MiniGemini_pytorch

mgm/constants.py

+CONTROLLER_HEART_BEAT_EXPIRATION = 30
+WORKER_HEART_BEAT_INTERVAL = 15
+
+LOGDIR = "."
+
+# Model Constants
+IGNORE_INDEX = -100
+IMAGE_TOKEN_INDEX = -200
+PREDICT_TOKEN_INDEX = -300
+DEFAULT_IMAGE_TOKEN = "<image>"
+DEFAULT_IMAGE_PATCH_TOKEN = "<im_patch>"
+DEFAULT_IM_START_TOKEN = "<im_start>"
+DEFAULT_IM_END_TOKEN = "<im_end>"
+IMAGE_PLACEHOLDER = "<image-placeholder>"
+DEFAULT_PREDICT_TOKEN = "<predict>"
+
+DESCRIPT_PROMPT = [
+    "Describe this image thoroughly.",
+    "Provide a detailed description in this picture.",
+    "Detail every aspect of what's in this picture.",
+    "Explain this image with precision and detail.",
+    "Give a comprehensive description of this visual.",
+    "Elaborate on the specifics within this image.",
+    "Offer a detailed account of this picture's contents.",
+    "Describe in detail what this image portrays.",
+    "Break down this image into detailed descriptions.",
+    "Provide a thorough description of the elements in this image."]
\ No newline at end of file

mgm/conversation.py

+import dataclasses
+from enum import auto, Enum
+from typing import List, Tuple
+import base64
+from io import BytesIO
+from PIL import Image
+
+
+class SeparatorStyle(Enum):
+    """Different separator style."""
+    SINGLE = auto()
+    TWO = auto()
+    MPT = auto()
+    PLAIN = auto()
+    LLAMA_2 = auto()
+    LLAMA_3 = auto()
+    GEMMA = auto()
+
+
+@dataclasses.dataclass
+class Conversation:
+    """A class that keeps all conversation history."""
+    system: str
+    roles: List[str]
+    messages: List[List[str]]
+    offset: int
+    sep_style: SeparatorStyle = SeparatorStyle.SINGLE
+    sep: str = "###"
+    sep2: str = None
+    version: str = "Unknown"
+
+    skip_next: bool = False
+
+    def get_prompt(self):
+        messages = self.messages
+        if len(messages) > 0 and type(messages[0][1]) is tuple:
+            messages = self.messages.copy()
+            init_role, init_msg = messages[0].copy()
+            init_msg = init_msg[0].replace("<image>", "").strip()
+            if 'mmtag' in self.version:
+                messages[0] = (init_role, init_msg)
+                messages.insert(0, (self.roles[0], "<Image><image></Image>"))
+                messages.insert(1, (self.roles[1], "Received."))
+            else:
+                messages[0] = (init_role, "<image>\n" + init_msg)
+
+        if self.sep_style == SeparatorStyle.SINGLE:
+            ret = self.system + self.sep
+            for role, message in messages:
+                if message:
+                    if type(message) is tuple:
+                        message = message[0]
+                    ret += role + ": " + message + self.sep
+                else:
+                    ret += role + ":"
+        elif self.sep_style == SeparatorStyle.TWO:
+            seps = [self.sep, self.sep2]
+            ret = self.system + seps[0]
+            for i, (role, message) in enumerate(messages):
+                if message:
+                    if type(message) is tuple:
+                        message = message[0]
+                    ret += role + ": " + message + seps[i % 2]
+                else:
+                    ret += role + ":"
+        elif self.sep_style == SeparatorStyle.MPT:
+            ret = self.system + self.sep
+            for role, message in messages:
+                if message:
+                    if type(message) is tuple:
+                        message = message[0]
+                    ret += role + message + self.sep
+                else:
+                    ret += role
+        elif self.sep_style == SeparatorStyle.LLAMA_2:
+            wrap_sys = lambda msg: f"<<SYS>>\n{msg}\n<</SYS>>\n\n" if len(msg) > 0 else msg
+            wrap_inst = lambda msg: f"[INST] {msg} [/INST]"
+            ret = ""
+
+            for i, (role, message) in enumerate(messages):
+                if i == 0:
+                    assert message, "first message should not be none"
+                    assert role == self.roles[0], "first message should come from user"
+                if message:
+                    if type(message) is tuple:
+                        message, _, _ = message
+                    if i == 0: message = wrap_sys(self.system) + message
+                    if i % 2 == 0:
+                        message = wrap_inst(message)
+                        ret += self.sep + message
+                    else:
+                        ret += " " + message + " " + self.sep2
+                else:
+                    ret += ""
+            ret = ret.lstrip(self.sep)
+        elif self.sep_style == SeparatorStyle.LLAMA_3:
+            ret = self.system + self.sep
+            for role, message in messages:
+                if message:
+                    if type(message) is tuple:
+                        message = message[0]
+                    ret += role + message + self.sep
+                else:
+                    ret += role
+        elif self.sep_style == SeparatorStyle.GEMMA:
+            seps = [self.sep, self.sep2]
+            ret = self.system + seps[0]
+            for i, (role, message) in enumerate(messages):
+                if message:
+                    if type(message) is tuple:
+                        message, _, _ = message
+                    ret += "<start_of_turn>" + role + "\n" + message + "<end_of_turn>\n" + seps[i % 2]
+                else:
+                    ret += "<start_of_turn>" + role + "\n"
+        elif self.sep_style == SeparatorStyle.PLAIN:
+            seps = [self.sep, self.sep2]
+            ret = self.system
+            for i, (role, message) in enumerate(messages):
+                if message:
+                    if type(message) is tuple:
+                        message, _, _ = message
+                    ret += message + seps[i % 2]
+                else:
+                    ret += ""
+        else:
+            raise ValueError(f"Invalid style: {self.sep_style}")
+
+        return ret
+
+    def append_message(self, role, message):
+        self.messages.append([role, message])
+
+    def process_image(self, image, image_process_mode, return_pil=False, image_format='PNG', max_len=1344, min_len=672):
+        if image_process_mode == "Pad":
+            def expand2square(pil_img, background_color=(122, 116, 104)):
+                width, height = pil_img.size
+                if width == height:
+                    return pil_img
+                elif width > height:
+                    result = Image.new(pil_img.mode, (width, width), background_color)
+                    result.paste(pil_img, (0, (width - height) // 2))
+                    return result
+                else:
+                    result = Image.new(pil_img.mode, (height, height), background_color)
+                    result.paste(pil_img, ((height - width) // 2, 0))
+                    return result
+            image = expand2square(image)
+        elif image_process_mode in ["Default", "Crop"]:
+            pass
+        elif image_process_mode == "Resize":
+            image = image.resize((336, 336))
+        else:
+            raise ValueError(f"Invalid image_process_mode: {image_process_mode}")
+        if max(image.size) > max_len:
+            max_hw, min_hw = max(image.size), min(image.size)
+            aspect_ratio = max_hw / min_hw
+            shortest_edge = int(min(max_len / aspect_ratio, min_len, min_hw))
+            longest_edge = int(shortest_edge * aspect_ratio)
+            W, H = image.size
+            if H > W:
+                H, W = longest_edge, shortest_edge
+            else:
+                H, W = shortest_edge, longest_edge
+            image = image.resize((W, H))
+        if return_pil:
+            return image
+        else:
+            buffered = BytesIO()
+            image.save(buffered, format=image_format)
+            img_b64_str = base64.b64encode(buffered.getvalue()).decode()
+            return img_b64_str
+
+    def get_images(self, return_pil=False):
+        images = []
+        for i, (role, msg) in enumerate(self.messages[self.offset:]):
+            if i % 2 == 0:
+                if type(msg) is tuple:
+                    msg, image, image_process_mode = msg
+                    image = self.process_image(image, image_process_mode, return_pil=return_pil)
+                    images.append(image)
+        return images
+
+    def to_gradio_chatbot(self):
+        ret = []
+        for i, (role, msg) in enumerate(self.messages[self.offset:]):
+            if i % 2 == 0:
+                if type(msg) is tuple:
+                    msg, image, image_process_mode = msg
+                    img_b64_str = self.process_image(
+                        image, "Default", return_pil=False,
+                        image_format='JPEG')
+                    img_str = f'<img src="data:image/jpeg;base64,{img_b64_str}" alt="user upload image" />'
+                    msg = img_str + msg.replace('<image>', '').strip()
+                    ret.append([msg, None])
+                else:
+                    ret.append([msg, None])
+            else:
+                if type(msg) is tuple and len(msg) == 2:
+                    msg, img_b64_str = msg
+                    img_str = f'<img src="data:image/jpeg;base64,{img_b64_str}" alt="user upload image" />'
+                    msg = msg.strip() + img_str
+                ret[-1][-1] = msg
+        return ret
+
+    def copy(self):
+        return Conversation(
+            system=self.system,
+            roles=self.roles,
+            messages=[[x, y] for x, y in self.messages],
+            offset=self.offset,
+            sep_style=self.sep_style,
+            sep=self.sep,
+            sep2=self.sep2,
+            version=self.version)
+
+    def dict(self):
+        if len(self.get_images()) > 0:
+            return {
+                "system": self.system,
+                "roles": self.roles,
+                "messages": [[x, y[0] if type(y) is tuple else y] for x, y in self.messages],
+                "offset": self.offset,
+                "sep": self.sep,
+                "sep2": self.sep2,
+            }
+        return {
+            "system": self.system,
+            "roles": self.roles,
+            "messages": self.messages,
+            "offset": self.offset,
+            "sep": self.sep,
+            "sep2": self.sep2,
+        }
+
+
+conv_vicuna_v0 = Conversation(
+    system="A chat between a curious human and an artificial intelligence assistant. "
+           "The assistant gives helpful, detailed, and polite answers to the human's questions.",
+    roles=("Human", "Assistant"),
+    messages=(
+        ("Human", "What are the key differences between renewable and non-renewable energy sources?"),
+        ("Assistant",
+            "Renewable energy sources are those that can be replenished naturally in a relatively "
+            "short amount of time, such as solar, wind, hydro, geothermal, and biomass. "
+            "Non-renewable energy sources, on the other hand, are finite and will eventually be "
+            "depleted, such as coal, oil, and natural gas. Here are some key differences between "
+            "renewable and non-renewable energy sources:\n"
+            "1. Availability: Renewable energy sources are virtually inexhaustible, while non-renewable "
+            "energy sources are finite and will eventually run out.\n"
+            "2. Environmental impact: Renewable energy sources have a much lower environmental impact "
+            "than non-renewable sources, which can lead to air and water pollution, greenhouse gas emissions, "
+            "and other negative effects.\n"
+            "3. Cost: Renewable energy sources can be more expensive to initially set up, but they typically "
+            "have lower operational costs than non-renewable sources.\n"
+            "4. Reliability: Renewable energy sources are often more reliable and can be used in more remote "
+            "locations than non-renewable sources.\n"
+            "5. Flexibility: Renewable energy sources are often more flexible and can be adapted to different "
+            "situations and needs, while non-renewable sources are more rigid and inflexible.\n"
+            "6. Sustainability: Renewable energy sources are more sustainable over the long term, while "
+            "non-renewable sources are not, and their depletion can lead to economic and social instability.\n")
+    ),
+    offset=2,
+    sep_style=SeparatorStyle.SINGLE,
+    sep="###",
+)
+
+conv_vicuna_v1 = Conversation(
+    system="A chat between a curious user and an artificial intelligence assistant. "
+    "The assistant gives helpful, detailed, and polite answers to the user's questions.",
+    roles=("USER", "ASSISTANT"),
+    version="v1",
+    messages=(),
+    offset=0,
+    sep_style=SeparatorStyle.TWO,
+    sep=" ",
+    sep2="</s>",
+)
+
+conv_llama_2 = Conversation(
+    system="""You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe.  Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature.
+
+If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.""",
+    roles=("USER", "ASSISTANT"),
+    version="llama_v2",
+    messages=(),
+    offset=0,
+    sep_style=SeparatorStyle.LLAMA_2,
+    sep="<s>",
+    sep2="</s>",
+)
+
+conv_llava_llama_2 = Conversation(
+    system="You are a helpful language and vision assistant. "
+           "You are able to understand the visual content that the user provides, "
+           "and assist the user with a variety of tasks using natural language.",
+    roles=("USER", "ASSISTANT"),
+    version="llama_v2",
+    messages=(),
+    offset=0,
+    sep_style=SeparatorStyle.LLAMA_2,
+    sep="<s>",
+    sep2="</s>",
+)
+
+conv_llama_3 = Conversation(
+    system="<|start_header_id|>system<|end_header_id|>\n\nYou are a helpful language and vision assistant. "
+           "You are able to understand the visual content that the user provides, "
+           "and assist the user with a variety of tasks using natural language.",
+    roles=("<|start_header_id|>user<|end_header_id|>\n\n", 
+           "<|start_header_id|>system<|end_header_id|>\n\n"),
+    version="llama_v3",
+    messages=(),
+    offset=0,
+    sep_style=SeparatorStyle.LLAMA_3,
+    sep="<|eot_id|>",
+)
+
+conv_mpt = Conversation(
+    system="""<|im_start|>system
+A conversation between a user and an LLM-based AI assistant. The assistant gives helpful and honest answers.""",
+    roles=("<|im_start|>user\n", "<|im_start|>assistant\n"),
+    version="mpt",
+    messages=(),
+    offset=0,
+    sep_style=SeparatorStyle.MPT,
+    sep="<|im_end|>",
+)
+
+conv_llava_plain = Conversation(
+    system="",
+    roles=("", ""),
+    messages=(
+    ),
+    offset=0,
+    sep_style=SeparatorStyle.PLAIN,
+    sep="\n",
+)
+
+conv_llava_v0 = Conversation(
+    system="A chat between a curious human and an artificial intelligence assistant. "
+           "The assistant gives helpful, detailed, and polite answers to the human's questions.",
+    roles=("Human", "Assistant"),
+    messages=(
+    ),
+    offset=0,
+    sep_style=SeparatorStyle.SINGLE,
+    sep="###",
+)
+
+conv_llava_v0_mmtag = Conversation(
+    system="A chat between a curious user and an artificial intelligence assistant. "
+           "The assistant is able to understand the visual content that the user provides, and assist the user with a variety of tasks using natural language."
+           "The visual content will be provided with the following format: <Image>visual content</Image>.",
+    roles=("Human", "Assistant"),
+    messages=(
+    ),
+    offset=0,
+    sep_style=SeparatorStyle.SINGLE,
+    sep="###",
+    version="v0_mmtag",
+)
+
+conv_llava_v1 = Conversation(
+    system="A chat between a curious human and an artificial intelligence assistant. "
+           "The assistant gives helpful, detailed, and polite answers to the human's questions.",
+    roles=("USER", "ASSISTANT"),
+    version="v1",
+    messages=(),
+    offset=0,
+    sep_style=SeparatorStyle.TWO,
+    sep=" ",
+    sep2="</s>",
+)
+
+conv_vicuna_imgsp_v1 = Conversation(
+    system="A chat between a curious user and an artificial intelligence assistant. "
+    "The assistant gives helpful, detailed, and polite answers to the user's questions.",
+    roles=("USER", "ASSISTANT"),
+    version="imgsp_v1",
+    messages=(),
+    offset=0,
+    sep_style=SeparatorStyle.TWO,
+    sep=" ",
+    sep2="</s>",
+)
+
+conv_llava_v1_mmtag = Conversation(
+    system="A chat between a curious user and an artificial intelligence assistant. "
+           "The assistant is able to understand the visual content that the user provides, and assist the user with a variety of tasks using natural language."
+           "The visual content will be provided with the following format: <Image>visual content</Image>.",
+    roles=("USER", "ASSISTANT"),
+    messages=(),
+    offset=0,
+    sep_style=SeparatorStyle.TWO,
+    sep=" ",
+    sep2="</s>",
+    version="v1_mmtag",
+)
+
+conv_phi_2 = Conversation(
+    system="A chat between a curious user and an artificial intelligence assistant. "
+           "The assistant gives helpful, detailed, and polite answers to the user's questions.",
+    roles=("USER", "ASSISTANT"),
+    version="phi2",
+    messages=(),
+    offset=0,
+    sep_style=SeparatorStyle.TWO,
+    sep=" ",
+    sep2="<|endoftext|>",
+)
+
+conv_mistral_instruct = Conversation(
+    system="",
+    roles=("USER", "ASSISTANT"),
+    version="llama_v2",
+    messages=(),
+    offset=0,
+    sep_style=SeparatorStyle.LLAMA_2,
+    sep="<s>",
+    sep2="</s>",
+)
+
+conv_gemma = Conversation(
+    system="",
+    roles=("user", "model"),
+    version="gemma",
+    messages=(),
+    offset=0,
+    sep_style=SeparatorStyle.GEMMA,
+    sep="",
+    sep2="<eos>",
+)
+
+conv_chatml_direct = Conversation(
+    system="""<|im_start|>system
+Answer the questions.""",
+    roles=("<|im_start|>user\n", "<|im_start|>assistant\n"),
+    version="mpt",
+    messages=(),
+    offset=0,
+    sep_style=SeparatorStyle.MPT,
+    sep="<|im_end|>",
+)
+
+default_conversation = conv_vicuna_v1
+conv_templates = {
+    "default": conv_vicuna_v0,
+    "v0": conv_vicuna_v0,
+    "v1": conv_vicuna_v1,
+    "vicuna_v1": conv_vicuna_v1,
+    "phi_2": conv_phi_2,
+    "gemma": conv_gemma,
+    "llama_2": conv_llama_2,
+    "llama_3": conv_llama_3,
+    "imgsp_v1": conv_vicuna_imgsp_v1,
+    "mistral_instruct": conv_mistral_instruct,
+    "chatml_direct": conv_chatml_direct,
+    "mistral_direct": conv_chatml_direct,
+    "plain": conv_llava_plain,
+    "v0_plain": conv_llava_plain,
+    "llava_v0": conv_llava_v0,
+    "v0_mmtag": conv_llava_v0_mmtag,
+    "llava_v1": conv_llava_v1,
+    "v1_mmtag": conv_llava_v1_mmtag,
+    "llava_llama_2": conv_llava_llama_2,
+    "mpt": conv_mpt,
+}
+
+
+if __name__ == "__main__":
+    print(default_conversation.get_prompt())
\ No newline at end of file

mgm/eval/MMMU/LICENSE

+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   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.

mgm/eval/MMMU/README.md

+# MMMU 
+
+[**🌐 Homepage**](https://mmmu-benchmark.github.io/) | [**🤗 Dataset**](https://huggingface.co/datasets/MMMU/MMMU/) | [**🤗 Paper**](https://huggingface.co/papers/2311.16502) | [**📖 arXiv**](https://arxiv.org/pdf/2311.16502.pdf) | [**GitHub**](https://github.com/MMMU-Benchmark/MMMU)
+
+
+
+This repo contains the evaluation code for the paper "[MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI](https://arxiv.org/pdf/2311.16502.pdf)"
+
+## 🔔News
+
+- **🚀[2024-01-31]: We added Human Expert performance on the [Leaderboard](https://mmmu-benchmark.github.io/#leaderboard)!🌟**
+- **🔥[2023-12-04]: Our evaluation server for test set is now availble on [EvalAI](https://eval.ai/web/challenges/challenge-page/2179/overview). We welcome all submissions and look forward to your participation! 😆**
+
+## Introduction
+We introduce MMMU: a new benchmark designed to evaluate multimodal models on massive multi-discipline tasks demanding college-level subject knowledge and deliberate reasoning. MMMU includes **11.5K meticulously collected multimodal questions** from college exams, quizzes, and textbooks, covering six core disciplines: Art & Design, Business, Science, Health & Medicine, Humanities & Social Science, and Tech & Engineering. These questions span **30 subjects** and **183 subfields**, comprising **32 highly heterogeneous image types**, such as charts, diagrams, maps, tables, music sheets, and chemical structures. Unlike existing benchmarks, MMMU focuses on advanced perception and reasoning with domain-specific knowledge, challenging models to perform tasks akin to those faced by experts. Our evaluation of 14 open-source LMMs and the proprietary GPT-4V(ision) highlights the substantial challenges posed by MMMU. Even the advanced GPT-4V only achieves a 56% accuracy, indicating significant room for improvement. We believe MMMU will stimulate the community to build next-generation multimodal foundation models towards expert artificial general intelligence (AGI).
+
+![Alt text](image.png)
+
+## Dataset Creation
+
+MMMU was created to challenge multimodal models with tasks that demand college-level subject knowledge and deliberate reasoning, pushing the boundaries of what these models can achieve in terms of expert-level perception and reasoning. Please refer to our huggingface [**🤗 Dataset**](https://huggingface.co/datasets/MMMU/MMMU/) for more details.
+
+## Evaluation
+Please refer to our [eval](eval)
+ folder for more details.
+
+## 🏆 Mini-Leaderboard
+| Model                      | Val (900) | Test (10.5K) |
+|----------------------------|:---------:|:------------:|
+| Expert (Best)              |   88.6    |      -       |
+| Expert (Medium)            |   82.6    |      -       |
+| Expert (Worst)             |   76.2    |      -       |
+| Gemini Ultra*              | **59.4**  |      -       |
+| GPT-4V(ision) (Playground) |   56.8    |   **55.7**   |
+| Qwen-VL-MAX*               |   51.4    |     46.8     |
+| LLaVA-1.6-34B*             |   51.1    |     44.7     |
+| Adept Fuyu-Heavy*          |   48.3    |      -       |
+| Gemini Pro*                |   47.9    |      -       |
+| Yi-VL-34B*                 |   45.9    |     41.6     |
+| Qwen-VL-PLUS*              |   45.2    |     40.8     |
+| Marco-VL*                  |   41.2    |     40.4     |
+| OmniLMM-12B*               |   41.1    |     40.4     |
+| InternLM-XComposer2-VL*    |   43.0    |     38.2     |
+| Yi-VL-6B*                  |   39.1    |     37.8     |
+| InfiMM-Zephyr-7B*          |   39.4    |     35.5     |
+| InternVL-Chat-V1.1*        |   39.1    |     35.3     |
+| SVIT*                      |   38.0    |     34.1     |
+| MiniCPM-V*                 |   37.2    |     34.1     |
+| Emu2-Chat*                 |   36.3    |     34.1     |
+| BLIP-2 FLAN-T5-XXL         |   35.4    |     34.0     |
+| InstructBLIP-T5-XXL        |   35.7    |     33.8     |
+| LLaVA-1.5-13B              |   36.4    |     33.6     |
+| Bunny-3B*                  |   38.2    |     33.0     |
+| Qwen-VL-7B-Chat            |   35.9    |     32.9     |
+| SPHINX*                    |   32.9    |     32.9     |
+| mPLUG-OWL2*                |   32.7    |     32.1     |
+| BLIP-2 FLAN-T5-XL          |   34.4    |     31.0     |
+| InstructBLIP-T5-XL         |   32.9    |     30.6     |
+| Gemini Nano2*              |   32.6    |      -       |
+| CogVLM                     |   32.1    |     30.1     |
+| Otter                      |   32.2    |     29.1     |
+| LLaMA-Adapter2-7B          |   29.8    |     27.7     |
+| MiniGPT4-Vicuna-13B        |   26.8    |     27.6     |
+| Adept Fuyu-8B              |   27.9    |     27.4     |
+| Kosmos2                    |   24.4    |     26.6     |
+| OpenFlamingo2-9B           |   28.7    |     26.3     |
+| Frequent Choice            |   22.1    |     23.9     |
+| Random Choice              |   26.8    |     25.8     |
+
+*: results provided by the authors.
+
+
+🎯 **We have released a full suite comprising 150 development samples and 900 validation samples. However, the 10,500 test questions are available without their answers.** Use the development set for few-shot/in-context learning, and the validation set for debugging models, selecting hyperparameters, and quick evaluations. The answers and explanations for the test set questions are withheld. You can submit your model's predictions for the **test set** on **[EvalAI](https://eval.ai/web/challenges/challenge-page/2179/overview)**.
+
+## Disclaimers
+The guidelines for the annotators emphasized strict compliance with copyright and licensing rules from the initial data source, specifically avoiding materials from websites that forbid copying and redistribution. 
+Should you encounter any data samples potentially breaching the copyright or licensing regulations of any site, we encourage you to [contact](#contact) us. Upon verification, such samples will be promptly removed.
+
+## Contact
+- Xiang Yue: xiangyue.work@gmail.com
+- Yu Su: su.809@osu.edu
+- Wenhu Chen: wenhuchen@uwaterloo.ca
+
+## Citation
+
+**BibTeX:**
+```bibtex
+@article{yue2023mmmu,
+  title={MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI},
+  author={Xiang Yue and Yuansheng Ni and Kai Zhang and Tianyu Zheng and Ruoqi Liu and Ge Zhang and Samuel Stevens and Dongfu Jiang and Weiming Ren and Yuxuan Sun and Cong Wei and Botao Yu and Ruibin Yuan and Renliang Sun and Ming Yin and Boyuan Zheng and Zhenzhu Yang and Yibo Liu and Wenhao Huang and Huan Sun and Yu Su and Wenhu Chen},
+  journal={arXiv preprint arXiv:2311.16502},
+  year={2023},
+}
+```

mgm/eval/MMMU/eval/README.md

+# Evaluation Guidelines
+We provide detailed instructions for evaluation. 
+To execute our evaluation script, please ensure that the structure of your model outputs is the same as ours.
+
+We provide two options:
+1. Evaluation only: you can parse the response on your own and simply provide one file with all the final predictions.
+2. Parse and evaluation: you can leave all the responses to us with the output formats shown below.
+
+## Evaluation Only
+If you want to use your own parsing logic and *only provide the final answer*, you can use `main_eval_only.py`.
+
+You can provide all the outputs in *one file* in the following format:
+
+```
+{
+    "validation_Accounting_1": "D", # strictly "A", "B", "C", "D" for multi-choice question
+    "validation_Architecture_and_Engineering_14": "0.0", # any string response for open question.
+    ...
+}
+```
+Then run eval_only with:
+```
+python main_eval_only.py --output_path ./example_outputs/llava1.5_13b/total_val_output.json
+```
+
+Please refer to [example output](https://github.com/MMMU-Benchmark/MMMU/blob/main/eval/example_outputs/llava1.5_13b/total_val_output.json) for a detailed prediction file form.
+
+
+## Parse and Evaluation
+You can also provide response and run the `main_parse_and_eval.py` to use our answer parsing processing and evaluation pipeline as follows:
+
+### Output folder structure
+
+```
+└── model_name
+    ├── category_name (e.g., Accounting)
+    │   ├── output.json
+    └── category_name (e.g., Electronics)
+        ├── output.json
+    ...
+```
+
+### Output file
+Each `output.json`` has a list of dict containing instances for evaluation ().
+```
+[
+    {
+        "id": "validation_Electronics_28",
+        "question_type": "multiple-choice",
+        "answer": "A", # given answer
+        "all_choices": [ # create using `get_multi_choice_info` in 
+            "A",
+            "B",
+            "C",
+            "D"
+        ],
+        "index2ans": { # create using `get_multi_choice_info` in 
+            "A": "75 + 13.3 cos(250t - 57.7°)V",
+            "B": "75 + 23.3 cos(250t - 57.7°)V",
+            "C": "45 + 3.3 cos(250t - 57.7°)V",
+            "D": "95 + 13.3 cos(250t - 57.7°)V"
+        },
+        "response": "B" # model response
+    },
+    {
+        "id": "validation_Electronics_29",
+        "question_type": "short-answer",
+        "answer": "30", # given answer
+        "response": "36 watts" # model response
+    },
+    ...
+]
+```
+
+### Evaluation
+```
+python main_parse_and_eval.py --path ./example_outputs/llava1.5_13b --subject ALL # all subject
+
+# OR you can sepecify one subject for the evaluation
+
+python main_parse_and_eval.py --path ./example_outputs/llava1.5_13b --subject elec # short name for Electronics. use --help for all short names
+
+```
+
+`main_parse_and_eval.py` will generate `parsed_output.json` and `result.json` in the subfolder under the same category with output.json, respectively.
+
+```
+├── Accounting
+│   ├── output.json
+│   ├── parsed_output.json
+│   └── result.json
+└── Electronics
+    ├── output.json
+    ├── parsed_output.json
+    └── result.json
+...
+```
+
+### Print Results
+You can print results locally if you want. (use `pip install tabulate` if you haven't)
+```
+python print_results.py --path ./example_outputs/llava1.5_13b
+# Results may be slightly different due to the ramdon selection for fail response
+```
+
+
+
+##### Run Llava
+In case if you want to reproduce the results of some of the models, please go check run_llava.py as an example.
+
+By seeting up the env following the [llava official repo](https://github.com/haotian-liu/LLaVA) and installing `datasets` packages by huggingface, you can run llava viathe following command:
+
+```
+CUDA_VISIBLE_DEVICES=0 nohup python run_llava.py \
+--output_path example_outputs/llava1.5_13b_val.json \
+--model_path liuhaotian/llava-v1.5-13b \
+--config_path configs/llava1.5.yaml
+```
+
+Then you can evaluate the results via the very first pipeline.

mgm/eval/MMMU/eval/configs/llava1.5.yaml

+task_instructions:
+- ""
+multi_choice_example_format:
+- "{}
+
+{}
+
+Answer with the option's letter from the given choices directly."
+
+short_ans_example_format:
+- "{}
+
+Answer the question using a single word or phrase."
+temperature:
+- 0
\ No newline at end of file

mgm/eval/MMMU/eval/convert_to_test.py

+import os
+import json
+from argparse import ArgumentParser
+
+from utils.eval_utils import evaluate
+from utils.data_utils import save_json
+
+
+def main():
+    parser = ArgumentParser()
+    parser.add_argument('--result_file', type=str, default='llava1.5_13b_val.txt',
+                        help='name of saved json')
+    parser.add_argument('--output_path', type=str, default='llava1.5_13b_val.json',
+                        help='name of saved json')
+
+    args = parser.parse_args()
+    out_samples = [json.loads(line) for line in open(args.result_file)]
+    out_json = {}
+    for _sample in out_samples:
+        _result = _sample['parsed_pred']
+        if isinstance(_result, list):
+            _result = str(_result[0])
+        out_json[_sample['id']] = _result
+    
+    save_json(args.output_path, out_json)
+
+
+if __name__ == '__main__':
+    main()

mgm/eval/MMMU/eval/eval.py

+import os
+import json
+from argparse import ArgumentParser
+
+from utils.eval_utils import evaluate
+from utils.data_utils import save_json
+
+
+def main():
+    parser = ArgumentParser()
+    parser.add_argument('--result_file', type=str, default='llava1.5_13b_val.txt',
+                        help='name of saved json')
+    parser.add_argument('--output_path', type=str, default='llava1.5_13b_val.json',
+                        help='name of saved json')
+
+    args = parser.parse_args()
+    out_samples = [json.loads(line) for line in open(args.result_file)]
+    
+    judge_dict, metric_dict = evaluate(out_samples)
+    metric_dict.update({"num_example": len(out_samples)})
+    judge_dict['metric_dict'] = metric_dict
+    save_dir = '/'.join(args.output_path.split('/')[:-1])
+    if not os.path.exists(save_dir):
+        os.makedirs(save_dir)
+    save_json(args.output_path, judge_dict)
+
+    print(metric_dict)
+
+
+if __name__ == '__main__':
+    main()