feat(ci): automatic release semver + git archival installation

.git_archival.txt

@@ -0,0 +1,4 @@
+node: $Format:%H$
+node-date: $Format:%cI$
+describe-name: $Format:%(describe:tags=true,match=*[0-9]*)$
+ref-names: $Format:%D$

.gitattributes

@@ -3,3 +3,5 @@ nightly-requirements-gpu.txt linguist-generated=true
 tests/models/__snapshots__/* linguist-generated=true
 typings/**/*.pyi linguist-generated=true
 * text=auto eol=lf
+# Needed for setuptools-scm-git-archive
+.git_archival.txt  export-subst

.github/actions/release.sh

@@ -13,7 +13,7 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-set -ex
+set -e
 
 # Function to print script usage
 print_usage() {
@@ -61,41 +61,43 @@ fi
 release_package() {
     local version="$1"
     echo "Releasing version ${version}..."
-
     jq --arg release_version "${version}" '.version = $release_version' < package.json > package.json.tmp && mv package.json.tmp package.json
-
-    if [[ $release == 'patch' ]]; then
-        hatch version "${version}"
-    fi
-
     towncrier build --yes --version "${version}"
-    git add CHANGELOG.md changelog.d src/openllm/__about__.py package.json
+    git add CHANGELOG.md changelog.d package.json
     git commit -S -sm "infra: prepare for release ${version} [generated] [skip ci]"
     git push origin main
-
     echo "Releasing tag ${version}..." && git tag -a "v${version}" -sm "Release ${version} [generated by GitHub Actions]"
     git push origin "v${version}"
-
     echo "Finish releasing version ${version}"
 }
 
-echo "Cleaning previously built artifacts..." && hatch clean
+#get highest tags across all branches, not just the current branch
+version="$(git describe --tags "$(git rev-list --tags --max-count=1)")"
+VERSION="${version#v}"
+# Save the current value of IFS to restore it later
+OLD_IFS=$IFS
+IFS='.'
+# split into array
+read -ra VERSION_BITS <<< "$VERSION"
+# Restore the original value of IFS
+IFS=$OLD_IFS
+VNUM1=${VERSION_BITS[0]}
+VNUM2=${VERSION_BITS[1]}
+VNUM3=${VERSION_BITS[2]}
 
 if [[ $release == 'major' ]]; then
-    hatch version major
-    CURRENT_VERSION=$(hatch version)
-    release_package "${CURRENT_VERSION}"
+    VNUM1=$((VNUM1+1))
+    VNUM2=0
+    VNUM3=0
 elif [[ $release == 'minor' ]]; then
-    hatch version minor
-    CURRENT_VERSION="$(hatch version)"
-    release_package "${CURRENT_VERSION}"
+    VNUM2=$((VNUM2+1))
+    VNUM3=0
 else
-    CURRENT_VERSION=$(hatch version)
-
-    if [[ "$CURRENT_VERSION" =~ \.dev ]]; then
-        release_package "${CURRENT_VERSION%%.dev*}"
-    else
-        echo "Current version is not properly setup as dev version. Aborting..."
-        exit 1
-    fi
+    VNUM3=$((VNUM3+1))
 fi
+
+echo "Commit count: $(git rev-list --count HEAD)"
+
+#create new tag
+RELEASE_VERSION="$VNUM1.$VNUM2.$VNUM3"
+release_package "${RELEASE_VERSION}"

.github/workflows/create-releases.yml

@@ -90,8 +90,11 @@ jobs:
         run: python -m build
       - name: Publish to PyPI
         uses: pypa/gh-action-pypi-publish@release/v1
+        with:
+          print-hash: true
   prepare-next-dev-cycle:
     needs:
+      - release
       - publish-python
       - binary-distribution
     runs-on: ubuntu-latest
@@ -126,16 +129,27 @@ jobs:
           GIT_COMMITTER_EMAIL: ${{ steps.import-gpg-key.outputs.email }}
         run: |
           git pull --autostash --no-edit --gpg-sign --ff origin main
-          echo "Bumping version to dev..." && hatch version patch && hatch version dev
-          jq --arg release_version "$(hatch version)" '.version = $release_version' < package.json > package.json.tmp && mv package.json.tmp package.json
-          git add src/openllm/__about__.py package.json && git commit -S -sm "infra: bump to dev version of $(hatch version) [generated] [skip ci]"
+          SEMVER="${{ needs.release.outputs.version }}"
+          OLD_IFS=$IFS
+          IFS='.'
+          read -ra VERSION_BITS <<< "$SEMVER"
+          IFS=$OLD_IFS
+          VNUM1=${VERSION_BITS[0]}
+          VNUM2=${VERSION_BITS[1]}
+          VNUM3=${VERSION_BITS[2]}
+          VNUM3=$((VNUM3+1))
+          DEV_VERSION="$VNUM1.$VNUM2.$VNUM3.dev0"
+          echo "Bumping version to ${DEV_VERSION}..."
+          jq --arg release_version "${DEV_VERSION}" '.version = $release_version' < package.json > package.json.tmp && mv package.json.tmp package.json
+          git add package.json && git commit -S -sm "infra: bump to dev version of ${DEV_VERSION} [generated] [skip ci]"
           git push origin HEAD:main
   binary-distribution:
     if: github.repository_owner == 'bentoml'
     needs: release
     name: Create binary/wheels distribution
     uses: bentoml/OpenLLM/.github/workflows/binary-releases.yml@main
   release-notes:
+    if: github.repository_owner == 'bentoml'
     needs:
       - release
       - publish-python

.gitignore

@@ -141,3 +141,4 @@ pyapp
 /target
 
 .pdm-python
+/src/openllm/_version.py

README.md

@@ -3,14 +3,22 @@
 <div align="center">
     <h1 align="center">🦾 OpenLLM</h1>
     <a href="https://pypi.org/project/openllm">
-        <img src="https://img.shields.io/pypi/v/openllm.svg" alt="pypi_status" />
+        <img src="https://img.shields.io/pypi/v/openllm.svg?logo=pypi&label=PyPI&logoColor=gold" alt="pypi_status" />
     </a><a href="https://github.com/bentoml/OpenLLM/actions/workflows/ci.yml">
         <img src="https://github.com/bentoml/OpenLLM/actions/workflows/ci.yml/badge.svg?branch=main" alt="ci" />
     </a><a href="https://twitter.com/bentomlai">
         <img src="https://badgen.net/badge/icon/@bentomlai/1DA1F2?icon=twitter&label=Follow%20Us" alt="Twitter" />
     </a><a href="https://l.bentoml.com/join-openllm-discord">
         <img src="https://badgen.net/badge/icon/OpenLLM/7289da?icon=discord&label=Join%20Us" alt="Discord" />
     </a><br>
+    </a><a href="https://pypi.org/project/openllm">
+        <img src="https://img.shields.io/pypi/pyversions/openllm.svg?logo=python&label=Python&logoColor=gold" alt="python_version" />
+    </a><a href="https://github.com/pypa/hatch">
+        <img src="https://img.shields.io/badge/%F0%9F%A5%9A-Hatch-4051b5.svg" alt="Hatch" />
+    </a><br>
+    </a><a href="https://github.com/astral-sh/ruff">
+        <img src="https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/charliermarsh/ruff/main/assets/badge/v2.json" alt="Ruff" />
+    </a><br>
     <p>An open platform for operating large language models (LLMs) in production.</br>
     Fine-tune, serve, deploy, and monitor any LLMs with ease.</p>
     <i></i>
@@ -39,10 +47,14 @@ Images or deploy as serverless endpoint via
 🤖️ **Bring your own LLM**: Fine-tune any LLM to suit your needs with
 `LLM.tuning()`. (Coming soon)
 
+<!-- hatch-fancy-pypi-readme intro stop -->
+
 ![Gif showing OpenLLM Intro](/assets/output.gif)
 <br/>
 
-## 🏃‍ Getting Started
+<!-- hatch-fancy-pypi-readme interim start -->
+
+## 🏃 Getting Started
 
 To use OpenLLM, you need to have Python 3.8 (or newer) and `pip` installed on
 your system. We highly recommend using a Virtual Environment to prevent package
@@ -105,13 +117,18 @@ openllm query 'Explain to me the difference between "further" and "farther"'
 
 Visit `http://localhost:3000/docs.json` for OpenLLM's API specification.
 
+OpenLLM seamlessly supports many models and different variants of models.
 Users can also specify different variants of the model to be served, by
 providing the `--model-id` argument, e.g.:
 
 ```bash
 openllm start flan-t5 --model-id google/flan-t5-large
 ```
 
+> **Note** that `openllm` also supports all variants of fine-tuning weights, custom model path
+> as well as quantized weights for any of the supported models as long as it can be loaded with
+> the model architecture. Refer to [supported models](https://github.com/bentoml/OpenLLM/tree/main#-supported-models) section for models' architecture.
+
 Use the `openllm models` command to see the list of models and their variants
 supported in OpenLLM.
 
@@ -127,17 +144,13 @@ dependencies can be installed with the instructions below:
 <tr>
 <th>Model</th>
 <th>Architecture</th>
-<th>CPU</th>
-<th>GPU</th>
 <th>Model Ids</th>
 <th>Installation</th>
 </tr>
 <tr>
 
 <td><a href=https://github.com/THUDM/ChatGLM-6B>chatglm</a></td>
 <td><a href=https://github.com/THUDM/ChatGLM-6B><code>ChatGLMForConditionalGeneration</code></a></td>
-<td>❌</td>
-<td>✅</td>
 <td>
 
 <ul><li><a href=https://huggingface.co/thudm/chatglm-6b><code>thudm/chatglm-6b</code></a></li>
@@ -159,8 +172,6 @@ pip install "openllm[chatglm]"
 
 <td><a href=https://github.com/databrickslabs/dolly>dolly-v2</a></td>
 <td><a href=https://huggingface.co/docs/transformers/main/model_doc/gpt_neox#transformers.GPTNeoXForCausalLM><code>GPTNeoXForCausalLM</code></a></td>
-<td>✅</td>
-<td>✅</td>
 <td>
 
 <ul><li><a href=https://huggingface.co/databricks/dolly-v2-3b><code>databricks/dolly-v2-3b</code></a></li>
@@ -180,8 +191,6 @@ pip install openllm
 
 <td><a href=https://falconllm.tii.ae/>falcon</a></td>
 <td><a href=https://falconllm.tii.ae/><code>FalconForCausalLM</code></a></td>
-<td>❌</td>
-<td>✅</td>
 <td>
 
 <ul><li><a href=https://huggingface.co/tiiuae/falcon-7b><code>tiiuae/falcon-7b</code></a></li>
@@ -202,8 +211,6 @@ pip install "openllm[falcon]"
 
 <td><a href=https://huggingface.co/docs/transformers/model_doc/flan-t5>flan-t5</a></td>
 <td><a href=https://huggingface.co/docs/transformers/main/model_doc/t5#transformers.T5ForConditionalGeneration><code>T5ForConditionalGeneration</code></a></td>
-<td>✅</td>
-<td>✅</td>
 <td>
 
 <ul><li><a href=https://huggingface.co/google/flan-t5-small><code>google/flan-t5-small</code></a></li>
@@ -225,8 +232,6 @@ pip install "openllm[flan-t5]"
 
 <td><a href=https://github.com/EleutherAI/gpt-neox>gpt-neox</a></td>
 <td><a href=https://huggingface.co/docs/transformers/main/model_doc/gpt_neox#transformers.GPTNeoXForCausalLM><code>GPTNeoXForCausalLM</code></a></td>
-<td>❌</td>
-<td>✅</td>
 <td>
 
 <ul><li><a href=https://huggingface.co/eleutherai/gpt-neox-20b><code>eleutherai/gpt-neox-20b</code></a></li></ul>
@@ -244,8 +249,6 @@ pip install openllm
 
 <td><a href=https://github.com/facebookresearch/llama>llama</a></td>
 <td><a href=https://huggingface.co/docs/transformers/main/model_doc/llama#transformers.LlamaForCausalLM><code>LlamaForCausalLM</code></a></td>
-<td>✅</td>
-<td>✅</td>
 <td>
 
 <ul><li><a href=https://huggingface.co/meta-llama/llama-2-70b-chat-hf><code>meta-llama/llama-2-70b-chat-hf</code></a></li>
@@ -275,8 +278,6 @@ pip install "openllm[llama]"
 
 <td><a href=https://huggingface.co/mosaicml>mpt</a></td>
 <td><a href=https://huggingface.co/mosaicml><code>MPTForCausalLM</code></a></td>
-<td>✅</td>
-<td>✅</td>
 <td>
 
 <ul><li><a href=https://huggingface.co/mosaicml/mpt-7b><code>mosaicml/mpt-7b</code></a></li>
@@ -300,8 +301,6 @@ pip install "openllm[mpt]"
 
 <td><a href=https://huggingface.co/docs/transformers/model_doc/opt>opt</a></td>
 <td><a href=https://huggingface.co/docs/transformers/main/model_doc/opt#transformers.OPTForCausalLM><code>OPTForCausalLM</code></a></td>
-<td>✅</td>
-<td>✅</td>
 <td>
 
 <ul><li><a href=https://huggingface.co/facebook/opt-125m><code>facebook/opt-125m</code></a></li>
@@ -324,8 +323,6 @@ pip install "openllm[opt]"
 
 <td><a href=https://github.com/Stability-AI/StableLM>stablelm</a></td>
 <td><a href=https://huggingface.co/docs/transformers/main/model_doc/gpt_neox#transformers.GPTNeoXForCausalLM><code>GPTNeoXForCausalLM</code></a></td>
-<td>✅</td>
-<td>✅</td>
 <td>
 
 <ul><li><a href=https://huggingface.co/stabilityai/stablelm-tuned-alpha-3b><code>stabilityai/stablelm-tuned-alpha-3b</code></a></li>
@@ -346,8 +343,6 @@ pip install openllm
 
 <td><a href=https://github.com/bigcode-project/starcoder>starcoder</a></td>
 <td><a href=https://huggingface.co/docs/transformers/main/model_doc/gpt_bigcode#transformers.GPTBigCodeForCausalLM><code>GPTBigCodeForCausalLM</code></a></td>
-<td>❌</td>
-<td>✅</td>
 <td>
 
 <ul><li><a href=https://huggingface.co/bigcode/starcoder><code>bigcode/starcoder</code></a></li>
@@ -366,8 +361,6 @@ pip install "openllm[starcoder]"
 
 <td><a href=https://github.com/baichuan-inc/Baichuan-7B>baichuan</a></td>
 <td><a href=https://github.com/baichuan-inc/Baichuan-7B><code>BaiChuanForCausalLM</code></a></td>
-<td>❌</td>
-<td>✅</td>
 <td>
 
 <ul><li><a href=https://huggingface.co/baichuan-inc/baichuan-7b><code>baichuan-inc/baichuan-7b</code></a></li>
@@ -596,9 +589,12 @@ client.ask_agent(
 )
 ```
 
+<!-- hatch-fancy-pypi-readme interim stop -->
+
 ![Gif showing Agent integration](/assets/agent.gif)
 <br/>
 
+<!-- hatch-fancy-pypi-readme meta start -->
 
 ## 🚀 Deploying to Production
 
@@ -664,7 +660,6 @@ the serverless cloud for shipping and scaling AI applications.
    [deployment instructions](https://docs.bentoml.com/en/latest/reference/cli.html#bentoml-deployment-create).
 
 
-
 ## 👥 Community
 
 Engage with like-minded individuals passionate about LLMs, AI, and more on our

changelog.d/143.feature.md

@@ -0,0 +1,5 @@
+Added installing with git-archival support
+
+```bash
+pip install "https://github.com/bentoml/openllm/archive/main.tar.gz"
+```