Skip to content

Commit

Permalink
release
Browse files Browse the repository at this point in the history
  • Loading branch information
@infwinston
infwinston committed Mar 31, 2024
0 parents commit 7f1b7f5
Show file tree
Hide file tree
Showing 14 changed files with 1,727 additions and 0 deletions.
1 change: 1 addition & 0 deletions .gitignore
Original file line number Diff line number Diff line change
@@ -0,0 +1 @@
data/arena-hard-v0.1/model_answer/
201 changes: 201 additions & 0 deletions LICENSE
Original file line number Diff line number Diff line change
@@ -0,0 +1,201 @@
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.
96 changes: 96 additions & 0 deletions README.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,96 @@
# Arena-Hard

Arena-Hard is an evaluation tool for instruction-tuned LLMs. It contains 500 challenging user queries. We prompt GPT-4-Turbo as judge to compare the models' responses against a baseline model (default: GPT-4-0314).

Check out our blog post for more details.

## Install Dependencies
```
git clone https://github.com/lm-sys/arena-hard.git
cd arena-hard
pip install -r requirements.txt
pip install -r requirements-optional.txt # Optional dependencies (e.g., anthropic sdk)
```

## Review pre-generated results:
We pre-generate many popular models answer and judgment. You can review them by:
```console
> python show_result.py

gpt-4-0125-preview | win-rate: 77.74 | average #tokens: 618
claude-3-opus-20240229 | win-rate: 60.36 | average #tokens: 539
gemini-1.5-pro | win-rate: 53.59 | average #tokens: 475
claude-3-sonnet-20240229 | win-rate: 47.24 | average #tokens: 553
claude-3-haiku-20240307 | win-rate: 41.47 | average #tokens: 504
gpt-4-0613 | win-rate: 37.9 | average #tokens: 354
mistral-large-2402 | win-rate: 37.77 | average #tokens: 399
Qwen1.5-72B-Chat | win-rate: 36.08 | average #tokens: 473
mistral-medium | win-rate: 32.94 | average #tokens: 492
gpt-3.5-turbo-0613 | win-rate: 25.14 | average #tokens: 403
```

## Evaluate a new model on Arena-hard-v0.1:

### Step 1. Set up the endpoint config to your model

Fill in your API endpoint in `config/api_config.yaml`. We support OpenAI compatible API server. You can specify `parallel` to indicate the number of concurrent API requests (default: 1).
```yaml
# example
gpt-3.5-turbo-0125:
model_name: gpt-3.5-turbo-0125
endpoints: null
api_type: openai
parallel: 8

[YOUR-MODEL-NAME]:
model_name: [YOUR-MODEL-NAME]
endpoints:
- api_base: [YOUR-ENDPOINT-URL]
api_key: [YOUR-API-KEY]
api_type: openai
parallel: 8
```
You may use inference engine such as [vLLM](https://docs.vllm.ai/en/latest/serving/openai_compatible_server.html) or [SGLang](https://github.com/sgl-project/sglang?tab=readme-ov-file#using-local-models) to host your model with an OpenAI compatible API server.
### Step 2. Generate Model Answers
In `config/gen_answer_config.yaml`, add your model name in `model_list`.
```yaml
bench_name: arena-hard-v0.1
temperature: 0.0
max_tokens: 4096
num_choices: 1
model_list:
- [YOUR-MODEL-NAME]
```
Run the command to generate answers:
```console
python gen_answer.py
```

### Step 3. Generate Judgments

In `config/judge_config.yaml`, add your model name in `model_list`.
```yaml
...
# Add your model below for evaluation
model_list:
- gpt-3.5-turbo-0125
- [YOUR-MODEL-NAME]
```

Run the command to generate judgments:
```console
python gen_judgment.py
```

### Step 4. Show result
Output model win rates. Optionally, use `--full-stats` for detailed results.
```console
> python show_result.py
```


## Citation
27 changes: 27 additions & 0 deletions config/api_config.yaml
Original file line number Diff line number Diff line change
@@ -0,0 +1,27 @@
# name: str
# model_name: str
# endpoints: default to null
# - api_base: str
# api_key: str
# api_version: str optional (only for azure)
# api_type: str
# tokenizer: str optional (to optimize token limits)
# parallel: int

gpt-3.5-turbo-0125:
model_name: gpt-3.5-turbo-0125
endpoints: null
api_type: openai
parallel: 8

gpt-4-0314:
model_name: gpt-4-0314
endpoints: null
api_type: openai
parallel: 8

gpt-4-1106-preview:
model_name: gpt-4-1106-preview
endpoints: null
api_type: openai
parallel: 8
11 changes: 11 additions & 0 deletions config/gen_answer_config.yaml
Original file line number Diff line number Diff line change
@@ -0,0 +1,11 @@
name: config of answer generation for arena-hard-v0.1

bench_name: arena-hard-v0.1

temperature: 0.0
max_tokens: 4096
num_choices: 1

# a list of model to generate answers
model_list:
- gpt-3.5-turbo-0125
25 changes: 25 additions & 0 deletions config/judge_config.yaml
Original file line number Diff line number Diff line change
@@ -0,0 +1,25 @@
name: judgment config file for Arena Hard

bench_name: arena-hard-v0.1

# Arena Hard default
judge_model: gpt-4-1106-preview
reference: False # Optional
ref_model: null

baseline: True
baseline_model: gpt-4-0314

pairwise: True
temperature: 0
max_tokens: 4096

regex_pattern: \[\[([AB<>=]+)\]\]

system_prompt: "Please act as an impartial judge and evaluate the quality of the responses provided by two AI assistants to the user prompt displayed below. You will be given assistant A's answer and assistant B's answer. Your job is to evaluate which assistant's answer is better.\n\nBegin your evaluation by generating your own answer to the prompt. You must provide your answers before judging any answers.\n\nWhen evaluating the assistants' answers, compare both assistants' answers with your answer. You must identify and correct any mistakes or inaccurate information.\n\nThen consider if the assistant's answers are helpful, relevant, and concise. Helpful means the answer correctly responds to the prompt or follows the instructions. Note when user prompt has any ambiguity or more than one interpretation, it is more helpful and appropriate to ask for clarifications or more information from the user than providing an answer based on assumptions. Relevant means all parts of the response closely connect or are appropriate to what is being asked. Concise means the response is clear and not verbose or excessive.\n\nThen consider the creativity and novelty of the assistant's answers when needed. Finally, identify any missing important information in the assistants' answers that would be beneficial to include when responding to the user prompt.\n\nAfter providing your explanation, you must output only one of the following choices as your final verdict with a label:\n\n1. Assistant A is significantly better: [[A>>B]]\n2. Assistant A is slightly better: [[A>B]]\n3. Tie, relatively the same: [[A=B]]\n4. Assistant B is slightly better: [[B>A]]\n5. Assistant B is significantly better: [[B>>A]]\n\nExample output: \"My final verdict is tie: [[A=B]]\"."

prompt_template: ["<|User Prompt|>\n{question_1}\n\n<|The Start of Assistant A's Answer|>\n{answer_1}\n<|The End of Assistant A's Answer|>\n\n<|The Start of Assistant B's Answer|>\n{answer_2}\n<|The End of Assistant B's Answer|>"]

# Add your model below for evaluation
model_list:
- gpt-3.5-turbo-0125
Loading

0 comments on commit 7f1b7f5

Please sign in to comment.