llama-cpp-python 0.2.65__tar.gz → 0.2.66__tar.gz

llama_cpp_python-0.2.66/.git/FETCH_HEAD

@@ -0,0 +1 @@
+26c7876ba0b31bd0e9f7bfc8f341b8b5b3d81fa7		'26c7876ba0b31bd0e9f7bfc8f341b8b5b3d81fa7' of https://github.com/abetlen/llama-cpp-python

llama_cpp_python-0.2.66/.git/HEAD

@@ -0,0 +1 @@
+26c7876ba0b31bd0e9f7bfc8f341b8b5b3d81fa7

{llama_cpp_python-0.2.65 → llama_cpp_python-0.2.66}/.git/config

@@ -9,7 +9,7 @@
 [gc]
 	auto = 0
 [http "https://github.com/"]
-	extraheader = AUTHORIZATION: basic eC1hY2Nlc3MtdG9rZW46Z2hzX1RkWU05UXN2QXJkejl6bWowd2tvdzhxSjBuVlMzeDRjcHgxSg==
+	extraheader = AUTHORIZATION: basic eC1hY2Nlc3MtdG9rZW46Z2hzXzF1VE5jaENjUk8yTTdveXZBUThTZWMxWnNmVktyRzMzdnBWZw==
 [submodule "vendor/llama.cpp"]
 	active = true
 	url = https://github.com/ggerganov/llama.cpp.git

llama_cpp_python-0.2.66/.git/config.worktree

@@ -0,0 +1,5 @@
+[core]
+	sparseCheckout = false
+	sparseCheckoutCone = false
+[index]
+	sparse = false

llama_cpp_python-0.2.66/.git/logs/HEAD

@@ -0,0 +1 @@
+0000000000000000000000000000000000000000 26c7876ba0b31bd0e9f7bfc8f341b8b5b3d81fa7 runner <runner@fv-az1542-362.uwdtf5zkgycefedjt5dtsy0pzd.bx.internal.cloudapp.net> 1714456184 +0000	checkout: moving from master to refs/tags/v0.2.66

llama_cpp_python-0.2.66/.git/modules/vendor/llama.cpp/HEAD

@@ -0,0 +1 @@
+8843a98c2ba97a25e93319a104f9ddfaf83ce4c4

{llama_cpp_python-0.2.65 → llama_cpp_python-0.2.66}/.git/modules/vendor/llama.cpp/config

@@ -16,7 +16,7 @@
 [gc]
 	auto = 0
 [http "https://github.com/"]
-	extraheader = AUTHORIZATION: basic eC1hY2Nlc3MtdG9rZW46Z2hzX1RkWU05UXN2QXJkejl6bWowd2tvdzhxSjBuVlMzeDRjcHgxSg==
+	extraheader = AUTHORIZATION: basic eC1hY2Nlc3MtdG9rZW46Z2hzXzF1VE5jaENjUk8yTTdveXZBUThTZWMxWnNmVktyRzMzdnBWZw==
 [url "https://github.com/"]
 	insteadOf = git@github.com:
 	insteadOf = org-6826477@github.com:

llama_cpp_python-0.2.66/.git/modules/vendor/llama.cpp/logs/HEAD

@@ -0,0 +1,2 @@
+0000000000000000000000000000000000000000 8843a98c2ba97a25e93319a104f9ddfaf83ce4c4 runner <runner@fv-az1542-362.uwdtf5zkgycefedjt5dtsy0pzd.bx.internal.cloudapp.net> 1714456185 +0000	clone: from https://github.com/ggerganov/llama.cpp.git
+8843a98c2ba97a25e93319a104f9ddfaf83ce4c4 8843a98c2ba97a25e93319a104f9ddfaf83ce4c4 runner <runner@fv-az1542-362.uwdtf5zkgycefedjt5dtsy0pzd.bx.internal.cloudapp.net> 1714456185 +0000	checkout: moving from master to 8843a98c2ba97a25e93319a104f9ddfaf83ce4c4

llama_cpp_python-0.2.66/.git/modules/vendor/llama.cpp/logs/refs/heads/master

@@ -0,0 +1 @@
+0000000000000000000000000000000000000000 8843a98c2ba97a25e93319a104f9ddfaf83ce4c4 runner <runner@fv-az1542-362.uwdtf5zkgycefedjt5dtsy0pzd.bx.internal.cloudapp.net> 1714456185 +0000	clone: from https://github.com/ggerganov/llama.cpp.git

llama_cpp_python-0.2.66/.git/modules/vendor/llama.cpp/logs/refs/remotes/origin/HEAD

@@ -0,0 +1 @@
+0000000000000000000000000000000000000000 8843a98c2ba97a25e93319a104f9ddfaf83ce4c4 runner <runner@fv-az1542-362.uwdtf5zkgycefedjt5dtsy0pzd.bx.internal.cloudapp.net> 1714456185 +0000	clone: from https://github.com/ggerganov/llama.cpp.git

{llama_cpp_python-0.2.65 → llama_cpp_python-0.2.66}/.git/modules/vendor/llama.cpp/modules/kompute/config

@@ -13,7 +13,7 @@
 [gc]
 	auto = 0
 [http "https://github.com/"]
-	extraheader = AUTHORIZATION: basic eC1hY2Nlc3MtdG9rZW46Z2hzX1RkWU05UXN2QXJkejl6bWowd2tvdzhxSjBuVlMzeDRjcHgxSg==
+	extraheader = AUTHORIZATION: basic eC1hY2Nlc3MtdG9rZW46Z2hzXzF1VE5jaENjUk8yTTdveXZBUThTZWMxWnNmVktyRzMzdnBWZw==
 [url "https://github.com/"]
 	insteadOf = git@github.com:
 	insteadOf = org-6826477@github.com:

llama_cpp_python-0.2.66/.git/modules/vendor/llama.cpp/modules/kompute/logs/HEAD

@@ -0,0 +1,2 @@
+0000000000000000000000000000000000000000 d1e3b0953cf66acc94b2e29693e221427b2c1f3f runner <runner@fv-az1542-362.uwdtf5zkgycefedjt5dtsy0pzd.bx.internal.cloudapp.net> 1714456185 +0000	clone: from https://github.com/nomic-ai/kompute.git
+d1e3b0953cf66acc94b2e29693e221427b2c1f3f 4565194ed7c32d1d2efa32ceab4d3c6cae006306 runner <runner@fv-az1542-362.uwdtf5zkgycefedjt5dtsy0pzd.bx.internal.cloudapp.net> 1714456186 +0000	checkout: moving from master to 4565194ed7c32d1d2efa32ceab4d3c6cae006306

llama_cpp_python-0.2.66/.git/modules/vendor/llama.cpp/modules/kompute/logs/refs/heads/master

@@ -0,0 +1 @@
+0000000000000000000000000000000000000000 d1e3b0953cf66acc94b2e29693e221427b2c1f3f runner <runner@fv-az1542-362.uwdtf5zkgycefedjt5dtsy0pzd.bx.internal.cloudapp.net> 1714456185 +0000	clone: from https://github.com/nomic-ai/kompute.git

llama_cpp_python-0.2.66/.git/modules/vendor/llama.cpp/modules/kompute/logs/refs/remotes/origin/HEAD

@@ -0,0 +1 @@
+0000000000000000000000000000000000000000 d1e3b0953cf66acc94b2e29693e221427b2c1f3f runner <runner@fv-az1542-362.uwdtf5zkgycefedjt5dtsy0pzd.bx.internal.cloudapp.net> 1714456185 +0000	clone: from https://github.com/nomic-ai/kompute.git

llama_cpp_python-0.2.66/.git/modules/vendor/llama.cpp/packed-refs

@@ -0,0 +1,2 @@
+# pack-refs with: peeled fully-peeled sorted 
+8843a98c2ba97a25e93319a104f9ddfaf83ce4c4 refs/remotes/origin/master

llama_cpp_python-0.2.66/.git/modules/vendor/llama.cpp/refs/heads/master

@@ -0,0 +1 @@
+8843a98c2ba97a25e93319a104f9ddfaf83ce4c4

llama_cpp_python-0.2.66/.git/modules/vendor/llama.cpp/refs/tags/b2769

@@ -0,0 +1 @@
+8843a98c2ba97a25e93319a104f9ddfaf83ce4c4

llama_cpp_python-0.2.66/.git/modules/vendor/llama.cpp/shallow

@@ -0,0 +1 @@
+8843a98c2ba97a25e93319a104f9ddfaf83ce4c4

llama_cpp_python-0.2.66/.git/refs/tags/v0.2.66

@@ -0,0 +1 @@
+26c7876ba0b31bd0e9f7bfc8f341b8b5b3d81fa7

llama_cpp_python-0.2.66/.git/shallow

@@ -0,0 +1 @@
+26c7876ba0b31bd0e9f7bfc8f341b8b5b3d81fa7

{llama_cpp_python-0.2.65 → llama_cpp_python-0.2.66}/.github/dependabot.yml

@@ -9,3 +9,7 @@ updates:
     directory: "/" # Location of package manifests
     schedule:
       interval: "weekly"
+  - package-ecosystem: "github-actions"
+    directory: "/"
+    schedule:
+      interval: "weekly"    

{llama_cpp_python-0.2.65 → llama_cpp_python-0.2.66}/.github/workflows/build-and-release.yaml

@@ -14,12 +14,12 @@ jobs:
         os: [ubuntu-20.04, windows-2019, macos-11]
 
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
         with:
           submodules: "recursive"
 
       # Used to host cibuildwheel
-      - uses: actions/setup-python@v3
+      - uses: actions/setup-python@v5
         with:
           python-version: "3.8"
 
@@ -29,7 +29,7 @@ jobs:
           python -m pip install -e .[all]
 
       - name: Build wheels
-        uses: pypa/cibuildwheel@v2.16.5
+        uses: pypa/cibuildwheel@v2.17.0
         env:
           # disable repair
           CIBW_REPAIR_WHEEL_COMMAND: ""
@@ -37,7 +37,7 @@ jobs:
           package-dir: .
           output-dir: wheelhouse
 
-      - uses: actions/upload-artifact@v3
+      - uses: actions/upload-artifact@v4
         with:
           path: ./wheelhouse/*.whl
 
@@ -55,30 +55,29 @@ jobs:
           platforms: linux/arm64
 
       - name: Build wheels
-        uses: pypa/cibuildwheel@v2.16.5
+        uses: pypa/cibuildwheel@v2.17.0
         env:
           CIBW_SKIP: "*musllinux* pp*"
           CIBW_REPAIR_WHEEL_COMMAND: ""
           CIBW_ARCHS: "aarch64"
           CIBW_BUILD: "cp38-* cp39-* cp310-* cp311-* cp312-*"
         with:
-          output-dir: wheelhouse/
+          output-dir: wheelhouse
 
       - name: Upload wheels as artifacts
         uses: actions/upload-artifact@v4
         with:
-          name: wheels-${{ matrix.version }}
-          path: wheelhouse/*.whl
+          path: ./wheelhouse/*.whl
 
   build_sdist:
     name: Build source distribution
     runs-on: ubuntu-latest
 
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
         with:
           submodules: "recursive"
-      - uses: actions/setup-python@v3
+      - uses: actions/setup-python@v5
         with:
           python-version: "3.8"
       - name: Install dependencies
@@ -88,7 +87,7 @@ jobs:
       - name: Build source distribution
         run: |
           python -m build --sdist
-      - uses: actions/upload-artifact@v3
+      - uses: actions/upload-artifact@v4
         with:
           path: ./dist/*.tar.gz
 
@@ -102,8 +101,8 @@ jobs:
         with:
           name: artifact
           path: dist
-      - uses: softprops/action-gh-release@v1
+      - uses: softprops/action-gh-release@v2
         with:
           files: dist/*
         env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

{llama_cpp_python-0.2.65 → llama_cpp_python-0.2.66}/.github/workflows/build-docker.yaml

@@ -12,18 +12,18 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout
-        uses: actions/checkout@v3
+        uses: actions/checkout@v4
         with:
           submodules: "recursive"
 
       - name: Set up QEMU
-        uses: docker/setup-qemu-action@v2
+        uses: docker/setup-qemu-action@v3
 
       - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v2
+        uses: docker/setup-buildx-action@v3
 
       - name: Login to GitHub Container Registry
-        uses: docker/login-action@v2 
+        uses: docker/login-action@v3 
         with:
           registry: ghcr.io
           username: ${{ github.repository_owner }}
@@ -31,7 +31,7 @@ jobs:
 
       - name: Build and push
         id: docker_build
-        uses: docker/build-push-action@v4
+        uses: docker/build-push-action@v5
         with:
           context: .
           file: "docker/simple/Dockerfile"

{llama_cpp_python-0.2.65 → llama_cpp_python-0.2.66}/.github/workflows/build-wheels-cuda.yaml

@@ -22,7 +22,7 @@ jobs:
           $matrix = @{
               'os' = @('ubuntu-20.04', 'windows-latest')
               'pyver' = @("3.10", "3.11", "3.12")
-              'cuda' = @("12.1.1", "12.2.2", "12.3.2")
+              'cuda' = @("12.1.1", "12.2.2", "12.3.2", "12.4.1")
               'releasetag' = @("basic")
           }
 
@@ -47,12 +47,12 @@ jobs:
         with:
           submodules: "recursive"
 
-      - uses: actions/setup-python@v4
+      - uses: actions/setup-python@v5
         with:
           python-version: ${{ matrix.pyver }}
 
       - name: Setup Mamba
-        uses: conda-incubator/setup-miniconda@v2.2.0
+        uses: conda-incubator/setup-miniconda@v3.0.4
         with:
           activate-environment: "build"
           python-version: ${{ matrix.pyver }}
@@ -65,7 +65,7 @@ jobs:
       - name: VS Integration Cache
         id: vs-integration-cache
         if: runner.os == 'Windows'
-        uses: actions/cache@v3.3.2
+        uses: actions/cache@v4.0.2
         with:
           path: ./MSBuildExtensions
           key: cuda-${{ matrix.cuda }}-vs-integration
@@ -74,7 +74,7 @@ jobs:
         if: runner.os == 'Windows' && steps.vs-integration-cache.outputs.cache-hit != 'true'
         run: |
           if ($env:CUDAVER -eq '12.1.1') {$x = '12.1.0'} else {$x = $env:CUDAVER}
-          $links = (Invoke-RestMethod 'https://github.com/Jimver/cuda-toolkit/raw/dc0ca7bb29c5a92f7a963d3d5c93f8d59765136a/src/links/windows-links.ts').Trim().split().where({$_ -ne ''})
+          $links = (Invoke-RestMethod 'https://raw.githubusercontent.com/Jimver/cuda-toolkit/master/src/links/windows-links.ts').Trim().split().where({$_ -ne ''})
           for ($i=$q=0;$i -lt $links.count -and $q -lt 2;$i++) {if ($links[$i] -eq "'$x',") {$q++}}
           Invoke-RestMethod $links[$i].Trim("'") -OutFile 'cudainstaller.zip'
           & 'C:\Program Files\7-Zip\7z.exe' e cudainstaller.zip -oMSBuildExtensions -r *\MSBuildExtensions\* > $null
@@ -122,7 +122,7 @@ jobs:
           # write the build tag to the output
           Write-Output "CUDA_VERSION=$cudaVersion" >> $env:GITHUB_ENV
 
-      - uses: softprops/action-gh-release@v1
+      - uses: softprops/action-gh-release@v2
         with:
           files: dist/*
           # Set tag_name to <tag>-cu<cuda_version>

{llama_cpp_python-0.2.65 → llama_cpp_python-0.2.66}/.github/workflows/build-wheels-metal.yaml

@@ -41,7 +41,7 @@ jobs:
         with:
           submodules: "recursive"
 
-      - uses: actions/setup-python@v4
+      - uses: actions/setup-python@v5
         with:
           python-version: ${{ matrix.pyver }}
 
@@ -78,7 +78,7 @@ jobs:
             VERBOSE=1 python -m build --wheel
           fi
 
-      - uses: softprops/action-gh-release@v1
+      - uses: softprops/action-gh-release@v2
         with:
           files: dist/*
           # set release name to <tag>-metal

{llama_cpp_python-0.2.65 → llama_cpp_python-0.2.66}/.github/workflows/generate-index-from-release.yaml

@@ -31,12 +31,14 @@ jobs:
       - name: Checkout
         uses: actions/checkout@v4
       - name: Setup Pages
-        uses: actions/configure-pages@v4
+        uses: actions/configure-pages@v5
       - name: Build
         run: |
           ./scripts/releases-to-pep-503.sh index/whl/cpu '^[v]?[0-9]+\.[0-9]+\.[0-9]+$'
           ./scripts/releases-to-pep-503.sh index/whl/cu121 '^[v]?[0-9]+\.[0-9]+\.[0-9]+-cu121$'
           ./scripts/releases-to-pep-503.sh index/whl/cu122 '^[v]?[0-9]+\.[0-9]+\.[0-9]+-cu122$'
+          ./scripts/releases-to-pep-503.sh index/whl/cu123 '^[v]?[0-9]+\.[0-9]+\.[0-9]+-cu123$'
+          ./scripts/releases-to-pep-503.sh index/whl/cu124 '^[v]?[0-9]+\.[0-9]+\.[0-9]+-cu124$'
           ./scripts/releases-to-pep-503.sh index/whl/metal '^[v]?[0-9]+\.[0-9]+\.[0-9]+-metal$'
       - name: Upload artifact
         uses: actions/upload-pages-artifact@v3

{llama_cpp_python-0.2.65 → llama_cpp_python-0.2.66}/.github/workflows/publish-to-test.yaml

@@ -16,11 +16,11 @@ jobs:
     runs-on: ubuntu-latest
 
     steps:
-    - uses: actions/checkout@v3
+    - uses: actions/checkout@v4
       with:
         submodules: "recursive"
     - name: Set up Python
-      uses: actions/setup-python@v4
+      uses: actions/setup-python@v5
       with:
         python-version: "3.8"
     - name: Append Dev Version to __version__
@@ -40,4 +40,4 @@ jobs:
       uses: pypa/gh-action-pypi-publish@release/v1
       with:
         password: ${{ secrets.TEST_PYPI_API_TOKEN }}
-        repository-url: https://test.pypi.org/legacy/
+        repository-url: https://test.pypi.org/legacy/

{llama_cpp_python-0.2.65 → llama_cpp_python-0.2.66}/.github/workflows/publish.yaml

@@ -10,11 +10,11 @@ jobs:
     runs-on: ubuntu-latest
 
     steps:
-    - uses: actions/checkout@v3
+    - uses: actions/checkout@v4
       with:
         submodules: "recursive"
     - name: Set up Python
-      uses: actions/setup-python@v4
+      uses: actions/setup-python@v5
       with:
         python-version: "3.8"
     - name: Install dependencies

{llama_cpp_python-0.2.65 → llama_cpp_python-0.2.66}/.github/workflows/test-pypi.yaml

@@ -8,11 +8,11 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        python-version: ["3.7", "3.8", "3.9", "3.10", "3.11"]
+        python-version: ["3.7", "3.8", "3.9", "3.10", "3.11", "3.12"]
 
     steps:
       - name: Set up Python ${{ matrix.python-version }}
-        uses: actions/setup-python@v4
+        uses: actions/setup-python@v5
         with:
           python-version: ${{ matrix.python-version }}
       - name: Install dependencies
@@ -28,11 +28,11 @@ jobs:
     runs-on: windows-latest
     strategy:
       matrix:
-        python-version: ["3.7", "3.8", "3.9", "3.10", "3.11"]
+        python-version: ["3.7", "3.8", "3.9", "3.10", "3.11", "3.12"]
 
     steps:
       - name: Set up Python ${{ matrix.python-version }}
-        uses: actions/setup-python@v4
+        uses: actions/setup-python@v5
         with:
           python-version: ${{ matrix.python-version }}
       - name: Install dependencies
@@ -48,11 +48,11 @@ jobs:
     runs-on: macos-latest
     strategy:
       matrix:
-        python-version: ["3.7", "3.8", "3.9", "3.10", "3.11"]
+        python-version: ["3.7", "3.8", "3.9", "3.10", "3.11", "3.12"]
 
     steps:
       - name: Set up Python ${{ matrix.python-version }}
-        uses: actions/setup-python@v4
+        uses: actions/setup-python@v5
         with:
           python-version: ${{ matrix.python-version }}
       - name: Install dependencies
@@ -61,4 +61,4 @@ jobs:
           python3 -m pip install --verbose llama-cpp-python[all]
       - name: Test with pytest
         run: |
-          python3 -c "import llama_cpp"
+          python3 -c "import llama_cpp"

{llama_cpp_python-0.2.65 → llama_cpp_python-0.2.66}/.github/workflows/test.yaml

@@ -21,7 +21,7 @@ jobs:
         with:
           submodules: "recursive"
       - name: Set up Python ${{ matrix.python-version }}
-        uses: actions/setup-python@v4
+        uses: actions/setup-python@v5
         with:
           python-version: ${{ matrix.python-version }}
       - name: Install dependencies
@@ -40,11 +40,11 @@ jobs:
         python-version: ["3.8", "3.9", "3.10", "3.11", "3.12"]
 
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
         with:
           submodules: "recursive"
       - name: Set up Python ${{ matrix.python-version }}
-        uses: actions/setup-python@v4
+        uses: actions/setup-python@v5
         with:
           python-version: ${{ matrix.python-version }}
       - name: Install dependencies
@@ -63,11 +63,11 @@ jobs:
         python-version: ["3.8", "3.9", "3.10", "3.11", "3.12"]
 
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
         with:
           submodules: "recursive"
       - name: Set up Python ${{ matrix.python-version }}
-        uses: actions/setup-python@v4
+        uses: actions/setup-python@v5
         with:
           python-version: ${{ matrix.python-version }}
       - name: Install dependencies
@@ -83,11 +83,11 @@ jobs:
   #   runs-on: ubuntu-latest
 
   #   steps:
-  #     - uses: actions/checkout@v3
+  #     - uses: actions/checkout@v4
   #       with:
   #         submodules: "recursive"
   #     - name: Set up Python 3.8
-  #       uses: actions/setup-python@v4
+  #       uses: actions/setup-python@v5
   #       with:
   #         python-version: "3.8"
   #     - name: Set up OpenCL & CLBlast
@@ -110,11 +110,11 @@ jobs:
     runs-on: macos-13
 
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
         with:
           submodules: "recursive"
       - name: Set up Python 3.8
-        uses: actions/setup-python@v4
+        uses: actions/setup-python@v5
         with:
           python-version: "3.8"
       - name: Install dependencies

{llama_cpp_python-0.2.65 → llama_cpp_python-0.2.66}/CHANGELOG.md

@@ -7,6 +7,17 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [0.2.66]
+
+- feat: Update llama.cpp to ggerganov/llama.cpp@8843a98c2ba97a25e93319a104f9ddfaf83ce4c4
+- feat: Generic Chat Formats, Tool Calling, and Huggingface Pull Support for Multimodal Models (Obsidian, LLaVA1.6, Moondream) by @abetlen in #1147
+- ci(fix): Workflow actions updates and fix arm64 wheels not included in release by @Smartappli in #1392
+- ci: Add support for pre-built cuda 12.4.1 wheels by @Smartappli in #1388
+- feat: Add support for str type kv_overrides by @abetlen in a411612b385cef100d76145da1fbd02a7b7cc894
+- fix: Functionary bug fixes by @jeffrey-fong in #1385
+- examples: fix quantize example by @iyubondyrev in #1387
+- ci: Update dependabot.yml by @Smartappli in #1391
+
 ## [0.2.65]
 
 - feat: Update llama.cpp to ggerganov/llama.cpp@46e12c4692a37bdd31a0432fc5153d7d22bc7f72

{llama_cpp_python-0.2.65 → llama_cpp_python-0.2.66}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: llama_cpp_python
-Version: 0.2.65
+Version: 0.2.66
 Summary: Python bindings for the llama.cpp library
 Author-Email: Andrei Betlen <abetlen@gmail.com>
 License: MIT
@@ -528,18 +528,21 @@ Due to discrepancies between llama.cpp and HuggingFace's tokenizers, it is requi
   tokenizer=LlamaHFTokenizer.from_pretrained("meetkai/functionary-small-v2.2-GGUF")
 )
 ```
+
+**NOTE**: There is no need to provide the default system messages used in Functionary as they are added automatically in the Functionary chat handler. Thus, the messages should contain just the chat messages and/or system messages that provide additional context for the model (e.g.: datetime, etc.).
 </details>
 
 ### Multi-modal Models
 
-`llama-cpp-python` supports the llava1.5 family of multi-modal models which allow the language model to
-read information from both text and images.
+`llama-cpp-python` supports such as llava1.5 which allow the language model to read information from both text and images.
 
 You'll first need to download one of the available multi-modal models in GGUF format:
 
 - [llava-v1.5-7b](https://huggingface.co/mys/ggml_llava-v1.5-7b)
 - [llava-v1.5-13b](https://huggingface.co/mys/ggml_llava-v1.5-13b)
 - [bakllava-1-7b](https://huggingface.co/mys/ggml_bakllava-1)
+- [llava-v1.6-34b](https://huggingface.co/cjpais/llava-v1.6-34B-gguf)
+- [moondream2](https://huggingface.co/vikhyatk/moondream2)
 
 Then you'll need to use a custom chat handler to load the clip model and process the chat messages and images.
 
@@ -551,7 +554,6 @@ Then you'll need to use a custom chat handler to load the clip model and process
   model_path="./path/to/llava/llama-model.gguf",
   chat_handler=chat_handler,
   n_ctx=2048, # n_ctx should be increased to accomodate the image embedding
-  logits_all=True,# needed to make llava work
 )
 >>> llm.create_chat_completion(
     messages = [
@@ -559,14 +561,45 @@ Then you'll need to use a custom chat handler to load the clip model and process
         {
             "role": "user",
             "content": [
-                {"type": "image_url", "image_url": {"url": "https://.../image.png"}},
-                {"type" : "text", "text": "Describe this image in detail please."}
+                {"type" : "text", "text": "What's in this image?"},
+                {"type": "image_url", "image_url": {"url": "https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg" } }
+            ]
+        }
+    ]
+)
+```
+
+You can also pull the model from the Hugging Face Hub using the `from_pretrained` method.
+
+```python
+>>> from llama_cpp import Llama
+>>> from llama_cpp.llama_chat_format import MoondreamChatHandler
+>>> chat_handler = MoondreamChatHandler.from_pretrained(
+  repo_id="vikhyatk/moondream2",
+  filename="*mmproj*",
+)
+>>> llm = Llama.from_pretrained(
+  repo_id="vikhyatk/moondream2"
+  filename="*text-model*",
+  chat_handler=chat_handler,
+  n_ctx=2048, # n_ctx should be increased to accomodate the image embedding
+)
+>>> llm.create_chat_completion(
+    messages = [
+        {
+            "role": "user",
+            "content": [
+                {"type" : "text", "text": "What's in this image?"},
+                {"type": "image_url", "image_url": {"url": "https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg" } }
+
             ]
         }
     ]
 )
 ```
 
+**Note**: Multi-modal models also support tool calling and JSON mode.
+
 <details>
 <summary>Loading a Local Image</summary>