Upload Phi-3.5-mini-instruct ONNX models for GPUs

README.md

@@ -7,6 +7,7 @@ inference: false
 
 # Phi-3.5-Mini-Instruct ONNX models
 This repository hosts the optimized versions of [Phi-3.5-mini-instruct](https://huggingface.co/microsoft/Phi-3.5-mini-instruct) to accelerate inference with ONNX Runtime.
+
 Optimized Phi-3.5 Mini models are published here in [ONNX](https://onnx.ai) format to run with [ONNX Runtime](https://onnxruntime.ai/) on CPU and GPU across devices, including server platforms, Windows, Linux and Mac desktops, and mobile CPUs, with the precision best suited to each of these targets.
 
 To easily get started with Phi-3.5, you can use our newly introduced ONNX Runtime Generate() API. See [here](https://aka.ms/generate-tutorial) for instructions on how to run it.
@@ -14,15 +15,14 @@ To easily get started with Phi-3.5, you can use our newly introduced ONNX Runtim
 ## ONNX Models 
 Here are some of the optimized configurations we have added:
 
-1.	ONNX model for fp16 CUDA: ONNX model you can use to run for your NVIDIA GPUs.
-2.	ONNX model for int4 CUDA: ONNX model for NVIDIA GPUs using int4 quantization via AWQ.
-3.	ONNX model for int4 CPU and Mobile: ONNX model for CPU and mobile using int4 quantization via AWQ.
+1. ONNX model for INT4 CPU: ONNX model for CPUs using int4 quantization via AWQ.
+2. ONNX model for INT4 GPU: ONNX model for GPUs using int4 quantization via AWQ.
 
 ## Model Summary
-Phi-3.5-mini is a lightweight, state-of-the-art open model built upon datasets used for Phi-3 - synthetic data and filtered publicly available websites - with a focus on very high-quality, reasoning dense data. The model belongs to the Phi-3 model family and supports 128K token context length. The model underwent a rigorous enhancement process, incorporating both supervised fine-tuning, proximal policy optimization, and direct preference optimization to ensure precise instruction adherence and robust safety measures.
+Phi-3.5 mini is a lightweight, state-of-the-art open model built upon datasets used for Phi-3 - synthetic data and filtered publicly available websites - with a focus on very high-quality, reasoning dense data. The model belongs to the Phi-3 model family and supports 128K token context length. The model underwent a rigorous enhancement process, incorporating both supervised fine-tuning, proximal policy optimization, and direct preference optimization to ensure precise instruction adherence and robust safety measures.
 
 ## Intended Uses
-The Phi 3.5 model is intended for commercial and research use in multiple languages. The model provides uses for general purpose AI systems and applications which require:
+The Phi 3.5 mini model is intended for commercial and research use in multiple languages. The model provides uses for general purpose AI systems and applications which require:
 
 1.	Memory/compute constrained environments
 2.	Latency bound scenarios
@@ -30,6 +30,7 @@ The Phi 3.5 model is intended for commercial and research use in multiple langua
 
 ## Use Case Considerations
 Phi 3.5 models are not specifically designed or evaluated for all downstream purposes. Developers should consider common limitations of language models as they select use cases, and evaluate and mitigate for accuracy, safety, and fariness before using within a specific downstream use case, particularly for high risk scenarios. Developers should be aware of and adhere to applicable laws or regulations (including privacy, trade compliance laws, etc.) that are relevant to their use case.
+
 Nothing contained in this Model Card should be interpreted as or deemed a restriction or modification to the license the model is released under.
 
 ## Release Notes
@@ -56,7 +57,7 @@ Minimum Configuration Required:
 - **Model Description:** This is a conversion of the Phi-3.5 Mini-Instruct model for ONNX Runtime inference.
 
 ## How to Get Started with the Model
-To make running of the Phi-3 models across a range of devices and platforms across various execution provider backends possible, we introduce a new API to wrap several aspects of generative AI inferencing. This API make it easy to drag and drop LLMs straight into your app. For running the early version of these models with ONNX Runtime, follow the steps [here](http://aka.ms/generate-tutorial).
+To make running of the Phi-3.5 models across a range of devices and platforms across various execution provider backends possible, we introduce a new API to wrap several aspects of generative AI inferencing. This API make it easy to drag and drop LLMs straight into your app. For running the early version of these models with ONNX Runtime, follow the steps [here](http://aka.ms/generate-tutorial).
 
 For example:
 
@@ -152,9 +153,10 @@ The table below shows the average throughput of the first 256 tokens generated (
 |----------------------------|----------|
 | torch                      | 2.4.1    |
 | triton                     | 3.0.0    |
-| onnxruntime-gpu            | 1.19.2   |
-| onnxruntime-genai          | 0.4.0    |
-| onnxruntime-genai-cuda     | 0.4.0    |
+| onnxruntime-gpu            | 1.20.1   |
+| onnxruntime-genai          | 0.5.2    |
+| onnxruntime-genai-cuda     | 0.5.2    |
+| onnxruntime-genai-directml | 0.5.2    |
 | transformers               | 4.44.2   |
 | llama.cpp                  | bdf314f38a2c90e18285f7d7067e8d736a14000a   |
 

cuda/cuda-fp16/genai_config.json

@@ -1,59 +0,0 @@
-{
-    "model": {
-        "bos_token_id": 1,
-        "context_length": 131072,
-        "decoder": {
-            "session_options": {
-                "log_id": "onnxruntime-genai",
-                "provider_options": [
-                    {
-                        "cuda": {
-                            "enable_cuda_graph": "0"
-                        }
-                    }
-                ]
-            },
-            "filename": "phi-3.5-mini-instruct-cuda-fp16.onnx",
-            "head_size": 96,
-            "hidden_size": 3072,
-            "inputs": {
-                "input_ids": "input_ids",
-                "attention_mask": "attention_mask",
-                "past_key_names": "past_key_values.%d.key",
-                "past_value_names": "past_key_values.%d.value"
-            },
-            "outputs": {
-                "logits": "logits",
-                "present_key_names": "present.%d.key",
-                "present_value_names": "present.%d.value"
-            },
-            "num_attention_heads": 32,
-            "num_hidden_layers": 32,
-            "num_key_value_heads": 32
-        },
-        "eos_token_id": [
-            32007,
-            32001,
-            32000
-        ],
-        "pad_token_id": 32000,
-        "type": "phi3",
-        "vocab_size": 32064
-    },
-    "search": {
-        "diversity_penalty": 0.0,
-        "do_sample": false,
-        "early_stopping": true,
-        "length_penalty": 1.0,
-        "max_length": 131072,
-        "min_length": 0,
-        "no_repeat_ngram_size": 0,
-        "num_beams": 1,
-        "num_return_sequences": 1,
-        "past_present_share_buffer": true,
-        "repetition_penalty": 1.0,
-        "temperature": 1.0,
-        "top_k": 1,
-        "top_p": 1.0
-    }
-}

cuda/cuda-fp16/phi-3.5-mini-instruct-cuda-fp16.onnx.data

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:ec1a077e5ebf1072ef95af5712951af20ce33b003a53717a134b4522b6104067
-size 7642159104

cuda/cuda-fp16/special_tokens_map.json

@@ -1,30 +0,0 @@
-{
-  "bos_token": {
-    "content": "<s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "eos_token": {
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": {
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "unk_token": {
-    "content": "<unk>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  }
-}

cuda/cuda-int4-awq-block-128/config.json

@@ -1,138 +0,0 @@
-{
-  "_name_or_path": "Phi-3.5-mini-instruct",
-  "architectures": [
-    "Phi3ForCausalLM"
-  ],
-  "attention_dropout": 0.0,
-  "auto_map": {
-    "AutoConfig": "configuration_phi3.Phi3Config",
-    "AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM"
-  },
-  "bos_token_id": 1,
-  "embd_pdrop": 0.0,
-  "eos_token_id": 32000,
-  "hidden_act": "silu",
-  "hidden_size": 3072,
-  "initializer_range": 0.02,
-  "intermediate_size": 8192,
-  "max_position_embeddings": 131072,
-  "model_type": "phi3",
-  "num_attention_heads": 32,
-  "num_hidden_layers": 32,
-  "num_key_value_heads": 32,
-  "original_max_position_embeddings": 4096,
-  "pad_token_id": 32000,
-  "resid_pdrop": 0.0,
-  "rms_norm_eps": 1e-05,
-  "rope_scaling": {
-    "long_factor": [
-      1.0800000429153442,
-      1.1100000143051147,
-      1.1399999856948853,
-      1.340000033378601,
-      1.5899999141693115,
-      1.600000023841858,
-      1.6200000047683716,
-      2.620000123977661,
-      3.2300000190734863,
-      3.2300000190734863,
-      4.789999961853027,
-      7.400000095367432,
-      7.700000286102295,
-      9.09000015258789,
-      12.199999809265137,
-      17.670000076293945,
-      24.46000099182129,
-      28.57000160217285,
-      30.420001983642578,
-      30.840002059936523,
-      32.590003967285156,
-      32.93000411987305,
-      42.320003509521484,
-      44.96000289916992,
-      50.340003967285156,
-      50.45000457763672,
-      57.55000305175781,
-      57.93000411987305,
-      58.21000289916992,
-      60.1400032043457,
-      62.61000442504883,
-      62.62000274658203,
-      62.71000289916992,
-      63.1400032043457,
-      63.1400032043457,
-      63.77000427246094,
-      63.93000411987305,
-      63.96000289916992,
-      63.970001220703125,
-      64.02999877929688,
-      64.06999969482422,
-      64.08000183105469,
-      64.12000274658203,
-      64.41000366210938,
-      64.4800033569336,
-      64.51000213623047,
-      64.52999877929688,
-      64.83999633789062
-    ],
-    "short_factor": [
-      1.0,
-      1.0199999809265137,
-      1.0299999713897705,
-      1.0299999713897705,
-      1.0499999523162842,
-      1.0499999523162842,
-      1.0499999523162842,
-      1.0499999523162842,
-      1.0499999523162842,
-      1.0699999332427979,
-      1.0999999046325684,
-      1.1099998950958252,
-      1.1599998474121094,
-      1.1599998474121094,
-      1.1699998378753662,
-      1.2899998426437378,
-      1.339999794960022,
-      1.679999828338623,
-      1.7899998426437378,
-      1.8199998140335083,
-      1.8499997854232788,
-      1.8799997568130493,
-      1.9099997282028198,
-      1.9399996995925903,
-      1.9899996519088745,
-      2.0199997425079346,
-      2.0199997425079346,
-      2.0199997425079346,
-      2.0199997425079346,
-      2.0199997425079346,
-      2.0199997425079346,
-      2.0299997329711914,
-      2.0299997329711914,
-      2.0299997329711914,
-      2.0299997329711914,
-      2.0299997329711914,
-      2.0299997329711914,
-      2.0299997329711914,
-      2.0299997329711914,
-      2.0299997329711914,
-      2.0799996852874756,
-      2.0899996757507324,
-      2.189999580383301,
-      2.2199995517730713,
-      2.5899994373321533,
-      2.729999542236328,
-      2.749999523162842,
-      2.8399994373321533
-    ],
-    "type": "longrope"
-  },
-  "rope_theta": 10000.0,
-  "sliding_window": 262144,
-  "tie_word_embeddings": false,
-  "torch_dtype": "bfloat16",
-  "transformers_version": "4.43.3",
-  "use_cache": true,
-  "attention_bias": false,
-  "vocab_size": 32064
-}

cuda/cuda-int4-awq-block-128/configuration_phi3.py

@@ -1,227 +0,0 @@
-# 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)}"
-            )

cuda/cuda-int4-awq-block-128/phi-3.5-mini-instruct-cuda-int4-awq-block-128.onnx.data

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:dfba2f38f25040110fd7beb4475a342af7e4dae6f889a6cb7a52131387a42c95
-size 2277120000

cuda/cuda-int4-awq-block-128/tokenizer_config.json

@@ -1,131 +0,0 @@
-{
-  "add_bos_token": false,
-  "add_eos_token": false,
-  "add_prefix_space": null,
-  "added_tokens_decoder": {
-    "0": {
-      "content": "<unk>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "1": {
-      "content": "<s>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "2": {
-      "content": "</s>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": false
-    },
-    "32000": {
-      "content": "<|endoftext|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "32001": {
-      "content": "<|assistant|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "32002": {
-      "content": "<|placeholder1|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "32003": {
-      "content": "<|placeholder2|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "32004": {
-      "content": "<|placeholder3|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "32005": {
-      "content": "<|placeholder4|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "32006": {
-      "content": "<|system|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "32007": {
-      "content": "<|end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "32008": {
-      "content": "<|placeholder5|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "32009": {
-      "content": "<|placeholder6|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "32010": {
-      "content": "<|user|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    }
-  },
-  "bos_token": "<s>",
-  "chat_template": "{% for message in messages %}{% if message['role'] == 'system' and message['content'] %}{{'<|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",
-  "sp_model_kwargs": {},
-  "tokenizer_class": "LlamaTokenizer",
-  "unk_token": "<unk>",
-  "use_default_system_prompt": false
-}

{cuda/cuda-int4-awq-block-128 → gpu/gpu-int4-awq-block-128}/genai_config.json

@@ -1,59 +1,54 @@
-{
-    "model": {
-        "bos_token_id": 1,
-        "context_length": 131072,
-        "decoder": {
-            "session_options": {
-                "log_id": "onnxruntime-genai",
-                "provider_options": [
-                    {
-                        "cuda": {
-                            "enable_cuda_graph": "0"
-                        }
-                    }
-                ]
-            },
-            "filename": "phi-3.5-mini-instruct-cuda-int4-awq-block-128.onnx",
-            "head_size": 96,
-            "hidden_size": 3072,
-            "inputs": {
-                "input_ids": "input_ids",
-                "attention_mask": "attention_mask",
-                "past_key_names": "past_key_values.%d.key",
-                "past_value_names": "past_key_values.%d.value"
-            },
-            "outputs": {
-                "logits": "logits",
-                "present_key_names": "present.%d.key",
-                "present_value_names": "present.%d.value"
-            },
-            "num_attention_heads": 32,
-            "num_hidden_layers": 32,
-            "num_key_value_heads": 32
-        },
-        "eos_token_id": [
-            32007,
-            32001,
-            32000
-        ],
-        "pad_token_id": 32000,
-        "type": "phi3",
-        "vocab_size": 32064
-    },
-    "search": {
-        "diversity_penalty": 0.0,
-        "do_sample": true,
-        "early_stopping": true,
-        "length_penalty": 1.0,
-        "max_length": 131072,
-        "min_length": 0,
-        "no_repeat_ngram_size": 0,
-        "num_beams": 1,
-        "num_return_sequences": 1,
-        "past_present_share_buffer": true,
-        "repetition_penalty": 1.0,
-        "temperature": 1.0,
-        "top_k": 1,
-        "top_p": 1.0
-    }
+{
+    "model": {
+        "bos_token_id": 1,
+        "context_length": 131072,
+        "decoder": {
+            "session_options": {
+                "log_id": "onnxruntime-genai",
+                "provider_options": []
+            },
+            "filename": "model.onnx",
+            "head_size": 96,
+            "hidden_size": 3072,
+            "inputs": {
+                "input_ids": "input_ids",
+                "attention_mask": "attention_mask",
+                "position_ids": "position_ids",
+                "past_key_names": "past_key_values.%d.key",
+                "past_value_names": "past_key_values.%d.value"
+            },
+            "outputs": {
+                "logits": "logits",
+                "present_key_names": "present.%d.key",
+                "present_value_names": "present.%d.value"
+            },
+            "num_attention_heads": 32,
+            "num_hidden_layers": 32,
+            "num_key_value_heads": 32
+        },
+        "eos_token_id": [
+            32007,
+            32001,
+            32000
+        ],
+        "pad_token_id": 32000,
+        "type": "phi3",
+        "vocab_size": 32064
+    },
+    "search": {
+        "diversity_penalty": 0.0,
+        "do_sample": true,
+        "early_stopping": true,
+        "length_penalty": 1.0,
+        "max_length": 131072,
+        "min_length": 0,
+        "no_repeat_ngram_size": 0,
+        "num_beams": 1,
+        "num_return_sequences": 1,
+        "past_present_share_buffer": true,
+        "repetition_penalty": 1.0,
+        "temperature": 1.0,
+        "top_k": 1,
+        "top_p": 1.0
+    }
 }

cuda/cuda-int4-awq-block-128/phi-3.5-mini-instruct-cuda-int4-awq-block-128.onnx → gpu/gpu-int4-awq-block-128/model.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fdf3ed5dab1205213634405e69ae41b5a564d93c646783ead672ad4406c1ed5f
-size 26214533
+oid sha256:d4392f76ffec63b659a83261e08337fbb33194f509816b7f843f7c46a6f37cc1
+size 320891

cuda/cuda-fp16/phi-3.5-mini-instruct-cuda-fp16.onnx → gpu/gpu-int4-awq-block-128/model.onnx.data

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e63bd67da9613d088594a83ca58665f4d5e931d673beab93157e56b5893b64c3
-size 26124593
+oid sha256:3ccad8fba8b01a75f6ef96bd5f27401b1ba92eca512819eee3128f576453fa15
+size 2303072256

{cuda/cuda-int4-awq-block-128 → gpu/gpu-int4-awq-block-128}/special_tokens_map.json

@@ -1,30 +1,30 @@
-{
-  "bos_token": {
-    "content": "<s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "eos_token": {
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": {
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "unk_token": {
-    "content": "<unk>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  }
-}
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

{cuda/cuda-fp16 → gpu/gpu-int4-awq-block-128}/tokenizer_config.json

@@ -1,131 +1,131 @@
-{
-  "add_bos_token": false,
-  "add_eos_token": false,
-  "add_prefix_space": null,
-  "added_tokens_decoder": {
-    "0": {
-      "content": "<unk>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "1": {
-      "content": "<s>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "2": {
-      "content": "</s>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": false
-    },
-    "32000": {
-      "content": "<|endoftext|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "32001": {
-      "content": "<|assistant|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "32002": {
-      "content": "<|placeholder1|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "32003": {
-      "content": "<|placeholder2|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "32004": {
-      "content": "<|placeholder3|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "32005": {
-      "content": "<|placeholder4|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "32006": {
-      "content": "<|system|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "32007": {
-      "content": "<|end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "32008": {
-      "content": "<|placeholder5|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "32009": {
-      "content": "<|placeholder6|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "32010": {
-      "content": "<|user|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    }
-  },
-  "bos_token": "<s>",
-  "chat_template": "{% for message in messages %}{% if message['role'] == 'system' and message['content'] %}{{'<|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",
-  "sp_model_kwargs": {},
-  "tokenizer_class": "LlamaTokenizer",
-  "unk_token": "<unk>",
-  "use_default_system_prompt": false
-}
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "32000": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32002": {
+      "content": "<|placeholder1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32003": {
+      "content": "<|placeholder2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32004": {
+      "content": "<|placeholder3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32005": {
+      "content": "<|placeholder4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32006": {
+      "content": "<|system|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32007": {
+      "content": "<|end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32008": {
+      "content": "<|placeholder5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32009": {
+      "content": "<|placeholder6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32010": {
+      "content": "<|user|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}{% if message['role'] == 'system' and message['content'] %}{{'<|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",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}