flexeval 0.3.1__tar.gz

flexeval-0.3.1/LICENSE

@@ -0,0 +1,202 @@
+
+                                 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.

flexeval-0.3.1/PKG-INFO

@@ -0,0 +1,91 @@
+Metadata-Version: 2.1
+Name: flexeval
+Version: 0.3.1
+Summary: 
+Author: ryokan-ri
+Author-email: ryokan.ri@sbintuitions.co.jp
+Requires-Python: >=3.8, !=2.7.*, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, !=3.4.*, !=3.5.*, !=3.6.*, !=3.7.*
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Provides-Extra: vllm
+Requires-Dist: datasets (>=2.14.6,<3.0.0)
+Requires-Dist: evaluate (>=0.4.1,<0.5.0)
+Requires-Dist: fuzzywuzzy (>=0.18.0,<0.19.0)
+Requires-Dist: google-api-python-client (>=2.131.0,<3.0.0)
+Requires-Dist: jinja2 (>=3.1.2,<4.0.0)
+Requires-Dist: jiwer (>=3.0.4,<4.0.0)
+Requires-Dist: jsonargparse[jsonnet] (>=4.26.1,<5.0.0)
+Requires-Dist: openai (>=1.16.1,<2.0.0)
+Requires-Dist: peft (>=0.10.0,<0.11.0)
+Requires-Dist: python-levenshtein (>=0.23.0,<0.24.0)
+Requires-Dist: rouge (>=1.0.1,<2.0.0)
+Requires-Dist: sacrebleu[ja] (>=2.4.1,<3.0.0)
+Requires-Dist: transformers[ja,sentencepiece,torch] (>=4.34.1,<5.0.0)
+Requires-Dist: vllm (>=0.4.0,<0.5.0) ; extra == "vllm"
+Description-Content-Type: text/markdown
+
+# FlexEval
+
+![logo](docs/assets/logo.png)
+
+**Flexible evaluation tool for language models. Easy to extend, highly customizable!**
+
+<h4 align="center">
+    <p>
+        <b>English</b> |
+        <a href="https://github.com/sbintuitions/flexeval/blob/main/README_ja.md">日本語</a> |
+    </p>
+</h4>
+
+With FlexEval, you can evaluate language models with:
+
+* Zero/few-shot in-context learning tasks
+* Open-ended text-generation benchmarks such as [MT-Bench](https://github.com/lm-sys/FastChat/tree/main/fastchat/llm_judge) with automatic evaluation using GPT-4
+* Log-probability-based multiple-choice tasks 
+* Computing perplexity of text data
+
+For more use cases, see the [documentation](https://sbintuitions.github.io/flexeval/).
+
+
+## Key Features
+
+* **Flexibility**: `flexeval` is flexible in terms of the evaluation setup and the language model to be evaluated.
+* **Modularity**: The core components of `flexeval` are easily extensible and replaceable.
+* **Clarity**: The results of evaluation are clear and all the details are saved.
+* **Reproducibility**: `flexeval` should be reproducible, with the ability to save and load configurations and results.
+
+## Installation
+
+```bash
+pip install flexeval
+```
+
+## Quick Start
+
+The following minimal example evaluates the hugging face model `sbintuitions/tiny-lm` with the `commonsense_qa` task.
+
+```bash
+flexeval_lm \
+  --language_model HuggingFaceLM \
+  --language_model.model_name "sbintuitions/tiny-lm" \
+  --eval_setup "commonsense_qa" \
+  --save_dir "results/commonsense_qa"
+```
+(The model used in the example is solely for debugging purposes and does not perform well. Try switching to your favorite model!)
+
+The results saved in `--saved_dir` contain:
+
+* `config.json`: The configuration of the evaluation, which can be used to replicate the evaluation.
+* `metrics.json`: The evaluation metrics.
+* `outputs.jsonl`: The outputs of the language model that comes with instance-level metrics.
+
+You can flexibly customize the evaluation by specifying command-line arguments or configuration files.
+Besides the [Transformers](https://github.com/huggingface/transformers) model, you can also evaluate models via [OpenAI ChatGPT](https://openai.com/index/openai-api/) and [vLLM](https://github.com/vllm-project/vllm), and other models can be readily added!
+
+## Next Steps
+* Run `flexeval_presets` to check the list of off-the-shelf presets in addition to `commonsense_qa`. You can find the details in the [Preset Configs](https://sbintuitions.github.io/flexeval/preset_configs/) section.
+* See [Getting Started](https://sbintuitions.github.io/flexeval/getting_started/) to check the tutorial examples for other kinds of tasks.
+* See the [Configuration Guide](https://sbintuitions.github.io/flexeval/configuration_guide/) to set up your evaluation.
+

flexeval-0.3.1/README.md

@@ -0,0 +1,62 @@
+# FlexEval
+
+![logo](docs/assets/logo.png)
+
+**Flexible evaluation tool for language models. Easy to extend, highly customizable!**
+
+<h4 align="center">
+    <p>
+        <b>English</b> |
+        <a href="https://github.com/sbintuitions/flexeval/blob/main/README_ja.md">日本語</a> |
+    </p>
+</h4>
+
+With FlexEval, you can evaluate language models with:
+
+* Zero/few-shot in-context learning tasks
+* Open-ended text-generation benchmarks such as [MT-Bench](https://github.com/lm-sys/FastChat/tree/main/fastchat/llm_judge) with automatic evaluation using GPT-4
+* Log-probability-based multiple-choice tasks 
+* Computing perplexity of text data
+
+For more use cases, see the [documentation](https://sbintuitions.github.io/flexeval/).
+
+
+## Key Features
+
+* **Flexibility**: `flexeval` is flexible in terms of the evaluation setup and the language model to be evaluated.
+* **Modularity**: The core components of `flexeval` are easily extensible and replaceable.
+* **Clarity**: The results of evaluation are clear and all the details are saved.
+* **Reproducibility**: `flexeval` should be reproducible, with the ability to save and load configurations and results.
+
+## Installation
+
+```bash
+pip install flexeval
+```
+
+## Quick Start
+
+The following minimal example evaluates the hugging face model `sbintuitions/tiny-lm` with the `commonsense_qa` task.
+
+```bash
+flexeval_lm \
+  --language_model HuggingFaceLM \
+  --language_model.model_name "sbintuitions/tiny-lm" \
+  --eval_setup "commonsense_qa" \
+  --save_dir "results/commonsense_qa"
+```
+(The model used in the example is solely for debugging purposes and does not perform well. Try switching to your favorite model!)
+
+The results saved in `--saved_dir` contain:
+
+* `config.json`: The configuration of the evaluation, which can be used to replicate the evaluation.
+* `metrics.json`: The evaluation metrics.
+* `outputs.jsonl`: The outputs of the language model that comes with instance-level metrics.
+
+You can flexibly customize the evaluation by specifying command-line arguments or configuration files.
+Besides the [Transformers](https://github.com/huggingface/transformers) model, you can also evaluate models via [OpenAI ChatGPT](https://openai.com/index/openai-api/) and [vLLM](https://github.com/vllm-project/vllm), and other models can be readily added!
+
+## Next Steps
+* Run `flexeval_presets` to check the list of off-the-shelf presets in addition to `commonsense_qa`. You can find the details in the [Preset Configs](https://sbintuitions.github.io/flexeval/preset_configs/) section.
+* See [Getting Started](https://sbintuitions.github.io/flexeval/getting_started/) to check the tutorial examples for other kinds of tasks.
+* See the [Configuration Guide](https://sbintuitions.github.io/flexeval/configuration_guide/) to set up your evaluation.

flexeval-0.3.1/flexeval/__init__.py

@@ -0,0 +1,17 @@
+from .core.chat_dataset import *
+from .core.evaluate_chat_response import evaluate_chat_response
+from .core.evaluate_from_file import evaluate_from_file
+from .core.evaluate_generation import evaluate_generation
+from .core.evaluate_multiple_choice import evaluate_multiple_choice
+from .core.evaluate_pairwise import evaluate_pairwise
+from .core.evaluate_perplexity import evaluate_perplexity
+from .core.few_shot_generator import *
+from .core.generation_dataset import *
+from .core.language_model import *
+from .core.metric import *
+from .core.metric.normalizer import *
+from .core.metric.tokenizer import *
+from .core.multiple_choice_dataset import *
+from .core.pairwise_comparison import *
+from .core.prompt_template import *
+from .core.text_dataset import *

flexeval-0.3.1/flexeval/core/chat_dataset/__init__.py

@@ -0,0 +1,3 @@
+from .base import ChatDataset, ChatInstance
+from .chatbot_bench import ChatbotBench
+from .hf_dataset import HfChatDataset

flexeval-0.3.1/flexeval/core/chat_dataset/base.py

@@ -0,0 +1,71 @@
+from __future__ import annotations
+
+from abc import ABC, abstractmethod
+from dataclasses import dataclass
+from typing import Any
+
+
+@dataclass
+class ChatInstance:
+    """
+    A dataclass representing a single chat that will be fed to a chat language model.
+    """
+
+    messages: list[dict[str, str]]
+    """
+    A list of messages in the chat.
+    The format of messages typically follows [OpenAI's Chat Completions API](https://platform.openai.com/docs/guides/text-generation/chat-completions-api).
+    ```json
+    [
+        {
+            "role": "assistant",
+            "content": "Hello! How can I help you today?"
+        },
+        {
+            "role": "user",
+            "content": "I'd like to book a flight to Paris."
+        }
+    ]
+    ```
+    """
+    references: list[str]
+    """
+    A list of reference responses to the user's last message.
+    The model's response will be evaluated against these references.
+    """
+    extra_info: dict[str, Any]
+    """
+    Extra information that can be used by passing to `Metric`.
+    """
+
+    def __post_init__(self) -> None:
+        if "messages" in self.extra_info:
+            msg = "extra_info cannot contain a key named 'messages'. It will conflict with the 'messages' attribute."
+            raise ValueError(msg)
+
+
+class ChatDataset(ABC):
+    """A dataset holding `ChatInstance`."""
+
+    @abstractmethod
+    def __len__(self) -> int:
+        """
+        Returns the number of chat instances in the dataset.
+        """
+        raise NotImplementedError
+
+    @abstractmethod
+    def __getitem__(self, i: int) -> ChatInstance:
+        """
+        Returns the i-th chat instance.
+        """
+        raise NotImplementedError
+
+    @abstractmethod
+    def require_incremental_response(self) -> bool:
+        """If true, the inputs consist of multiple user utterances and the
+        model should generate responses for each utterance incrementally.
+
+        Otherwise, the model just has to continue the conversation from the last user utterance.
+        """
+        raise NotImplementedError

flexeval-0.3.1/flexeval/core/chat_dataset/chatbot_bench.py

@@ -0,0 +1,81 @@
+from __future__ import annotations
+
+import json
+from os import PathLike
+from pathlib import Path
+
+from .base import ChatDataset, ChatInstance
+
+
+def resolve_file_path_or_name(file_path_or_name: str | PathLike[str]) -> Path:
+    if not Path(file_path_or_name).exists():
+        curated_dataset_path = Path(__file__).parent / "chatbot_bench_datasets" / f"{file_path_or_name}.jsonl"
+        if not curated_dataset_path.exists():
+            msg = f"Unknown dataset path or name: {file_path_or_name}"
+            raise ValueError(msg)
+        file_path = curated_dataset_path
+    else:
+        file_path = file_path_or_name
+    return file_path
+
+
+class ChatbotBench(ChatDataset):
+    """This class loads data with the jsonl format used in chat evaluation benchmarks such as
+    MT-Bench (Multi-turn Benchmark) or Vicuna QA Benchmark.
+
+    Example of a line from a jsonl file:
+        {
+          "question_id": 00,
+          "category": "writing",
+          "turns": [
+            "Compose an engaging travel blog post about a recent trip to Hawaii.",
+            "Rewrite your previous response. Start every sentence with the letter A."
+          ]
+        }
+    """
+
+    def __init__(
+        self,
+        file_path_or_name: str,
+        ref_file_path_or_name: str | None = None,
+        need_ref_categories: list[str] | None = None,
+    ) -> None:
+        file_path = resolve_file_path_or_name(file_path_or_name)
+
+        self._id_to_question_id: list[int | str] = []
+        self._id_to_category: list[str] = []
+        self._messages_dict: dict[int | str, list[dict[str, str]]] = {}
+        with open(file_path) as f:
+            for line in f:
+                item = json.loads(line)
+                self._id_to_question_id.append(item["question_id"])
+                self._id_to_category.append(item["category"])
+                self._messages_dict[item["question_id"]] = [{"role": "user", "content": turn} for turn in item["turns"]]
+
+        self._references_dict: dict[int | str, list[str]] = {}
+        if ref_file_path_or_name is not None:
+            ref_file_path = resolve_file_path_or_name(ref_file_path_or_name)
+            with open(ref_file_path) as f:
+                for line in f:
+                    item = json.loads(line)
+                    self._references_dict[item["question_id"]] = item["choices"][0]["turns"]
+
+        self.need_ref_categories = need_ref_categories or [
+            "math",
+            "coding",
+            "reasoning",
+        ]
+
+    def require_incremental_response(self) -> bool:
+        return True
+
+    def __len__(self) -> int:
+        return len(self._id_to_question_id)
+
+    def __getitem__(self, i: int) -> ChatInstance:
+        question_id = self._id_to_question_id[i]
+        category = self._id_to_category[i]
+        references: list[str] = []
+        if category in self.need_ref_categories:
+            references = self._references_dict.get(question_id, [])
+        return ChatInstance(self._messages_dict[question_id], references=references, extra_info={"category": category})

flexeval-0.3.1/flexeval/core/chat_dataset/chatbot_bench_datasets/README.md

@@ -0,0 +1,13 @@
+# Chatbot Bench Datasets
+
+The files under this directory are curated from the following sources.
+
+- `mt-ja.jsonl`: https://raw.githubusercontent.com/Stability-AI/FastChat/jp-stable/fastchat/llm_judge/data/japanese_mt_bench/question_full.jsonl
+- `mt-ja-ref-gpt4.jsonl`: https://raw.githubusercontent.com/Stability-AI/FastChat/jp-stable/fastchat/llm_judge/data/japanese_mt_bench/reference_answer/gpt-4.jsonl
+- `mt-en.jsonl`: https://raw.githubusercontent.com/lm-sys/FastChat/main/fastchat/llm_judge/data/mt_bench/question.jsonl
+- `mt-en-ref-gpt4.jsonl`: https://raw.githubusercontent.com/lm-sys/FastChat/main/fastchat/llm_judge/data/mt_bench/reference_answer/gpt-4.jsonl
+- `vicuna-ja`: https://raw.githubusercontent.com/ku-nlp/ja-vicuna-qa-benchmark/main/data/jp_bench/question.jsonl
+- `vicuna-ja-ref-gpt4.jsonl`: https://raw.githubusercontent.com/ku-nlp/ja-vicuna-qa-benchmark/main/data/jp_bench/reference_answer/gpt-4/results.jsonl
+- `vicuna-en`: https://raw.githubusercontent.com/lm-sys/FastChat/main/fastchat/llm_judge/data/vicuna_bench/question.jsonl
+- `vicuna-en-ref-gpt4.jsonl`: https://raw.githubusercontent.com/lm-sys/FastChat/main/fastchat/llm_judge/data/vicuna_bench/reference_answer/gpt-4.jsonl
+- `rakuda-v2-ja.jsonl`: https://raw.githubusercontent.com/yuzu-ai/japanese-llm-ranking/fae1ee79c69b0c3acf8e8a1994e43c7952e7bd9c/jrank/data/rakuda_v2/questions.jsonl