Skip to content

Add language model architecture for inference script #108

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
Eamon2009 merged 30 commits into from
Jul 1, 2026
+381 −147
Merged

Add language model architecture for inference script #108

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
30 commits
Select commit Hold shift + click to select a range
87dae35
Add optimize CI, and update documentation (#85)
codeaddict-119 Jun 14, 2026
6703c1e
Update training configuration parameters (#89)
Eamon2009 Jun 15, 2026
bf21fe9
Revise README with new images and details
Eamon2009 Jun 16, 2026
394193a
Update README with new images and project details
Eamon2009 Jun 16, 2026
d7acb8d
Update hardware descriptions in README
Eamon2009 Jun 16, 2026
401f16c
training training run with best val loss of 2.9971
Eamon2009 Jun 16, 2026
fdb606d
inference: text generation loop sampling
Eamon2009 Jun 16, 2026
624d4af
model architecture and sync tokenizer with main to export weights
Eamon2009 Jun 16, 2026
b82c47b
Add CI approval workflow configuration
Eamon2009 Jun 16, 2026
0835a76
chore(deps): bump hadolint/hadolint-action from 3.1.0 to 3.3.0 (#70)
dependabot[bot] Jun 16, 2026
5dffd41
chore(deps): bump pydantic from 2.10.4 to 2.13.4 in /backend
dependabot[bot] Jun 17, 2026
7c58078
Mark frontend vendored and add pytorch submodule
Eamon2009 Jun 18, 2026
b5b86c1
Add pytoch/pytorch file
Eamon2009 Jun 18, 2026
eb41598
Delete libtorch directory
Eamon2009 Jun 18, 2026
c909f47
chore(deps): bump docker/metadata-action from 5 to 6 (#55)
dependabot[bot] Jun 19, 2026
d9be5b1
chore(deps): bump docker/login-action from 3 to 4
dependabot[bot] Jun 19, 2026
60b7a36
chore(deps): bump docker/login-action from 3 to 4 (#54)
Eamon2009 Jun 19, 2026
c328d5f
chore(deps): bump docker/setup-qemu-action from 3 to 4
dependabot[bot] Jun 19, 2026
1a7aa75
chore(deps): bump docker/setup-qemu-action from 3 to 4 (#90)
Eamon2009 Jun 20, 2026
b2b4640
chore(deps): bump docker/setup-buildx-action from 3 to 4
dependabot[bot] Jun 20, 2026
4b2fb2c
chore(deps): bump actions/upload-artifact from 4 to 7
dependabot[bot] Jun 20, 2026
35b58e5
Revise README for improved clarity and details
Eamon2009 Jun 26, 2026
e693d16
Merge branch 'master' into dependabot/github_actions/docker/setup-bui…
Eamon2009 Jun 26, 2026
ba96927
chore(deps): bump docker/setup-buildx-action from 3 to 4 (#83)
Eamon2009 Jun 26, 2026
7d2be58
Merge branch 'master' into dependabot/github_actions/actions/upload-a…
Eamon2009 Jun 26, 2026
75ae95f
chore(deps): bump actions/upload-artifact from 4 to 7 (#91)
Eamon2009 Jun 26, 2026
19b372f
Merge branch 'master' into dependabot/pip/backend/pydantic-2.13.4
Eamon2009 Jun 26, 2026
4f278f9
chore(deps): bump pydantic from 2.10.4 to 2.13.4 in /backend (#92)
Eamon2009 Jun 26, 2026
eb419c8
chore(deps): bump redis from 5.2.1 to 8.0.1 in /backend (#93)
dependabot[bot] Jun 28, 2026
bfc869a
Fix grammar in README.md project description
Eamon2009 Jun 30, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 5 additions & 0 deletions .gitattributes
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1 +1,6 @@
frontend/** linguist-vendored
frontend/** linguist-vendored
[submodule "pytorch"]
path = pytorch
url = https://github.com/pytorch/pytorch

28 changes: 14 additions & 14 deletions .github/workflows/ci.yml → .github/workflows/ci-approval.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
name: CI
name: ci-approval

on:
workflow_dispatch:
Expand Down Expand Up @@ -84,7 +84,7 @@ jobs:
run: ./quadtrix --help || true

- name: Upload binary
uses: actions/upload-artifact@v4
uses: actions/upload-artifact@v7
with:
name: quadtrix-linux-amd64
path: quadtrix
Expand All @@ -111,7 +111,7 @@ jobs:
run: tar -czf quadtrix-macos-arm64.tar.gz quadtrix

- name: Upload binary
uses: actions/upload-artifact@v4
uses: actions/upload-artifact@v7
with:
name: quadtrix-macos-arm64
path: quadtrix-macos-arm64.tar.gz
Expand All @@ -127,23 +127,23 @@ jobs:
steps:
- uses: actions/checkout@v4

- uses: docker/setup-qemu-action@v3
- uses: docker/setup-buildx-action@v3
- uses: docker/setup-qemu-action@v4
- uses: docker/setup-buildx-action@v4

- name: Set lowercase image prefix
run: echo "IMAGE_PREFIX=ghcr.io/${GITHUB_REPOSITORY_OWNER,,}/quadtrix" >> $GITHUB_ENV

- name: Login to GHCR
if: ${{ inputs.push_image == 'true' }}
uses: docker/login-action@v3
uses: docker/login-action@v4
with:
registry: ${{ env.REGISTRY }}
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}

- name: Extract metadata
id: meta
uses: docker/metadata-action@v5
uses: docker/metadata-action@v6
with:
images: ${{ env.IMAGE_PREFIX }}-cpp
tags: |
Expand Down Expand Up @@ -174,23 +174,23 @@ jobs:
steps:
- uses: actions/checkout@v4

- uses: docker/setup-qemu-action@v3
- uses: docker/setup-buildx-action@v3
- uses: docker/setup-qemu-action@v4
- uses: docker/setup-buildx-action@v4

- name: Set lowercase image prefix
run: echo "IMAGE_PREFIX=ghcr.io/${GITHUB_REPOSITORY_OWNER,,}/quadtrix" >> $GITHUB_ENV

- name: Login to GHCR
if: ${{ inputs.push_image == 'true' }}
uses: docker/login-action@v3
uses: docker/login-action@v4
with:
registry: ${{ env.REGISTRY }}
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}

- name: Extract metadata
id: meta
uses: docker/metadata-action@v5
uses: docker/metadata-action@v6
with:
images: ${{ env.IMAGE_PREFIX }}-cpu
tags: |
Expand Down Expand Up @@ -221,22 +221,22 @@ jobs:
steps:
- uses: actions/checkout@v4

- uses: docker/setup-buildx-action@v3
- uses: docker/setup-buildx-action@v4

- name: Set lowercase image prefix
run: echo "IMAGE_PREFIX=ghcr.io/${GITHUB_REPOSITORY_OWNER,,}/quadtrix" >> $GITHUB_ENV

- name: Login to GHCR
if: ${{ inputs.push_image == 'true' }}
uses: docker/login-action@v3
uses: docker/login-action@v4
with:
registry: ${{ env.REGISTRY }}
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}

- name: Extract metadata
id: meta
uses: docker/metadata-action@v5
uses: docker/metadata-action@v6
with:
images: ${{ env.IMAGE_PREFIX }}-cuda
tags: |
Expand Down
22 changes: 11 additions & 11 deletions .github/workflows/docker-publish.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -41,23 +41,23 @@ jobs:
steps:
- uses: actions/checkout@v4

- uses: docker/setup-qemu-action@v3
- uses: docker/setup-buildx-action@v3
- uses: docker/setup-qemu-action@v4
- uses: docker/setup-buildx-action@v4

- name: Set lowercase image prefix
run: echo "IMAGE_PREFIX=ghcr.io/${GITHUB_REPOSITORY_OWNER,,}/quadtrix" >> "$GITHUB_ENV"

- name: Login to GHCR
if: ${{ inputs.push_image == 'true' }}
uses: docker/login-action@v3
uses: docker/login-action@v4
with:
registry: ${{ env.REGISTRY }}
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}

- name: Extract metadata
id: meta
uses: docker/metadata-action@v5
uses: docker/metadata-action@v6
with:
images: ${{ env.IMAGE_PREFIX }}-cpp
tags: |
Expand Down Expand Up @@ -88,23 +88,23 @@ jobs:
steps:
- uses: actions/checkout@v4

- uses: docker/setup-qemu-action@v3
- uses: docker/setup-buildx-action@v3
- uses: docker/setup-qemu-action@v4
- uses: docker/setup-buildx-action@v4

- name: Set lowercase image prefix
run: echo "IMAGE_PREFIX=ghcr.io/${GITHUB_REPOSITORY_OWNER,,}/quadtrix" >> "$GITHUB_ENV"

- name: Login to GHCR
if: ${{ inputs.push_image == 'true' }}
uses: docker/login-action@v3
uses: docker/login-action@v4
with:
registry: ${{ env.REGISTRY }}
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}

- name: Extract metadata
id: meta
uses: docker/metadata-action@v5
uses: docker/metadata-action@v6
with:
images: ${{ env.IMAGE_PREFIX }}-cpu
tags: |
Expand Down Expand Up @@ -135,22 +135,22 @@ jobs:
steps:
- uses: actions/checkout@v4

- uses: docker/setup-buildx-action@v3
- uses: docker/setup-buildx-action@v4

- name: Set lowercase image prefix
run: echo "IMAGE_PREFIX=ghcr.io/${GITHUB_REPOSITORY_OWNER,,}/quadtrix" >> "$GITHUB_ENV"

- name: Login to GHCR
if: ${{ inputs.push_image == 'true' }}
uses: docker/login-action@v3
uses: docker/login-action@v4
with:
registry: ${{ env.REGISTRY }}
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}

- name: Extract metadata
id: meta
uses: docker/metadata-action@v5
uses: docker/metadata-action@v6
with:
images: ${{ env.IMAGE_PREFIX }}-cuda
tags: |
Expand Down
8 changes: 4 additions & 4 deletions .github/workflows/pr-check.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -150,7 +150,7 @@ jobs:
run: ./quadtrix --help || true

- name: Upload artifact
uses: actions/upload-artifact@v4
uses: actions/upload-artifact@v7
with:
name: ${{ matrix.artifact }}
path: quadtrix
Expand Down Expand Up @@ -199,19 +199,19 @@ jobs:
exit $failed

- name: Lint — Dockerfile.cpp
uses: hadolint/hadolint-action@v3.1.0
uses: hadolint/hadolint-action@v3.3.0
with:
dockerfile: .devops/Dockerfile.cpp
failure-threshold: error

- name: Lint — Dockerfile (CPU)
uses: hadolint/hadolint-action@v3.1.0
uses: hadolint/hadolint-action@v3.3.0
with:
dockerfile: .devops/Dockerfile
failure-threshold: error

- name: Lint — Dockerfile.backend (CUDA)
uses: hadolint/hadolint-action@v3.1.0
uses: hadolint/hadolint-action@v3.3.0
with:
dockerfile: .devops/Dockerfile.backend
failure-threshold: error
Expand Down
6 changes: 3 additions & 3 deletions .github/workflows/release.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -93,7 +93,7 @@ jobs:
tar -czf "${package}.tar.gz" -C "${ARTIFACT_ROOT}" "${package}"

- name: Upload artifacts
uses: actions/upload-artifact@v4
uses: actions/upload-artifact@v7
with:
name: quadtrix-bin-ubuntu-${{ matrix.build }}-cpu
path: quadtrix-${{ needs.release-metadata.outputs.tag_name }}-bin-ubuntu-${{ matrix.build }}-cpu.tar.gz
Expand Down Expand Up @@ -142,7 +142,7 @@ jobs:
Compress-Archive -Path "${env:ARTIFACT_ROOT}\${package}\*" -DestinationPath "${package}.zip" -Force

- name: Upload artifacts
uses: actions/upload-artifact@v4
uses: actions/upload-artifact@v7
with:
name: quadtrix-bin-windows-${{ matrix.arch }}-cpu
path: quadtrix-${{ needs.release-metadata.outputs.tag_name }}-bin-windows-${{ matrix.arch }}-cpu.zip
Expand Down Expand Up @@ -192,7 +192,7 @@ jobs:
tar -czf "${package}.tar.gz" -C "${ARTIFACT_ROOT}" "${package}"

- name: Upload artifacts
uses: actions/upload-artifact@v4
uses: actions/upload-artifact@v7
with:
name: quadtrix-bin-macos-${{ matrix.build }}-cpu
path: quadtrix-${{ needs.release-metadata.outputs.tag_name }}-bin-macos-${{ matrix.build }}-cpu.tar.gz
Expand Down
Loading
Loading