-<|assistant|>
-```
-
-## Run the Model
-
-### Using Transformers
-
-```python
-import torch
-from transformers import AutoModelForCausalLM, AutoTokenizer
-
-# Define the model and tokenizer
-model_id = "HridaAI/Hrida-T2SQL-3B-128k-V0.1"
-tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
-model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float16, trust_remote_code=True)
-
-# Define the context and prompt
-prompt = """
-Answer to the query will be in the form of an SQL query.
-### Context: CREATE TABLE Employees (
-    EmployeeID INT PRIMARY KEY,
-    FirstName VARCHAR(50),
-    LastName VARCHAR(50),
-    Age INT,
-    DepartmentID INT,
-    Salary DECIMAL(10, 2),
-    DateHired DATE,
-    Active BOOLEAN,
-    FOREIGN KEY (DepartmentID) REFERENCES Departments(DepartmentID)
-); 
-
-CREATE TABLE Departments (
-    DepartmentID INT PRIMARY KEY,
-    DepartmentName VARCHAR(100),
-    Location VARCHAR(100)
-); 
-### Input: Write a SQL query to select all the employees who are active.
-### Response:
-"""
-# Prepare the input
-messages = [{"role": "user", "content": prompt}]
-inputs = tokenizer.apply_chat_template(messages, return_tensors="pt", add_generation_prompt=True)
-
-# Generate the output
-outputs = model.generate(inputs, max_length=300)
-print(tokenizer.decode(outputs[0]))
-
-
-```
-
-### Using MLX
-
-```python
-from mlx_lm import generate, load
-
-model,tokenizer = load("HridaAI/Hrida-T2SQL-3B-128k-V0.1")
-
-prompt = """
-Answer to the quey will be in the form of SQL query.
-### Context: CREATE TABLE Employees (
-    EmployeeID INT PRIMARY KEY,
-    FirstName VARCHAR(50),
-    LastName VARCHAR(50),
-    Age INT,
-    DepartmentID INT,
-    Salary DECIMAL(10, 2),
-    DateHired DATE,
-    Active BOOLEAN,
-    FOREIGN KEY (DepartmentID) REFERENCES Departments(DepartmentID)
-); 
-
-CREATE TABLE Departments (
-    DepartmentID INT PRIMARY KEY,
-    DepartmentName VARCHAR(100),
-    Location VARCHAR(100)
-); ### Input: Write a SQL query to select all the employees who are active. ### Response:"""
-
-response = generate(model=model,tokenizer=tokenizer,prompt=prompt, verbose=True)
-
-```

config.json

@@ -6,9 +6,7 @@
     "attention_dropout": 0.0,
     "auto_map": {
         "AutoConfig": "configuration_phi3.Phi3Config",
-        "AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM",
-        "AutoModelForSequenceClassification": "modeling_phi3.Phi3ForSequenceClassification",
-        "AutoModelForTokenClassification": "modeling_phi3.Phi3ForTokenClassification"
+        "AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM"
     },
     "bos_token_id": 1,
     "embd_pdrop": 0.0,
@@ -28,71 +26,64 @@
     "rms_norm_eps": 1e-05,
     "rope_scaling": {
         "long_factor": [
-            1.0299999713897705,
-            1.0499999523162842,
-            1.0499999523162842,
-            1.0799999237060547,
-            1.2299998998641968,
-            1.2299998998641968,
-            1.2999999523162842,
-            1.4499999284744263,
-            1.5999999046325684,
-            1.6499998569488525,
-            1.8999998569488525,
-            2.859999895095825,
-            3.68999981880188,
-            5.419999599456787,
-            5.489999771118164,
-            5.489999771118164,
-            9.09000015258789,
-            11.579999923706055,
-            15.65999984741211,
-            15.769999504089355,
-            15.789999961853027,
-            18.360000610351562,
-            21.989999771118164,
-            23.079999923706055,
-            30.009998321533203,
-            32.35000228881836,
-            32.590003967285156,
-            35.56000518798828,
-            39.95000457763672,
-            53.840003967285156,
-            56.20000457763672,
-            57.95000457763672,
-            59.29000473022461,
-            59.77000427246094,
-            59.920005798339844,
-            61.190006256103516,
-            61.96000671386719,
-            62.50000762939453,
-            63.3700065612793,
-            63.48000717163086,
-            63.48000717163086,
-            63.66000747680664,
-            63.850006103515625,
-            64.08000946044922,
-            64.760009765625,
-            64.80001068115234,
-            64.81001281738281,
-            64.81001281738281
+            1.0700000524520874,
+            1.1200000047683716,
+            1.149999976158142,
+            1.4199999570846558,
+            1.5699999332427979,
+            1.7999999523162842,
+            2.129999876022339,
+            2.129999876022339,
+            3.009999990463257,
+            5.910000324249268,
+            6.950000286102295,
+            9.070000648498535,
+            9.930000305175781,
+            10.710000038146973,
+            11.130000114440918,
+            14.609999656677246,
+            15.409998893737793,
+            19.809999465942383,
+            37.279998779296875,
+            38.279998779296875,
+            38.599998474121094,
+            40.12000274658203,
+            46.20000457763672,
+            50.940006256103516,
+            53.66000747680664,
+            54.9373893737793,
+            56.89738845825195,
+            57.28738784790039,
+            59.98738479614258,
+            60.86738586425781,
+            60.887386322021484,
+            61.71739196777344,
+            62.91739273071289,
+            62.957393646240234,
+            63.41739273071289,
+            63.8173942565918,
+            63.83739471435547,
+            63.897396087646484,
+            63.93739700317383,
+            64.06739807128906,
+            64.11434936523438,
+            64.12435150146484,
+            64.15435028076172,
+            64.19435119628906,
+            64.24435424804688,
+            64.57435607910156,
+            64.69000244140625,
+            64.76000213623047
         ],
         "short_factor": [
-            1.05,
-            1.05,
-            1.05,
             1.1,
             1.1,
-            1.1500000000000001,
-            1.2000000000000002,
-            1.2500000000000002,
+            1.1,
             1.3000000000000003,
             1.3500000000000003,
-            1.5000000000000004,
-            2.000000000000001,
-            2.000000000000001,
-            2.000000000000001,
-            2.000000000000001,
+            1.3500000000000003,
+            1.4000000000000004,
+            1.5500000000000005,
             2.000000000000001,
             2.000000000000001,
             2.000000000000001,
@@ -113,27 +104,34 @@
             2.0500000000000007,
             2.0500000000000007,
             2.0500000000000007,
+            2.0500000000000007,
+            2.0500000000000007,
+            2.0500000000000007,
             2.1000000000000005,
             2.1000000000000005,
-            2.1000000000000005,
-            2.1500000000000004,
             2.1500000000000004,
-            2.3499999999999996,
-            2.549999999999999,
-            2.5999999999999988,
-            2.5999999999999988,
+            2.25,
+            2.25,
+            2.25,
+            2.25,
+            2.25,
+            2.3999999999999995,
+            2.4499999999999993,
+            2.499999999999999,
+            2.6999999999999984,
+            2.6999999999999984,
             2.7499999999999982,
-            2.849999999999998,
-            2.849999999999998,
-            2.9499999999999975
+            2.799999999999998,
+            2.8999999999999977,
+            3.049999999999997
         ],
-        "type": "su"
+        "type": "longrope"
     },
     "rope_theta": 10000.0,
     "sliding_window": 262144,
     "tie_word_embeddings": false,
     "torch_dtype": "bfloat16",
-    "transformers_version": "4.39.3",
+    "transformers_version": "4.40.2",
     "use_cache": true,
     "vocab_size": 32064
 }

configuration_phi3.py

@@ -1,213 +1,227 @@
-# coding=utf-8
-# Copyright 2024 Microsoft and the HuggingFace Inc. team. All rights reserved.
-#
-# 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.
-
-""" Phi-3 model configuration"""
-
-
-from transformers.configuration_utils import PretrainedConfig
-from transformers.utils import logging
-
-
-logger = logging.get_logger(__name__)
-
-PHI3_PRETRAINED_CONFIG_ARCHIVE_MAP = {
-    "microsoft/Phi-3-mini-4k-instruct": "https://huggingface.co/microsoft/Phi-3-mini-4k-instruct/resolve/main/config.json",
-    "microsoft/Phi-3-mini-128k-instruct": "https://huggingface.co/microsoft/Phi-3-mini-128k-instruct/resolve/main/config.json",
-}
-
-
-class Phi3Config(PretrainedConfig):
-    r"""
-    This is the configuration class to store the configuration of a [`Phi3Model`]. It is used to instantiate a Phi-3
-    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
-    [microsoft/Phi-3-mini-4k-instruct](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct).
-
-    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 32064):
-            Vocabulary size of the Phi-3 model. Defines the number of different tokens that can be represented by the
-            `inputs_ids` passed when calling [`Phi3Model`].
-        hidden_size (`int`, *optional*, defaults to 3072):
-            Dimension of the hidden representations.
-        intermediate_size (`int`, *optional*, defaults to 8192):
-            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`.
-        resid_pdrop (`float`, *optional*, defaults to 0.0):
-            Dropout probability for mlp outputs.
-        embd_pdrop (`int`, *optional*, defaults to 0.0):
-            The dropout ratio for the embeddings.
-        attention_dropout (`float`, *optional*, defaults to 0.0):
-            The dropout ratio after computing the attention scores.
-        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 4096):
-            The maximum sequence length that this model might ever be used with.
-        original_max_position_embeddings (`int`, *optional*, defaults to 4096):
-            The maximum sequence length that this model was trained with. This is used to determine the size of the
-            original RoPE embeddings when using long scaling.
-        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-05):
-            The epsilon value used for the RMSNorm.
-        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`. Whether to tie weight embeddings or not.
-        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*):
-            The scaling strategy for the RoPE embeddings. If `None`, no scaling is applied. If a dictionary, it must
-            contain the following keys: `type`, `short_factor` and `long_factor`. The `type` must be either `su` or `yarn` and
-            the `short_factor` and `long_factor` must be lists of numbers with the same length as the hidden size
-            divided by the number of attention heads divided by 2.
-        bos_token_id (`int`, *optional*, defaults to 1):
-            The id of the "beginning-of-sequence" token.
-        eos_token_id (`int`, *optional*, defaults to 32000):
-            The id of the "end-of-sequence" token.
-        pad_token_id (`int`, *optional*, defaults to 32000):
-            The id of the padding token.
-        sliding_window (`int`, *optional*):
-            Sliding window attention window size. If `None`, no sliding window is applied.
-
-    Example:
-
-    ```python
-    >>> from transformers import Phi3Model, Phi3Config
-
-    >>> # Initializing a Phi-3 style configuration
-    >>> configuration = Phi3Config.from_pretrained("microsoft/Phi-3-mini-4k-instruct")
-
-    >>> # Initializing a model from the configuration
-    >>> model = Phi3Model(configuration)
-
-    >>> # Accessing the model configuration
-    >>> configuration = model.config
-    ```"""
-
-    model_type = "phi3"
-    keys_to_ignore_at_inference = ["past_key_values"]
-
-    def __init__(
-        self,
-        vocab_size=32064,
-        hidden_size=3072,
-        intermediate_size=8192,
-        num_hidden_layers=32,
-        num_attention_heads=32,
-        num_key_value_heads=None,
-        resid_pdrop=0.0,
-        embd_pdrop=0.0,
-        attention_dropout=0.0,
-        hidden_act="silu",
-        max_position_embeddings=4096,
-        original_max_position_embeddings=4096,
-        initializer_range=0.02,
-        rms_norm_eps=1e-5,
-        use_cache=True,
-        tie_word_embeddings=False,
-        rope_theta=10000.0,
-        rope_scaling=None,
-        bos_token_id=1,
-        eos_token_id=32000,
-        pad_token_id=32000,
-        sliding_window=None,
-        **kwargs,
-    ):
-        self.vocab_size = vocab_size
-        self.hidden_size = hidden_size
-        self.intermediate_size = intermediate_size
-        self.num_hidden_layers = num_hidden_layers
-        self.num_attention_heads = num_attention_heads
-
-        if num_key_value_heads is None:
-            num_key_value_heads = num_attention_heads
-
-        self.num_key_value_heads = num_key_value_heads
-        self.resid_pdrop = resid_pdrop
-        self.embd_pdrop = embd_pdrop
-        self.attention_dropout = attention_dropout
-        self.hidden_act = hidden_act
-        self.max_position_embeddings = max_position_embeddings
-        self.original_max_position_embeddings = original_max_position_embeddings
-        self.initializer_range = initializer_range
-        self.rms_norm_eps = rms_norm_eps
-        self.use_cache = use_cache
-        self.rope_theta = rope_theta
-        self.rope_scaling = rope_scaling
-        self._rope_scaling_validation()
-        self.sliding_window = sliding_window
-
-        super().__init__(
-            bos_token_id=bos_token_id,
-            eos_token_id=eos_token_id,
-            pad_token_id=pad_token_id,
-            tie_word_embeddings=tie_word_embeddings,
-            **kwargs,
-        )
-
-    def _rope_scaling_validation(self):
-        """
-        Validate the `rope_scaling` configuration.
-        """
-        if self.rope_scaling is None:
-            return
-
-        if not isinstance(self.rope_scaling, dict) or len(self.rope_scaling) != 3:
-            raise ValueError(
-                "`rope_scaling` must be a dictionary with three fields, `type`, `short_factor` and `long_factor`, "
-                f"got {self.rope_scaling}"
-            )
-        rope_scaling_type = self.rope_scaling.get("type", None)
-        rope_scaling_short_factor = self.rope_scaling.get("short_factor", None)
-        rope_scaling_long_factor = self.rope_scaling.get("long_factor", None)
-        if rope_scaling_type is None or rope_scaling_type not in ["su", "yarn"]:
-            raise ValueError(f"`rope_scaling`'s type field must be one of ['su', 'yarn'], got {rope_scaling_type}")
-        if not (
-            isinstance(rope_scaling_short_factor, list)
-            and all(isinstance(x, (int, float)) for x in rope_scaling_short_factor)
-        ):
-            raise ValueError(
-                f"`rope_scaling`'s short_factor field must be a list of numbers, got {rope_scaling_short_factor}"
-            )
-        if not len(rope_scaling_short_factor) == self.hidden_size // self.num_attention_heads // 2:
-            raise ValueError(
-                f"`rope_scaling`'s short_factor field must have length {self.hidden_size // self.num_attention_heads // 2}, got {len(rope_scaling_short_factor)}"
-            )
-        if not (
-            isinstance(rope_scaling_long_factor, list)
-            and all(isinstance(x, (int, float)) for x in rope_scaling_long_factor)
-        ):
-            raise ValueError(
-                f"`rope_scaling`'s long_factor field must be a list of numbers, got {rope_scaling_long_factor}"
-            )
-        if not len(rope_scaling_long_factor) == self.hidden_size // self.num_attention_heads // 2:
-            raise ValueError(
-                f"`rope_scaling`'s long_factor field must have length {self.hidden_size // self.num_attention_heads // 2}, got {len(rope_scaling_long_factor)}"
-            )
+# coding=utf-8
+# Copyright 2024 Microsoft and the HuggingFace Inc. team. All rights reserved.
+#
+# 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.
+
+""" Phi-3 model configuration"""
+
+
+from transformers.configuration_utils import PretrainedConfig
+from transformers.utils import logging
+
+
+logger = logging.get_logger(__name__)
+
+PHI3_PRETRAINED_CONFIG_ARCHIVE_MAP = {
+    "microsoft/Phi-3-mini-4k-instruct": "https://huggingface.co/microsoft/Phi-3-mini-4k-instruct/resolve/main/config.json",
+    "microsoft/Phi-3-mini-128k-instruct": "https://huggingface.co/microsoft/Phi-3-mini-128k-instruct/resolve/main/config.json",
+}
+
+
+class Phi3Config(PretrainedConfig):
+    r"""
+    This is the configuration class to store the configuration of a [`Phi3Model`]. It is used to instantiate a Phi-3
+    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
+    [microsoft/Phi-3-mini-4k-instruct](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct).
+
+    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 32064):
+            Vocabulary size of the Phi-3 model. Defines the number of different tokens that can be represented by the
+            `inputs_ids` passed when calling [`Phi3Model`].
+        hidden_size (`int`, *optional*, defaults to 3072):
+            Dimension of the hidden representations.
+        intermediate_size (`int`, *optional*, defaults to 8192):
+            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`.
+        resid_pdrop (`float`, *optional*, defaults to 0.0):
+            Dropout probability for mlp outputs.
+        embd_pdrop (`int`, *optional*, defaults to 0.0):
+            The dropout ratio for the embeddings.
+        attention_dropout (`float`, *optional*, defaults to 0.0):
+            The dropout ratio after computing the attention scores.
+        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 4096):
+            The maximum sequence length that this model might ever be used with.
+        original_max_position_embeddings (`int`, *optional*, defaults to 4096):
+            The maximum sequence length that this model was trained with. This is used to determine the size of the
+            original RoPE embeddings when using long scaling.
+        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-05):
+            The epsilon value used for the RMSNorm.
+        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`. Whether to tie weight embeddings or not.
+        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*):
+            The scaling strategy for the RoPE embeddings. If `None`, no scaling is applied. If a dictionary, it must
+            contain the following keys: `type`, `short_factor` and `long_factor`. The `type` must be `longrope` and 
+            the `short_factor` and `long_factor` must be lists of numbers with the same length as the hidden size 
+            divided by the number of attention heads divided by 2.
+        bos_token_id (`int`, *optional*, defaults to 1):
+            The id of the "beginning-of-sequence" token.
+        eos_token_id (`int`, *optional*, defaults to 32000):
+            The id of the "end-of-sequence" token.
+        pad_token_id (`int`, *optional*, defaults to 32000):
+            The id of the padding token.
+        sliding_window (`int`, *optional*):
+            Sliding window attention window size. If `None`, no sliding window is applied.
+
+    Example:
+
+    ```python
+    >>> from transformers import Phi3Model, Phi3Config
+
+    >>> # Initializing a Phi-3 style configuration
+    >>> configuration = Phi3Config.from_pretrained("microsoft/Phi-3-mini-4k-instruct")
+
+    >>> # Initializing a model from the configuration
+    >>> model = Phi3Model(configuration)
+
+    >>> # Accessing the model configuration
+    >>> configuration = model.config
+    ```"""
+
+    model_type = "phi3"
+    keys_to_ignore_at_inference = ["past_key_values"]
+
+    def __init__(
+        self,
+        vocab_size=32064,
+        hidden_size=3072,
+        intermediate_size=8192,
+        num_hidden_layers=32,
+        num_attention_heads=32,
+        num_key_value_heads=None,
+        resid_pdrop=0.0,
+        embd_pdrop=0.0,
+        attention_dropout=0.0,
+        hidden_act="silu",
+        max_position_embeddings=4096,
+        original_max_position_embeddings=4096,
+        initializer_range=0.02,
+        rms_norm_eps=1e-5,
+        use_cache=True,
+        tie_word_embeddings=False,
+        rope_theta=10000.0,
+        rope_scaling=None,
+        bos_token_id=1,
+        eos_token_id=32000,
+        pad_token_id=32000,
+        sliding_window=None,
+        **kwargs,
+    ):
+        self.vocab_size = vocab_size
+        self.hidden_size = hidden_size
+        self.intermediate_size = intermediate_size
+        self.num_hidden_layers = num_hidden_layers
+        self.num_attention_heads = num_attention_heads
+
+        if num_key_value_heads is None:
+            num_key_value_heads = num_attention_heads
+
+        self.num_key_value_heads = num_key_value_heads
+        self.resid_pdrop = resid_pdrop
+        self.embd_pdrop = embd_pdrop
+        self.attention_dropout = attention_dropout
+        self.hidden_act = hidden_act
+        self.max_position_embeddings = max_position_embeddings
+        self.original_max_position_embeddings = original_max_position_embeddings
+        self.initializer_range = initializer_range
+        self.rms_norm_eps = rms_norm_eps
+        self.use_cache = use_cache
+        self.rope_theta = rope_theta
+        self.rope_scaling = rope_scaling
+        self._rope_scaling_adjustment()
+        self._rope_scaling_validation()
+        self.sliding_window = sliding_window
+
+        super().__init__(
+            bos_token_id=bos_token_id,
+            eos_token_id=eos_token_id,
+            pad_token_id=pad_token_id,
+            tie_word_embeddings=tie_word_embeddings,
+            **kwargs,
+        )
+
+    def _rope_scaling_adjustment(self):
+        """
+        Adjust the `type` of the `rope_scaling` configuration for backward compatibility.
+        """
+        if self.rope_scaling is None:
+            return
+
+        rope_scaling_type = self.rope_scaling.get("type", None)
+
+        # For backward compatibility if previous version used "su" or "yarn"
+        if rope_scaling_type is not None and rope_scaling_type in ["su", "yarn"]:
+            self.rope_scaling["type"] = "longrope"
+
+    def _rope_scaling_validation(self):
+        """
+        Validate the `rope_scaling` configuration.
+        """
+        if self.rope_scaling is None:
+            return
+
+        if not isinstance(self.rope_scaling, dict) or len(self.rope_scaling) != 3:
+            raise ValueError(
+                "`rope_scaling` must be a dictionary with three fields, `type`, `short_factor` and `long_factor`, "
+                f"got {self.rope_scaling}"
+            )
+        rope_scaling_type = self.rope_scaling.get("type", None)
+        rope_scaling_short_factor = self.rope_scaling.get("short_factor", None)
+        rope_scaling_long_factor = self.rope_scaling.get("long_factor", None)
+        if rope_scaling_type is None or rope_scaling_type not in ["longrope"]:
+            raise ValueError(f"`rope_scaling`'s type field must be one of ['longrope'], got {rope_scaling_type}")
+        if not (
+            isinstance(rope_scaling_short_factor, list)
+            and all(isinstance(x, (int, float)) for x in rope_scaling_short_factor)
+        ):
+            raise ValueError(
+                f"`rope_scaling`'s short_factor field must be a list of numbers, got {rope_scaling_short_factor}"
+            )
+        if not len(rope_scaling_short_factor) == self.hidden_size // self.num_attention_heads // 2:
+            raise ValueError(
+                f"`rope_scaling`'s short_factor field must have length {self.hidden_size // self.num_attention_heads // 2}, got {len(rope_scaling_short_factor)}"
+            )
+        if not (
+            isinstance(rope_scaling_long_factor, list)
+            and all(isinstance(x, (int, float)) for x in rope_scaling_long_factor)
+        ):
+            raise ValueError(
+                f"`rope_scaling`'s long_factor field must be a list of numbers, got {rope_scaling_long_factor}"
+            )
+        if not len(rope_scaling_long_factor) == self.hidden_size // self.num_attention_heads // 2:
+            raise ValueError(
+                f"`rope_scaling`'s long_factor field must have length {self.hidden_size // self.num_attention_heads // 2}, got {len(rope_scaling_long_factor)}"
+            )

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0f504204ef88a41c3a36c3e7ad8f7292a524642aec9b4fcf3d8650c8252ef0d
+oid sha256:116ff9bda1d393660238f360909bf52758633a0096f26310ef0f522cc41d4c68
 size 5356281360

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ddc323b2152c4160cac4e2c6794aa15b725d07ce4f3c735d52e50493d5282e9f
+oid sha256:b18d25709caa69a4028471c23f922cbce133096419a345371ecfae4289d6eb8f
 size 2285900500

tokenizer.json

@@ -150,12 +150,6 @@
   "post_processor": {
     "type": "TemplateProcessing",
     "single": [
-      {
-        "SpecialToken": {
-          "id": "<s>",
-          "type_id": 0
-        }
-      },
       {
         "Sequence": {
           "id": "A",
@@ -164,24 +158,12 @@
       }
     ],
     "pair": [
-      {
-        "SpecialToken": {
-          "id": "<s>",
-          "type_id": 0
-        }
-      },
       {
         "Sequence": {
           "id": "A",
           "type_id": 0
         }
       },
-      {
-        "SpecialToken": {
-          "id": "<s>",
-          "type_id": 1
-        }
-      },
       {
         "Sequence": {
           "id": "B",
@@ -189,17 +171,7 @@
         }
       }
     ],
-    "special_tokens": {
-      "<s>": {
-        "id": "<s>",
-        "ids": [
-          1
-        ],
-        "tokens": [
-          "<s>"
-        ]
-      }
-    }
+    "special_tokens": {}
   },
   "decoder": {
     "type": "Sequence",

tokenizer_config.json

@@ -1,6 +1,7 @@
 {
-  "add_bos_token": true,
+  "add_bos_token": false,
   "add_eos_token": false,
+  "add_prefix_space": null,
   "added_tokens_decoder": {
     "0": {
       "content": "<unk>",
@@ -116,9 +117,10 @@
     }
   },
   "bos_token": "<s>",
-  "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') %}{{'<|user|>' + '\n' + message['content'] + '<|end|>' + '\n' + '<|assistant|>' + '\n'}}{% elif (message['role'] == 'assistant') %}{{message['content'] + '<|end|>' + '\n'}}{% endif %}{% endfor %}",
+  "chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}{{'<|system|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'user' %}{{'<|user|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>\n' + message['content'] + '<|end|>\n'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|endoftext|>",
+  "legacy": false,
   "model_max_length": 131072,
   "pad_token": "<|endoftext|>",
   "padding_side": "left",