Update README.md (ShishirPatil#320)

This PR updates the discord link in the README.md to make it never expires and has no max-user limit. It also adds the date field to the change log. This PR **does not** change the leaderboard score.
vinaybagade · Apr 6, 2024 · 033435c · 033435c
1 parent a8fb9ad
commit 033435c
Show file tree

Hide file tree

Showing 3 changed files with 9 additions and 9 deletions.
diff --git a/README.md b/README.md
@@ -19,7 +19,7 @@
 
 **:newspaper_roll: Checkout our paper!** [![arXiv](https://img.shields.io/badge/arXiv-2305.15334-<COLOR>.svg?style=flat-square)](https://arxiv.org/abs/2305.15334)
 
-**:wave: Join our Discord!** [![Discord](https://img.shields.io/discord/1111172801899012102?label=Discord&logo=discord&logoColor=green&style=flat-square)](https://discord.gg/SwTyuTAxX3)
+**:wave: Join our Discord!** [![Discord](https://img.shields.io/discord/1111172801899012102?label=Discord&logo=discord&logoColor=green&style=flat-square)](https://discord.gg/grXXvj9Whz)
 
 
 `Gorilla` enables LLMs to use tools by invoking APIs. Given a natural language query, Gorilla comes up with the semantically- and syntactically- correct API to invoke. With Gorilla, we are the first to demonstrate how to use LLMs to invoke 1,600+ (and growing) API calls accurately while reducing hallucination. We also release APIBench, the largest collection of APIs, curated and easy to be trained on! Join us, as we try to expand the largest API store and teach LLMs how to write them! Hop on our Discord, or open a PR, or email us if you would like to have your API incorporated as well.

diff --git a/berkeley-function-call-leaderboard/README.md b/berkeley-function-call-leaderboard/README.md
@@ -114,7 +114,7 @@ If you want to run all evaluation at the same time, you can use `all` as the tes
 
 Running proprietary model like GPTs, Claude, Mistral-X will requires an API-Key which can be supplied in `openfunctions_evaluation.py`.
 
-If decided to run OSS model, openfunctions evaluation uses vllm and therefore requires GPU for hosting and inferencing. If you have questions or concerns about evaluating OSS models, please reach out to us in our [discord channel](https://discord.gg/rgyHBXvw).
+If decided to run OSS model, openfunctions evaluation uses vllm and therefore requires GPU for hosting and inferencing. If you have questions or concerns about evaluating OSS models, please reach out to us in our [discord channel](https://discord.gg/grXXvj9Whz).
 
 
 
@@ -217,11 +217,11 @@ For inferencing `Databrick-DBRX-instruct`, you need to create a Databrick Azure
 
 
 ## Changelog
-* [#309](https://github.com/ShishirPatil/gorilla/pull/309) Bug fix for evaluation dataset possible answers. Implement **string standardization** for the AST evaluation pipeline, i.e. removing white spaces and a subset of punctuations (`,./-_*^`) to make the AST evaluation more robust and accurate. Fixed AST evaluation issue for type `tuple`. Add 2 new models `meetkai/functionary-small-v2.4 (FC)`, `meetkai/functionary-medium-v2.4 (FC)` to the leaderboard.
-* [#299](https://github.com/ShishirPatil/gorilla/pull/299) Leaderboard April 1 update with new models (`Claude-3-Haiku`, `Databrick-DBRX-Instruct`), more advanced AST evaluation procedure, and updated evaluation datasets. Cost and latency statistics during evaluation are also measured. We also released the manual that our evaluation procedure is based on, available [here](https://gorilla.cs.berkeley.edu/blogs/8_berkeley_function_calling_leaderboard.html#metrics).
-* [#254](https://github.com/ShishirPatil/gorilla/pull/254) Leaderboard update with 3 new models: `Claude-3-Opus-20240229 (Prompt)`, `Claude-3-Sonnet-20240229 (Prompt)`, and `meetkai/functionary-medium-v2.2 (FC)`
-* [#237](https://github.com/ShishirPatil/gorilla/pull/237) and [238](https://github.com/ShishirPatil/gorilla/pull/238) leaderboard update resulting from [#223](https://github.com/ShishirPatil/gorilla/pull/223); 3 new models: `mistral-large-2402`, `gemini-1.0-pro`, and `gemma`.
-* [#223](https://github.com/ShishirPatil/gorilla/pull/223) modifications to REST evaluation. 
+* [April 3, 2024] [#309](https://github.com/ShishirPatil/gorilla/pull/309): Bug fix for evaluation dataset possible answers. Implement **string standardization** for the AST evaluation pipeline, i.e. removing white spaces and a subset of punctuations (`,./-_*^`) to make the AST evaluation more robust and accurate. Fixed AST evaluation issue for type `tuple`. Add 2 new models `meetkai/functionary-small-v2.4 (FC)`, `meetkai/functionary-medium-v2.4 (FC)` to the leaderboard.
+* [April 1, 2024] [#299](https://github.com/ShishirPatil/gorilla/pull/299): Leaderboard update with new models (`Claude-3-Haiku`, `Databrick-DBRX-Instruct`), more advanced AST evaluation procedure, and updated evaluation datasets. Cost and latency statistics during evaluation are also measured. We also released the manual that our evaluation procedure is based on, available [here](https://gorilla.cs.berkeley.edu/blogs/8_berkeley_function_calling_leaderboard.html#metrics).
+* [Mar 11, 2024] [#254](https://github.com/ShishirPatil/gorilla/pull/254): Leaderboard update with 3 new models: `Claude-3-Opus-20240229 (Prompt)`, `Claude-3-Sonnet-20240229 (Prompt)`, and `meetkai/functionary-medium-v2.2 (FC)`
+* [Mar 5, 2024] [#237](https://github.com/ShishirPatil/gorilla/pull/237) and [238](https://github.com/ShishirPatil/gorilla/pull/238): leaderboard update resulting from [#223](https://github.com/ShishirPatil/gorilla/pull/223); 3 new models: `mistral-large-2402`, `gemini-1.0-pro`, and `gemma`.
+* [Feb 29, 2024] [#223](https://github.com/ShishirPatil/gorilla/pull/223): modifications to REST evaluation. 
 
 
 ## Contributing
@@ -237,7 +237,7 @@ To add new model to the Function Calling Leaderboard, here are a few things you
 3. Modify `model_handler/handler_map.py`. This mapping contains key as the exact model name and value as the handler object of the specific model. 
 4. If your model is price based, please update the pricing detail, i.e. price per million tokens under `eval_runner_helper.py`
 5. Raise a [Pull Request](https://github.com/ShishirPatil/gorilla/pulls) with your new Model Handler. We will run the model handler if an endpoint is established. If self-hosting is required and the model size is large, we might not be able to accommodate model hosting therefore an OpenAI compatible endpoint for evaluation is desired. 
-6. Feel Free to join [Gorilla Discord Leaderboard Channel](https://discord.gg/rgyHBXvw) and reach out to us for any questions or concerns in adding new models. We are happy to help you!
+6. Feel Free to join [Gorilla Discord](https://discord.gg/grXXvj9Whz) `#leaderboard` and reach out to us for any questions or concerns in adding new models. We are happy to help you!
 
 
 All the leaderboard statistics, and data used to train the models is released under Apache 2.0.

diff --git a/raft/sample_data/blog.txt b/raft/sample_data/blog.txt
@@ -241,7 +241,7 @@ CoT Answer: ##Reason: The document ##begin_quote## The Oberoi family is an India
 </p>
 
 <p>
-                        We hope you enjoyed this blog post. We would love to hear from you on <a href="https://discord.gg/SwTyuTAxX3">Discord</a>, <a href="https://twitter.com/shishirpatil_/status/1661780076277678082">Twitter (#GorillaLLM)</a>, and <a href="https://github.com/ShishirPatil/gorilla/">GitHub</a>.<br> 
+                        We hope you enjoyed this blog post. We would love to hear from you on <a href="https://discord.gg/grXXvj9Whz">Discord</a>, <a href="https://twitter.com/shishirpatil_/status/1661780076277678082">Twitter (#GorillaLLM)</a>, and <a href="https://github.com/ShishirPatil/gorilla/">GitHub</a>.<br> 
                     </p>
                     <!-- <p id="gorilla-bibtex">
                         If you would like to cite Gorilla:<br>