mirror of https://github.com/microsoft/semantic-kernel.git synced 2026-10-12 02:19:06 +00:00

T

dependabot[bot]andEvan Mattson d3e1105871 Python: Bump transformers from 4.41.2 to 4.42.4 in /python (#7275 )

Bumps [transformers](https://github.com/huggingface/transformers) from
4.41.2 to 4.42.4.
<details>
<summary>Release notes</summary>
<p><em>Sourced from <a
href="https://github.com/huggingface/transformers/releases">transformers's
releases</a>.</em></p>
<blockquote>
<h2>Patch release v4.42.4</h2>
<h1>Mostly gemma2 support FA2 softcapping!</h1>
<p>but also fix the sliding window for long context and other typos.</p>
<ul>
<li>[Gemma2] Support FA2 softcapping (<a
href="https://redirect.github.com/huggingface/transformers/issues/31887">#31887</a>)
by <a
href="https://github.com/ArthurZucker"><code>@ArthurZucker</code></a></li>
<li>[ConvertSlow] make sure the order is preserved for addedtokens (<a
href="https://redirect.github.com/huggingface/transformers/issues/31902">#31902</a>)
by <a
href="https://github.com/ArthurZucker"><code>@ArthurZucker</code></a></li>
<li>Fixes to alternating SWA layers in Gemma2 (<a
href="https://redirect.github.com/huggingface/transformers/issues/31775">#31775</a>)
by <a
href="https://github.com/turboderp"><code>@turboderp</code></a></li>
<li>Requires for torch.tensor before casting (<a
href="https://redirect.github.com/huggingface/transformers/issues/31755">#31755</a>)
by <a
href="https://github.com/echarlaix"><code>@echarlaix</code></a></li>
</ul>
<p>Was off last week could not get this out, thanks all for your
patience 🥳</p>
<h2>Patch release v4.42.3</h2>
<h1>Make sure we have attention softcapping for &quot;eager&quot; GEMMA2
model</h1>
<p>After experimenting, we noticed that for the 27b model mostly,
softcapping is a must. So adding it back (it should have been there, but
an error on my side made it disappear) sorry all! 😭</p>
<ul>
<li>Gemma capping is a must for big models (<a
href="https://redirect.github.com/huggingface/transformers/issues/31698">#31698</a>)</li>
</ul>
<h2>Patch release v4.42.2</h2>
<h1>Patch release</h1>
<p>Thanks to our 2 contributors for their prompt fixing mostly applies
for training and FA2!</p>
<ul>
<li>Fix Gemma2 4d attention mask (<a
href="https://redirect.github.com/huggingface/transformers/issues/31674">#31674</a>)
by <a href="https://github.com/hiyouga"><code>@hiyouga</code></a></li>
<li>don't zero out the attention_mask when using sliding window with
flash attention (<a
href="https://redirect.github.com/huggingface/transformers/issues/31670">#31670</a>)
by <a
href="https://github.com/winglian"><code>@winglian</code></a></li>
</ul>
<h2>v4.42.1: Patch release</h2>
<p>Patch release for commit:</p>
<ul>
<li>[HybridCache] Fix get_seq_length method (<a
href="https://redirect.github.com/huggingface/transformers/issues/31661">#31661</a>)</li>
</ul>
<h2>v4.42.0: Gemma 2, RTDETR, InstructBLIP, LLAVa Next, New Model
Adder</h2>
<h2>New model additions</h2>
<h3>Gemma-2</h3>
<p>The Gemma2 model was proposed in <a
href="https://blog.google/technology/developers/Gemma2-open-models/">Gemma2:
Open Models Based on Gemini Technology and Research</a> by Gemma2 Team,
Google.
Gemma2 models are trained on 6T tokens, and released with 2 versions, 2b
and 7b.</p>
<p>The abstract from the paper is the following:</p>
<p><em>This work introduces Gemma2, a new family of open language models
demonstrating strong performance across academic benchmarks for language
understanding, reasoning, and safety. We release two sizes of models (2
billion and 7 billion parameters), and provide both pretrained and
fine-tuned checkpoints. Gemma2 outperforms similarly sized open models
on 11 out of 18 text-based tasks, and we present comprehensive
evaluations of safety and responsibility aspects of the models,
alongside a detailed description of our model development. We believe
the responsible release of LLMs is critical for improving the safety of
frontier models, and for enabling the next wave of LLM
innovations</em></p>
<p><img
src="https://github.com/huggingface/transformers/assets/30755778/798b25f4-485a-4b60-abe5-af612def209b"
alt="image" /></p>
<ul>
<li>Add gemma 2 by <a
href="https://github.com/ArthurZucker"><code>@ArthurZucker</code></a>
in <a
href="https://redirect.github.com/huggingface/transformers/issues/31659">#31659</a></li>
</ul>
<h3>RTDETR</h3>
<!-- raw HTML omitted -->
</blockquote>
<p>... (truncated)</p>
</details>
<details>
<summary>Commits</summary>
<ul>
<li><a
href="https://github.com/huggingface/transformers/commit/fc35907f95459d7a6c5281dfadd680b6f7b620e3"><code>fc35907</code></a>
v4.42.4</li>
<li><a
href="https://github.com/huggingface/transformers/commit/e002fcd8edc5ee24d9ac71c6790b129fdd94982b"><code>e002fcd</code></a>
[<code>Gemma2</code>] Support FA2 softcapping (<a
href="https://redirect.github.com/huggingface/transformers/issues/31887">#31887</a>)</li>
<li><a
href="https://github.com/huggingface/transformers/commit/2e434169e7b052420be4d5b2aa1d9c8da6ebe3e7"><code>2e43416</code></a>
[<code>ConvertSlow</code>] make sure the order is preserved for
addedtokens (<a
href="https://redirect.github.com/huggingface/transformers/issues/31902">#31902</a>)</li>
<li><a
href="https://github.com/huggingface/transformers/commit/c43fd9d159f7480e62d02f1966ce83385cebea59"><code>c43fd9d</code></a>
Fixes to alternating SWA layers in Gemma2 (<a
href="https://redirect.github.com/huggingface/transformers/issues/31775">#31775</a>)</li>
<li><a
href="https://github.com/huggingface/transformers/commit/0be998bc7f9393c1672a7ff93fbccd15d5c39f3c"><code>0be998b</code></a>
Requires for torch.tensor before casting (<a
href="https://redirect.github.com/huggingface/transformers/issues/31755">#31755</a>)</li>
<li><a
href="https://github.com/huggingface/transformers/commit/b7ee1e80b912c6cdd93b54dd77af061fde151d28"><code>b7ee1e8</code></a>
v4.42.3</li>
<li><a
href="https://github.com/huggingface/transformers/commit/da50b41a272724dba0821d643a44dfebb23e3786"><code>da50b41</code></a>
Gemma capping is a must for big models (<a
href="https://redirect.github.com/huggingface/transformers/issues/31698">#31698</a>)</li>
<li><a
href="https://github.com/huggingface/transformers/commit/086c74efdf98b4e64ac40863ce190144316873a5"><code>086c74e</code></a>
v4.42.2</li>
<li><a
href="https://github.com/huggingface/transformers/commit/869186743da66563d07ea8ea81ebfc88bbf5139c"><code>8691867</code></a>
Fix Gemma2 4d attention mask (<a
href="https://redirect.github.com/huggingface/transformers/issues/31674">#31674</a>)</li>
<li><a
href="https://github.com/huggingface/transformers/commit/7edc9931c52d9de22d2c569122dfc3d927fd280e"><code>7edc993</code></a>
don't zero out the attention_mask when using sliding window with flash
attent...</li>
<li>Additional commits viewable in <a
href="https://github.com/huggingface/transformers/compare/v4.41.2...v4.42.4">compare
view</a></li>
</ul>
</details>
<br />


[![Dependabot compatibility
score](https://dependabot-badges.githubapp.com/badges/compatibility_score?dependency-name=transformers&package-manager=pip&previous-version=4.41.2&new-version=4.42.4)](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)

Dependabot will resolve any conflicts with this PR as long as you don't
alter it yourself. You can also trigger a rebase manually by commenting
`@dependabot rebase`.

[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)

---

<details>
<summary>Dependabot commands and options</summary>
<br />

You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits
that have been made to it
- `@dependabot merge` will merge this PR after your CI passes on it
- `@dependabot squash and merge` will squash and merge this PR after
your CI passes on it
- `@dependabot cancel merge` will cancel a previously requested merge
and block automerging
- `@dependabot reopen` will reopen this PR if it is closed
- `@dependabot close` will close this PR and stop Dependabot recreating
it. You can achieve the same result by closing it manually
- `@dependabot show <dependency name> ignore conditions` will show all
of the ignore conditions of the specified dependency
- `@dependabot ignore this major version` will close this PR and stop
Dependabot creating any more for this major version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this minor version` will close this PR and stop
Dependabot creating any more for this minor version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this dependency` will close this PR and stop
Dependabot creating any more for this dependency (unless you reopen the
PR or upgrade to it yourself)


</details>

Signed-off-by: dependabot[bot] <[email protected]>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Evan Mattson <[email protected]>

2024-07-18 20:51:31 +00:00

.devcontainer

Change version of .Net in dev container to 8 so it can run Polyglot n… (#4201 )

2023-12-12 19:16:24 +00:00

.github

Python: Migrate to Ollama Python SDK (#7165 )

2024-07-16 22:38:21 +00:00

.vscode

.Net: Update Concepts README for new Prompt samples (#6173 )

2024-05-09 19:14:15 +00:00

docs

ADR Bug - Fixed typo in ADR (#7113 )

2024-07-05 17:38:50 +00:00

dotnet

.Net: Added example of Plan generation and execution using Auto Function Calling (#7046 )

2024-07-17 16:38:24 +00:00

java

Java: Bump com.azure:azure-identity from 1.9.1 to 1.12.2 in /java/samples/semantickernel-demos/semantickernel-spring-starter (#7234 )

2024-07-12 12:56:55 +00:00

prompt_template_samples

Python: Restructure samples into new folders to make things more clear. (#6116 )

2024-05-04 11:50:04 +00:00

python

Python: Bump transformers from 4.41.2 to 4.42.4 in /python (#7275 )

2024-07-18 20:51:31 +00:00

.editorconfig

Merge remote-tracking branch 'upstream/main' into java-development

2024-05-29 18:37:35 +01:00

.gitattributes

.Net: Fix build batch to align with Bash script (#2813 )

2023-09-15 11:49:02 +00:00

.gitignore

Merge remote-tracking branch 'upstream/main' into merge-all-2

2024-02-13 14:17:49 +00:00

.pre-commit-config.yaml

Python: Bump ruff to 0.5.1 (#7180 )

2024-07-10 07:17:53 +00:00

CODE_OF_CONDUCT.md

First commit, let the journey begin!

2023-02-24 16:38:23 -08:00

COMMUNITY.md

community office hours (#5840 )

2024-04-11 17:21:23 +00:00

CONTRIBUTING.md

Update CONTRIBUTING.md (#2503 )

2023-09-04 19:55:35 +00:00

FEATURE_MATRIX.md

Create pointers to learn.microsoft.com (#2159 )

2023-07-25 22:41:13 +00:00

LICENSE

First commit, let the journey begin!

2023-02-24 16:38:23 -08:00

README.md

.Net: Filters graduation (#7004 )

2024-07-08 15:08:17 +00:00

SECURITY.md

Fix broken links (#4930 )

2024-02-08 15:38:18 +00:00

README.md

Semantic Kernel

Status

Python
.NET
Java

Overview

Semantic Kernel is an SDK that integrates Large Language Models (LLMs) like OpenAI, Azure OpenAI, and Hugging Face with conventional programming languages like C#, Python, and Java. Semantic Kernel achieves this by allowing you to define plugins that can be chained together in just a few lines of code.

What makes Semantic Kernel special, however, is its ability to automatically orchestrate plugins with AI. With Semantic Kernel planners, you can ask an LLM to generate a plan that achieves a user's unique goal. Afterwards, Semantic Kernel will execute the plan for the user.

Please star the repo to show your support for this project!

Getting started with Semantic Kernel

The Semantic Kernel SDK is available in C#, Python, and Java. To get started, choose your preferred language below. See the Feature Matrix to see a breakdown of feature parity between our currently supported languages.

Using Semantic Kernel in C#

Using Semantic Kernel in Python

Using Semantic Kernel in Java

The quickest way to get started with the basics is to get an API key from either OpenAI or Azure OpenAI and to run one of the C#, Python, and Java console applications/scripts below.

For C#:

Create a new console app.
Add the semantic kernel nuget Microsoft.SemanticKernel.
Copy the code from here into the app Program.cs file.
Replace the configuration placeholders for API key and other params with your key and settings.
Run with F5 or dotnet run

For Python:

Install the pip package: python -m pip install semantic-kernel.
Create a new script e.g. hello-world.py.
Store your API key and settings in an .env file as described here.
Copy the code from here into the hello-world.py script.
Run the python script.

For Java:

Clone the repository: git clone https://github.com/microsoft/semantic-kernel.git
1. To access the latest Java code, clone and checkout the Java development branch: git clone -b java-development https://github.com/microsoft/semantic-kernel.git
Follow the instructions here

Learning how to use Semantic Kernel

The fastest way to learn how to use Semantic Kernel is with our C# and Python Jupyter notebooks. These notebooks demonstrate how to use Semantic Kernel with code snippets that you can run with a push of a button.

Once you've finished the getting started notebooks, you can then check out the main walkthroughs on our Learn site. Each sample comes with a completed C# and Python project that you can run locally.

Finally, refer to our API references for more details on the C# and Python APIs:

C# API reference
Python API reference (coming soon)
Java API reference (coming soon)

Join the community

We welcome your contributions and suggestions to SK community! One of the easiest ways to participate is to engage in discussions in the GitHub repository. Bug reports and fixes are welcome!

For new features, components, or extensions, please open an issue and discuss with us before sending a PR. This is to avoid rejection as we might be taking the core in a different direction, but also to consider the impact on the larger ecosystem.

To learn more and get started:

Read the documentation
Learn how to contribute to the project
Join the Discord community
Attend regular office hours and SK community events
Follow the team on our blog

Contributor Wall of Fame

Code of Conduct

This project has adopted the Microsoft Open Source Code of Conduct. For more information see the Code of Conduct FAQ or contact [email protected] with any additional questions or comments.

License

Licensed under the MIT license.