crfm-helm 0.5.2__tar.gz → 0.5.4__tar.gz

{crfm_helm-0.5.2/src/crfm_helm.egg-info → crfm_helm-0.5.4}/PKG-INFO

@@ -1,16 +1,19 @@
 Metadata-Version: 2.1
 Name: crfm-helm
-Version: 0.5.2
+Version: 0.5.4
 Summary: Benchmark for language models
 Home-page: https://github.com/stanford-crfm/helm
 Author: Stanford CRFM
 Author-email: contact-crfm@stanford.edu
 License: Apache License 2.0
 Keywords: language models benchmarking
+Classifier: Programming Language :: Python :: 3
 Classifier: Programming Language :: Python :: 3 :: Only
-Classifier: Programming Language :: Python :: 3.8
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
 Classifier: License :: OSI Approved :: Apache Software License
-Requires-Python: <3.11,>=3.8
+Requires-Python: <3.12,>=3.9
 Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: cattrs~=22.2
@@ -28,8 +31,7 @@ Requires-Dist: bottle~=0.12.23
 Requires-Dist: datasets~=2.17
 Requires-Dist: pyarrow>=11.0.0
 Requires-Dist: pyarrow-hotfix~=0.6
-Requires-Dist: nltk~=3.7
-Requires-Dist: pyext~=0.7
+Requires-Dist: nltk<3.8.2,~=3.7
 Requires-Dist: rouge-score~=0.1.2
 Requires-Dist: scipy~=1.10
 Requires-Dist: uncertainty-calibration~=0.1.4
@@ -37,18 +39,18 @@ Requires-Dist: scikit-learn~=1.1
 Requires-Dist: transformers~=4.40
 Requires-Dist: torch<3.0.0,>=1.13.1
 Requires-Dist: torchvision<3.0.0,>=0.14.1
-Requires-Dist: google-api-python-client~=2.64
 Provides-Extra: proxy-server
-Requires-Dist: gunicorn~=20.1.0; extra == "proxy-server"
+Requires-Dist: gunicorn>=20.1; extra == "proxy-server"
 Provides-Extra: human-evaluation
 Requires-Dist: scaleapi~=2.13.0; extra == "human-evaluation"
 Requires-Dist: surge-api~=1.1.0; extra == "human-evaluation"
 Provides-Extra: scenarios
-Requires-Dist: gdown~=4.4.0; extra == "scenarios"
+Requires-Dist: gdown~=5.1; extra == "scenarios"
 Requires-Dist: sympy~=1.11.1; extra == "scenarios"
 Requires-Dist: xlrd~=2.0.1; extra == "scenarios"
 Provides-Extra: metrics
-Requires-Dist: numba~=0.56.4; extra == "metrics"
+Requires-Dist: google-api-python-client~=2.64; extra == "metrics"
+Requires-Dist: numba~=0.56; extra == "metrics"
 Requires-Dist: pytrec_eval==0.5; extra == "metrics"
 Requires-Dist: sacrebleu~=2.2.1; extra == "metrics"
 Provides-Extra: summarization
@@ -68,12 +70,18 @@ Requires-Dist: jieba==0.42.1; extra == "cleva"
 Requires-Dist: opencc==1.1.6; extra == "cleva"
 Requires-Dist: langdetect==1.0.9; extra == "cleva"
 Provides-Extra: images
-Requires-Dist: accelerate~=0.25.0; extra == "images"
+Requires-Dist: crfm-helm[accelerate]; extra == "images"
 Requires-Dist: pillow~=10.2; extra == "images"
 Provides-Extra: mongo
 Requires-Dist: pymongo~=4.2; extra == "mongo"
 Provides-Extra: unitxt
 Requires-Dist: evaluate~=0.4.1; extra == "unitxt"
+Provides-Extra: bhasa
+Requires-Dist: pythainlp==5.0.0; extra == "bhasa"
+Requires-Dist: pyonmttok==1.37.0; extra == "bhasa"
+Requires-Dist: sacrebleu~=2.2.1; extra == "bhasa"
+Provides-Extra: accelerate
+Requires-Dist: accelerate~=0.25; extra == "accelerate"
 Provides-Extra: aleph-alpha
 Requires-Dist: aleph-alpha-client~=2.14.0; extra == "aleph-alpha"
 Requires-Dist: tokenizers>=0.13.3; extra == "aleph-alpha"
@@ -100,11 +108,11 @@ Provides-Extra: google
 Requires-Dist: google-cloud-aiplatform~=1.48; extra == "google"
 Provides-Extra: together
 Requires-Dist: together~=1.1; extra == "together"
-Provides-Extra: tsinghua
-Requires-Dist: icetk~=0.0.4; extra == "tsinghua"
 Provides-Extra: yandex
 Requires-Dist: sentencepiece~=0.1.97; extra == "yandex"
 Provides-Extra: models
+Requires-Dist: crfm-helm[ai21]; extra == "models"
+Requires-Dist: crfm-helm[accelerate]; extra == "models"
 Requires-Dist: crfm-helm[aleph-alpha]; extra == "models"
 Requires-Dist: crfm-helm[allenai]; extra == "models"
 Requires-Dist: crfm-helm[amazon]; extra == "models"
@@ -115,7 +123,6 @@ Requires-Dist: crfm-helm[mistral]; extra == "models"
 Requires-Dist: crfm-helm[openai]; extra == "models"
 Requires-Dist: crfm-helm[reka]; extra == "models"
 Requires-Dist: crfm-helm[together]; extra == "models"
-Requires-Dist: crfm-helm[tsinghua]; extra == "models"
 Requires-Dist: crfm-helm[yandex]; extra == "models"
 Requires-Dist: crfm-helm[openvino]; extra == "models"
 Provides-Extra: reka
@@ -124,27 +131,28 @@ Provides-Extra: vlm
 Requires-Dist: crfm-helm[openai]; extra == "vlm"
 Requires-Dist: einops~=0.7.0; extra == "vlm"
 Requires-Dist: einops-exts~=0.0.4; extra == "vlm"
-Requires-Dist: open-clip-torch~=2.24.0; extra == "vlm"
-Requires-Dist: torch~=2.1.2; extra == "vlm"
+Requires-Dist: open-clip-torch~=2.24; extra == "vlm"
+Requires-Dist: torch~=2.1; extra == "vlm"
 Requires-Dist: transformers_stream_generator~=0.0.4; extra == "vlm"
 Requires-Dist: scipy~=1.10; extra == "vlm"
 Requires-Dist: torchvision<3.0.0,>=0.14.1; extra == "vlm"
 Requires-Dist: crfm-helm[reka]; extra == "vlm"
 Requires-Dist: crfm-helm[images]; extra == "vlm"
-Requires-Dist: crfm-helm[image2structure]; extra == "vlm"
+Requires-Dist: crfm-helm[image2struct]; extra == "vlm"
 Requires-Dist: pycocoevalcap~=1.2; extra == "vlm"
-Provides-Extra: image2structure
-Requires-Dist: crfm-helm[images]; extra == "image2structure"
-Requires-Dist: latex~=0.7.0; extra == "image2structure"
-Requires-Dist: pdf2image~=1.16.3; extra == "image2structure"
-Requires-Dist: selenium~=4.17.2; extra == "image2structure"
-Requires-Dist: html2text~=2024.2.26; extra == "image2structure"
-Requires-Dist: opencv-python~=4.7.0.68; extra == "image2structure"
-Requires-Dist: lpips~=0.1.4; extra == "image2structure"
-Requires-Dist: imagehash~=4.3.1; extra == "image2structure"
+Provides-Extra: image2struct
+Requires-Dist: crfm-helm[images]; extra == "image2struct"
+Requires-Dist: latex~=0.7.0; extra == "image2struct"
+Requires-Dist: pdf2image~=1.16.3; extra == "image2struct"
+Requires-Dist: selenium~=4.17.2; extra == "image2struct"
+Requires-Dist: html2text~=2024.2.26; extra == "image2struct"
+Requires-Dist: opencv-python~=4.7.0.68; extra == "image2struct"
+Requires-Dist: lpips~=0.1.4; extra == "image2struct"
+Requires-Dist: imagehash~=4.3.1; extra == "image2struct"
 Provides-Extra: heim
-Requires-Dist: gdown~=4.4.0; extra == "heim"
+Requires-Dist: gdown~=5.1; extra == "heim"
 Requires-Dist: diffusers~=0.24.0; extra == "heim"
+Requires-Dist: icetk~=0.0.4; extra == "heim"
 Requires-Dist: jax~=0.4.13; extra == "heim"
 Requires-Dist: jaxlib~=0.4.13; extra == "heim"
 Requires-Dist: crfm-helm[openai]; extra == "heim"
@@ -158,16 +166,17 @@ Requires-Dist: wandb~=0.13.11; extra == "heim"
 Requires-Dist: google-cloud-translate~=3.11.2; extra == "heim"
 Requires-Dist: autokeras~=1.0.20; extra == "heim"
 Requires-Dist: clip-anytorch~=2.5.0; extra == "heim"
-Requires-Dist: google-cloud-storage~=2.9.0; extra == "heim"
+Requires-Dist: google-cloud-storage~=2.9; extra == "heim"
 Requires-Dist: lpips~=0.1.4; extra == "heim"
 Requires-Dist: multilingual-clip~=1.0.10; extra == "heim"
 Requires-Dist: NudeNet~=2.0.9; extra == "heim"
 Requires-Dist: opencv-python~=4.7.0.68; extra == "heim"
 Requires-Dist: pytorch-fid~=0.3.0; extra == "heim"
-Requires-Dist: tensorflow~=2.11.1; extra == "heim"
+Requires-Dist: tensorflow~=2.11; extra == "heim"
 Requires-Dist: timm~=0.6.12; extra == "heim"
 Requires-Dist: torch-fidelity~=0.3.0; extra == "heim"
 Requires-Dist: torchmetrics~=0.11.1; extra == "heim"
+Requires-Dist: scikit-image!=0.23.*,==0.*,>=0.22; extra == "heim"
 Requires-Dist: crfm-helm[images]; extra == "heim"
 Provides-Extra: all
 Requires-Dist: crfm-helm[proxy-server]; extra == "all"
@@ -183,6 +192,7 @@ Requires-Dist: crfm-helm[models]; extra == "all"
 Requires-Dist: crfm-helm[mongo]; extra == "all"
 Requires-Dist: crfm-helm[heim]; extra == "all"
 Requires-Dist: crfm-helm[vlm]; extra == "all"
+Requires-Dist: crfm-helm[bhasa]; extra == "all"
 Provides-Extra: dev
 Requires-Dist: pytest~=7.2.0; extra == "dev"
 Requires-Dist: pre-commit~=2.20.0; extra == "dev"
@@ -209,40 +219,16 @@ Welcome! The **`crfm-helm`** Python package contains code used in the **Holistic
 
 To get started, refer to [the documentation on Read the Docs](https://crfm-helm.readthedocs.io/) for how to install and run the package.
 
-## Directory Structure
+## Papers
 
-The directory structure for this repo is as follows
+This repository contains code used to produce results for the following papers:
 
-```
-├── docs # MD used to generate readthedocs
-│
-├── scripts # Python utility scripts for HELM
-│ ├── cache
-│ ├── data_overlap # Calculate train test overlap
-│ │ ├── common
-│ │ ├── scenarios
-│ │ └── test
-│ ├── efficiency
-│ ├── fact_completion
-│ ├── offline_eval
-│ └── scale
-└── src
-├── helm # Benchmarking Scripts for HELM
-│ │
-│ ├── benchmark # Main Python code for running HELM
-│ │ │
-│ │ └── static # Current JS (Jquery) code for rendering front-end
-│ │ │
-│ │ └── ...
-│ │
-│ ├── common # Additional Python code for running HELM
-│ │
-│ └── proxy # Python code for external web requests
-│
-└── helm-frontend # New React Front-end
-```
+- Holistic Evaluation of Vision-Language Models (VHELM) - paper (TBD), [leaderboard](https://crfm.stanford.edu/helm/vhelm/latest/), [documentation](https://crfm-helm.readthedocs.io/en/latest/vhelm/)
+- Holistic Evaluation of Text-To-Image Models (HEIM) - [paper](https://arxiv.org/abs/2311.04287), [leaderboard](https://crfm.stanford.edu/helm/heim/latest/), [documentation](https://crfm-helm.readthedocs.io/en/latest/heim/)
+
+The HELM Python package can be used to reproduce the published model evaluation results from these paper. To get started, refer to the documentation links above for the corresponding paper, or the [main Reproducing Leaderboards documentation](https://crfm-helm.readthedocs.io/en/latest/reproducing_leaderboards/).
 
-# Holistic Evaluation of Text-To-Image Models
+## Holistic Evaluation of Text-To-Image Models
 
 <img src="https://github.com/stanford-crfm/helm/raw/heim/src/helm/benchmark/static/heim/images/heim-logo.png" alt=""  width="800"/>
 
@@ -275,6 +261,22 @@ demonstrating strengths in different aspects.
 This repository contains the code used to produce the [results on the website](https://crfm.stanford.edu/heim/latest/) 
 and [paper](https://arxiv.org/abs/2311.04287).
 
+## Citation
+
+If you use this software in your research, please cite the [Holistic Evaluation of Language Models paper](https://openreview.net/forum?id=iO4LZibEqW) as below.
+
+```bibtex
+@article{
+liang2023holistic,
+title={Holistic Evaluation of Language Models},
+author={Percy Liang and Rishi Bommasani and Tony Lee and Dimitris Tsipras and Dilara Soylu and Michihiro Yasunaga and Yian Zhang and Deepak Narayanan and Yuhuai Wu and Ananya Kumar and Benjamin Newman and Binhang Yuan and Bobby Yan and Ce Zhang and Christian Alexander Cosgrove and Christopher D Manning and Christopher Re and Diana Acosta-Navas and Drew Arad Hudson and Eric Zelikman and Esin Durmus and Faisal Ladhak and Frieda Rong and Hongyu Ren and Huaxiu Yao and Jue WANG and Keshav Santhanam and Laurel Orr and Lucia Zheng and Mert Yuksekgonul and Mirac Suzgun and Nathan Kim and Neel Guha and Niladri S. Chatterji and Omar Khattab and Peter Henderson and Qian Huang and Ryan Andrew Chi and Sang Michael Xie and Shibani Santurkar and Surya Ganguli and Tatsunori Hashimoto and Thomas Icard and Tianyi Zhang and Vishrav Chaudhary and William Wang and Xuechen Li and Yifan Mai and Yuhui Zhang and Yuta Koreeda},
+journal={Transactions on Machine Learning Research},
+issn={2835-8856},
+year={2023},
+url={https://openreview.net/forum?id=iO4LZibEqW},
+note={Featured Certification, Expert Certification}
+}
+```
 # Tutorial
 
 This tutorial will explain how to use the HELM command line tools to run benchmarks, aggregate statistics, and visualize results.
@@ -285,34 +287,26 @@ We will run two runs using the `mmlu` scenario on the `openai/gpt2` model. The `
 
 `helm-run` is a command line tool for running benchmarks.
 
-To run this benchmark using the HELM command-line tools, we need to specify **run spec descriptions** that describes the desired runs. For this example, the run spec descriptions are `mmlu:subject=anatomy,model=openai/gpt2` (for anatomy) and `mmlu:subject=philosophy,model=openai/gpt2` (for philosophy).
-
-Next, we need to create a **run spec configuration file** containing these run spec descriptions. A run spec configuration file is a text file containing `RunEntries` serialized to JSON, where each entry in `RunEntries` contains a run spec description. The `description` field of each entry should be a **run spec description**. Create a text file named `run_entries.conf` with the following contents:
-
-```
-entries: [
-  {description: "mmlu:subject=anatomy,model=openai/gpt2", priority: 1},
-  {description: "mmlu:subject=philosophy,model=openai/gpt2", priority: 1},
-]
-```
+To run this benchmark using the HELM command-line tools, we need to specify **run entries** that describes the desired runs. For this example, the run entries are `mmlu:subject=anatomy,model=openai/gpt2` (for anatomy) and `mmlu:subject=philosophy,model=openai/gpt2` (for philosophy).
 
-We will now use `helm-run` to execute the runs that have been specified in this run spec configuration file. Run this command:
+We will now use `helm-run` to execute the runs. Run this command:
 
-```
-helm-run --conf-paths run_entries.conf --suite v1 --max-eval-instances 10
+```sh
+helm-run --run-entries mmlu:subject=anatomy,model=openai/gpt2 mmlu:subject=philosophy,model=openai/gpt2 --suite my-suite --max-eval-instances 10
 ```
 
-The meaning of the additional arguments are as follows:
+The meaning of the arguments are as follows:
 
+- `--run-entries` specifies the run entries from the desired runs.
 - `--suite` specifies a subdirectory under the output directory in which all the output will be placed.
-- `--max-eval-instances` limits evaluation to only the first *N* inputs (i.e. instances) from the benchmark.
+- `--max-eval-instances` limits evaluation to only *N* instances (i.e. items) from the benchmark, using a randomly shuffled order of instances.
 
 `helm-run` creates an environment directory environment and an output directory by default.
 
 -  The environment directory is `prod_env/` by default and can be set using `--local-path`. Credentials for making API calls should be added to a `credentials.conf` file in this directory.
 -  The output directory is `benchmark_output/` by default and can be set using `--output-path`.
 
-After running this command, navigate to the `benchmark_output/runs/v1/` directory. This should contain a two sub-directories named `mmlu:subject=anatomy,model=openai_gpt2` and `mmlu:subject=philosophy,model=openai_gpt2`. Note that the names of these sub-directories is based on the run spec descriptions we used earlier, but with `/` replaced with `_`.
+After running this command, navigate to the `benchmark_output/runs/my-suite/` directory. This should contain a two sub-directories named `mmlu:subject=anatomy,model=openai_gpt2` and `mmlu:subject=philosophy,model=openai_gpt2`. Note that the names of these sub-directories is based on the run entries we used earlier, but with `/` replaced with `_`.
 
 Each output sub-directory will contain several JSON files that were generated during the corresponding run:
 
@@ -322,60 +316,35 @@ Each output sub-directory will contain several JSON files that were generated du
 - `per_instance_stats.json` contains a serialized list of `PerInstanceStats`, which contains the statistics produced for the metrics for each instance (i.e. input).
 - `stats.json` contains a serialized list of `PerInstanceStats`, which contains the statistics produced for the metrics, aggregated across all instances (i.e. inputs).
 
-`helm-run` provides additional arguments that can be used to filter out `--models-to-run`, `--groups-to-run` and `--priority`. It can be convenient to create a large `run_entries.conf` file containing every run spec description of interest, and then use these flags to filter down the RunSpecs to actually run. As an example, the main `run_specs.conf` file used for the HELM benchmarking paper can be found [here](https://github.com/stanford-crfm/helm/blob/main/src/helm/benchmark/presentation/run_specs.conf).
-
-**Using model or model_deployment:** Some models have several deployments (for exmaple `eleutherai/gpt-j-6b` is deployed under `huggingface/gpt-j-6b`, `gooseai/gpt-j-6b` and `together/gpt-j-6b`). Since the results can differ depending on the deployment, we provide a way to specify the deployment instead of the model. Instead of using `model=eleutherai/gpt-g-6b`, use `model_deployment=huggingface/gpt-j-6b`. If you do not, a deployment will be arbitrarily chosen. This can still be used for models that have a single deployment and is a good practice to follow to avoid any ambiguity.
-
 ## Using `helm-summarize`
 
 The `helm-summarize` reads the output files of `helm-run` and computes aggregate statistics across runs. Run the following:
 
-```
-helm-summarize --suite v1
+```sh
+helm-summarize --suite my-suite
 ```
 
-This reads the pre-existing files in `benchmark_output/runs/v1/` that were written by `helm-run` previously, and writes the following new files back to `benchmark_output/runs/v1/`:
+This reads the pre-existing files in `benchmark_output/runs/my-suite/` that were written by `helm-run` previously, and writes the following new files back to `benchmark_output/runs/my-suite/`:
 
 - `summary.json` contains a serialized `ExecutiveSummary` with a date and suite name.
-- `run_specs.json` contains the run spec descriptions for all the runs.
+- `run_specs.json` contains the run entries for all the runs.
 - `runs.json` contains serialized list of `Run`, which contains the run path, run spec and adapter spec and statistics for each run.
 - `groups.json` contains a serialized list of `Table`, each containing information about groups in a group category.
 - `groups_metadata.json` contains a list of all the groups along with a human-readable description and a taxonomy.
 
-Additionally, for each group and group-relavent metric, it will output a pair of files: `benchmark_output/runs/v1/groups/latex/<group_name>_<metric_name>.tex` and `benchmark_output/runs/v1/groups/json/<group_name>_<metric_name>.json`. These files contain the statistics for that metric from each run within the group.
-
-<!--
-# TODO(#1441): Enable plots
-
-## Using `helm-create-plots`
-
-The `helm-create-plots` reads the `groups` directory created by `helm-summarize` and creates plots, equivalent to those use in the HELM paper. Run the following:
-
-```
-helm-create-plots --suite v1
-```
-
-This reads the pre-existing files in `benchmark_output/runs/v1/groups` that were written by `helm-summarize` previously,
-and creates plots (`.png` or `.pdf`) at `benchmark_output/runs/v1/plots`.
-
--->
+Additionally, for each group and group-relavent metric, it will output a pair of files: `benchmark_output/runs/my-suite/groups/latex/<group_name>_<metric_name>.tex` and `benchmark_output/runs/my-suite/groups/json/<group_name>_<metric_name>.json`. These files contain the statistics for that metric from each run within the group.
 
 ## Using `helm-server`
 
 Finally, the `helm-server` command launches a web server to visualize the output files of `helm-run` and `helm-benchmark`. Run:
 
+```sh
+helm-server --suite my-suite
 ```
-helm-server
-```
-
-Open a browser and go to http://localhost:8000/ to view the visualization. You should see a similar view as [live website for the paper](https://crfm.stanford.edu/helm/v1.0/), but for the data from your benchmark runs. The website has three main sections:
-
-- **Models** contains a list of available models.
-- **Scenarios** contains a list of available scenarios.
-- **Results** contains results from the runs, organized into groups and categories of groups.
-- **Raw Runs** contains a searchable list of runs.
 
-## Other Tips
+Open a browser and go to http://localhost:8000/ to view the visualization. You should see a similar view as [live website for the paper](https://crfm.stanford.edu/helm/classic/latest/), but for the data from your benchmark runs. The website has the following sections accessible from the top menu bar:
 
-- The suite name can be used as a versioning mechanism to separate runs using different versions of scenarios or models.
-- Tools such as [`jq`](https://stedolan.github.io/jq/) are useful for examining the JSON output files on the command line.
+- **Leaderboards** contains the leaderboards with aggregate metrics.
+- **Models** contains a list of models and their descriptions
+- **Scenarios** contains a list of scenarios and their descriptions.
+- **Predictions** contains a searchable list of runs.

{crfm_helm-0.5.2 → crfm_helm-0.5.4}/README.md

@@ -17,40 +17,16 @@ Welcome! The **`crfm-helm`** Python package contains code used in the **Holistic
 
 To get started, refer to [the documentation on Read the Docs](https://crfm-helm.readthedocs.io/) for how to install and run the package.
 
-## Directory Structure
-
-The directory structure for this repo is as follows
-
-```
-├── docs # MD used to generate readthedocs
-│
-├── scripts # Python utility scripts for HELM
-│ ├── cache
-│ ├── data_overlap # Calculate train test overlap
-│ │ ├── common
-│ │ ├── scenarios
-│ │ └── test
-│ ├── efficiency
-│ ├── fact_completion
-│ ├── offline_eval
-│ └── scale
-└── src
-├── helm # Benchmarking Scripts for HELM
-│ │
-│ ├── benchmark # Main Python code for running HELM
-│ │ │
-│ │ └── static # Current JS (Jquery) code for rendering front-end
-│ │ │
-│ │ └── ...
-│ │
-│ ├── common # Additional Python code for running HELM
-│ │
-│ └── proxy # Python code for external web requests
-│
-└── helm-frontend # New React Front-end
-```
-
-# Holistic Evaluation of Text-To-Image Models
+## Papers
+
+This repository contains code used to produce results for the following papers:
+
+- Holistic Evaluation of Vision-Language Models (VHELM) - paper (TBD), [leaderboard](https://crfm.stanford.edu/helm/vhelm/latest/), [documentation](https://crfm-helm.readthedocs.io/en/latest/vhelm/)
+- Holistic Evaluation of Text-To-Image Models (HEIM) - [paper](https://arxiv.org/abs/2311.04287), [leaderboard](https://crfm.stanford.edu/helm/heim/latest/), [documentation](https://crfm-helm.readthedocs.io/en/latest/heim/)
+
+The HELM Python package can be used to reproduce the published model evaluation results from these paper. To get started, refer to the documentation links above for the corresponding paper, or the [main Reproducing Leaderboards documentation](https://crfm-helm.readthedocs.io/en/latest/reproducing_leaderboards/).
+
+## Holistic Evaluation of Text-To-Image Models
 
 <img src="https://github.com/stanford-crfm/helm/raw/heim/src/helm/benchmark/static/heim/images/heim-logo.png" alt=""  width="800"/>
 
@@ -82,3 +58,20 @@ demonstrating strengths in different aspects.
 
 This repository contains the code used to produce the [results on the website](https://crfm.stanford.edu/heim/latest/) 
 and [paper](https://arxiv.org/abs/2311.04287).
+
+## Citation
+
+If you use this software in your research, please cite the [Holistic Evaluation of Language Models paper](https://openreview.net/forum?id=iO4LZibEqW) as below.
+
+```bibtex
+@article{
+liang2023holistic,
+title={Holistic Evaluation of Language Models},
+author={Percy Liang and Rishi Bommasani and Tony Lee and Dimitris Tsipras and Dilara Soylu and Michihiro Yasunaga and Yian Zhang and Deepak Narayanan and Yuhuai Wu and Ananya Kumar and Benjamin Newman and Binhang Yuan and Bobby Yan and Ce Zhang and Christian Alexander Cosgrove and Christopher D Manning and Christopher Re and Diana Acosta-Navas and Drew Arad Hudson and Eric Zelikman and Esin Durmus and Faisal Ladhak and Frieda Rong and Hongyu Ren and Huaxiu Yao and Jue WANG and Keshav Santhanam and Laurel Orr and Lucia Zheng and Mert Yuksekgonul and Mirac Suzgun and Nathan Kim and Neel Guha and Niladri S. Chatterji and Omar Khattab and Peter Henderson and Qian Huang and Ryan Andrew Chi and Sang Michael Xie and Shibani Santurkar and Surya Ganguli and Tatsunori Hashimoto and Thomas Icard and Tianyi Zhang and Vishrav Chaudhary and William Wang and Xuechen Li and Yifan Mai and Yuhui Zhang and Yuta Koreeda},
+journal={Transactions on Machine Learning Research},
+issn={2835-8856},
+year={2023},
+url={https://openreview.net/forum?id=iO4LZibEqW},
+note={Featured Certification, Expert Certification}
+}
+```

crfm_helm-0.5.4/docs/tutorial.md

@@ -0,0 +1,71 @@
+# Tutorial
+
+This tutorial will explain how to use the HELM command line tools to run benchmarks, aggregate statistics, and visualize results.
+
+We will run two runs using the `mmlu` scenario on the `openai/gpt2` model. The `mmlu` scenario implements the **Massive Multitask Language (MMLU)** benchmark from [this paper](https://arxiv.org/pdf/2009.03300.pdf), and consists of a Question Answering (QA) task using a dataset with questions from 57 subjects such as elementary mathematics, US history, computer science, law, and more. Note that GPT-2 performs poorly on MMLU, so this is just a proof of concept. We will run two runs: the first using questions about anatomy, and the second using questions about philosophy.
+
+## Using `helm-run`
+
+`helm-run` is a command line tool for running benchmarks.
+
+To run this benchmark using the HELM command-line tools, we need to specify **run entries** that describes the desired runs. For this example, the run entries are `mmlu:subject=anatomy,model=openai/gpt2` (for anatomy) and `mmlu:subject=philosophy,model=openai/gpt2` (for philosophy).
+
+We will now use `helm-run` to execute the runs. Run this command:
+
+```sh
+helm-run --run-entries mmlu:subject=anatomy,model=openai/gpt2 mmlu:subject=philosophy,model=openai/gpt2 --suite my-suite --max-eval-instances 10
+```
+
+The meaning of the arguments are as follows:
+
+- `--run-entries` specifies the run entries from the desired runs.
+- `--suite` specifies a subdirectory under the output directory in which all the output will be placed.
+- `--max-eval-instances` limits evaluation to only *N* instances (i.e. items) from the benchmark, using a randomly shuffled order of instances.
+
+`helm-run` creates an environment directory environment and an output directory by default.
+
+-  The environment directory is `prod_env/` by default and can be set using `--local-path`. Credentials for making API calls should be added to a `credentials.conf` file in this directory.
+-  The output directory is `benchmark_output/` by default and can be set using `--output-path`.
+
+After running this command, navigate to the `benchmark_output/runs/my-suite/` directory. This should contain a two sub-directories named `mmlu:subject=anatomy,model=openai_gpt2` and `mmlu:subject=philosophy,model=openai_gpt2`. Note that the names of these sub-directories is based on the run entries we used earlier, but with `/` replaced with `_`.
+
+Each output sub-directory will contain several JSON files that were generated during the corresponding run:
+
+- `run_spec.json` contains the `RunSpec`, which specifies the scenario, adapter and metrics for the run.
+- `scenario.json` contains a serialized `Scenario`, which contains the scenario for the run and specifies the instances (i.e. inputs) used.
+- `scenario_state.json` contains a serialized `ScenarioState`, which contains every request to and response from the model.
+- `per_instance_stats.json` contains a serialized list of `PerInstanceStats`, which contains the statistics produced for the metrics for each instance (i.e. input).
+- `stats.json` contains a serialized list of `PerInstanceStats`, which contains the statistics produced for the metrics, aggregated across all instances (i.e. inputs).
+
+## Using `helm-summarize`
+
+The `helm-summarize` reads the output files of `helm-run` and computes aggregate statistics across runs. Run the following:
+
+```sh
+helm-summarize --suite my-suite
+```
+
+This reads the pre-existing files in `benchmark_output/runs/my-suite/` that were written by `helm-run` previously, and writes the following new files back to `benchmark_output/runs/my-suite/`:
+
+- `summary.json` contains a serialized `ExecutiveSummary` with a date and suite name.
+- `run_specs.json` contains the run entries for all the runs.
+- `runs.json` contains serialized list of `Run`, which contains the run path, run spec and adapter spec and statistics for each run.
+- `groups.json` contains a serialized list of `Table`, each containing information about groups in a group category.
+- `groups_metadata.json` contains a list of all the groups along with a human-readable description and a taxonomy.
+
+Additionally, for each group and group-relavent metric, it will output a pair of files: `benchmark_output/runs/my-suite/groups/latex/<group_name>_<metric_name>.tex` and `benchmark_output/runs/my-suite/groups/json/<group_name>_<metric_name>.json`. These files contain the statistics for that metric from each run within the group.
+
+## Using `helm-server`
+
+Finally, the `helm-server` command launches a web server to visualize the output files of `helm-run` and `helm-benchmark`. Run:
+
+```sh
+helm-server --suite my-suite
+```
+
+Open a browser and go to http://localhost:8000/ to view the visualization. You should see a similar view as [live website for the paper](https://crfm.stanford.edu/helm/classic/latest/), but for the data from your benchmark runs. The website has the following sections accessible from the top menu bar:
+
+- **Leaderboards** contains the leaderboards with aggregate metrics.
+- **Models** contains a list of models and their descriptions
+- **Scenarios** contains a list of scenarios and their descriptions.
+- **Predictions** contains a searchable list of runs.