diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml index e809509..394909c 100644 --- a/.github/workflows/ci.yml +++ b/.github/workflows/ci.yml @@ -49,7 +49,7 @@ jobs: runs-on: ubuntu-latest steps: - uses: actions/checkout@v4 - - uses: actions/setup-python@v4 + - uses: actions/setup-python@v5 with: python-version: "3.11" - name: Install dependencies with poetry @@ -76,7 +76,7 @@ jobs: runs-on: ubuntu-latest steps: - uses: actions/checkout@v4 - - uses: actions/setup-python@v4 + - uses: actions/setup-python@v5 with: python-version: "3.11" - name: Run ruff check diff --git a/.github/workflows/helm-test.yml b/.github/workflows/helm-test.yml index 0a2949b..c3fdde7 100644 --- a/.github/workflows/helm-test.yml +++ b/.github/workflows/helm-test.yml @@ -41,7 +41,7 @@ jobs: with: version: v3.12.3 - - uses: actions/setup-python@v4 + - uses: actions/setup-python@v5 with: python-version: '3.10' check-latest: true diff --git a/.github/workflows/model-check.yml b/.github/workflows/model-check.yml index df83848..b590d57 100644 --- a/.github/workflows/model-check.yml +++ b/.github/workflows/model-check.yml @@ -34,7 +34,7 @@ jobs: runs-on: ubuntu-latest steps: - uses: actions/checkout@v4 - - uses: actions/setup-python@v4 + - uses: actions/setup-python@v5 with: python-version: "3.11" - name: Install dependencies with poetry diff --git a/README.md b/README.md index 91e2512..0b51b63 100644 --- a/README.md +++ b/README.md @@ -69,16 +69,13 @@ Instructions for setting up Serge on Kubernetes can be found in the [wiki](https | **OpenChat** | 7B-v3.5 | | **OpenLLaMA** | 3B-v2, 7B-v2, 13B-v2 | | **Orca 2** | 7B, 13B | +| **Python Code** | 13B, 33B | | **PsyMedRP** | 13B-v1, 20B-v1 | | **Starling LM** | 7B-Alpha | | **Vicuna** | 7B-v1.5, 13B-v1.5 | -| **Zephyr** | 7B-Alpha, 7B-Beta | +| **Zephyr** | 3B, 7B-Alpha, 7B-Beta | -Additional weights can be added to the `serge_weights` volume using `docker cp`: - -```bash -docker cp ./my_weight.bin serge:/usr/src/app/weights/ -``` +Additional models can be requested by opening a GitHub issue. ## ⚠️ Memory Usage @@ -104,5 +101,5 @@ To run Serge in development mode: ```bash git clone https://github.com/serge-chat/serge.git cd serge/ -docker compose -f docker-compose.dev.yml up -d --build +docker compose -f docker-compose.dev.yml up --build ``` diff --git a/api/src/serge/data/models.json b/api/src/serge/data/models.json index 3d6c4ba..e8245f6 100644 --- a/api/src/serge/data/models.json +++ b/api/src/serge/data/models.json @@ -350,23 +350,7 @@ ] } ] - }, - { - "name": "SlimOrca", - "models": [ - { - "name": "SlimOrca-13B", - "repo": "TheBloke/SlimOrca-13B-GGUF", - "files": [ - { - "name": "q4_K_M", - "filename": "slimorca-13b.Q4_K_M.gguf", - "disk_space": 7865956352.0 - } - ] - } - ] - }, + }, { "name": "Orca_2", "models": [ @@ -393,7 +377,34 @@ ] } ] - }, + }, + { + "name": "Python-Code", + "models": [ + { + "name": "Python-Code-13B", + "repo": "TheBloke/Python-Code-13B-GGUF", + "files": [ + { + "name": "q4_K_M", + "filename": "python-code-13b.Q4_K_M.gguf", + "disk_space": 7865956352.0 + } + ] + }, + { + "name": "Python-Code-33B", + "repo": "TheBloke/Python-Code-33B-GGUF", + "files": [ + { + "name": "q4_K_M", + "filename": "python-code-33b.Q4_K_M.gguf", + "disk_space": 19621140000.0 + } + ] + } + ] + }, { "name": "PsyMedRP", "models": [ @@ -421,6 +432,22 @@ } ] }, + { + "name": "SlimOrca", + "models": [ + { + "name": "SlimOrca-13B", + "repo": "TheBloke/SlimOrca-13B-GGUF", + "files": [ + { + "name": "q4_K_M", + "filename": "slimorca-13b.Q4_K_M.gguf", + "disk_space": 7865956352.0 + } + ] + } + ] + }, { "name": "StarlingLM", "models": [ @@ -467,6 +494,17 @@ { "name": "Zephyr", "models": [ + { + "name": "Zephyr-3B", + "repo": "TheBloke/stablelm-zephyr-3b-GGUF", + "files": [ + { + "name": "q4_K_M", + "filename": "stablelm-zephyr-3b.Q4_K_M.gguf", + "disk_space": 1708595648.0 + } + ] + }, { "name": "Zephyr-7B-Alpha", "repo": "TheBloke/zephyr-7B-alpha-GGUF", diff --git a/web/package-lock.json b/web/package-lock.json index e1d9ba7..a0132ea 100644 --- a/web/package-lock.json +++ b/web/package-lock.json @@ -13,7 +13,7 @@ "clipboard": "^2.0.11", "daisyui": "^4.4.19", "highlight.js": "^11.9.0", - "markdown-it": "^13.0.2", + "markdown-it": "^14.0.0", "markdown-it-highlightjs": "^4.0.1", "prettier-plugin-svelte": "^3.1.2", "prettier-plugin-tailwindcss": "^0.5.9" @@ -39,7 +39,7 @@ "svelte-check": "^3.6.2", "tailwindcss": "^3.3.6", "tslib": "^2.6.2", - "typescript": "^5.3.2", + "typescript": "^5.3.3", "vite": "^4.5.1" } }, @@ -1971,9 +1971,9 @@ "dev": true }, "node_modules/entities": { - "version": "3.0.1", - "resolved": "https://registry.npmjs.org/entities/-/entities-3.0.1.tgz", - "integrity": "sha512-WiyBqoomrwMdFG1e0kqvASYfnlb0lp8M5o5Fw2OFq1hNZxxcNk8Ik0Xm7LxzBhuidnZB/UtBqVCgUz3kBOP51Q==", + "version": "4.5.0", + "resolved": "https://registry.npmjs.org/entities/-/entities-4.5.0.tgz", + "integrity": "sha512-V0hjH4dGPh9Ao5p0MoRY6BVqtwCjhz6vI5LT8AJ55H+4g9/4vbHx1I54fS0XuclLhDHArPQCiMjDxjaL8fPxhw==", "engines": { "node": ">=0.12" }, @@ -3542,11 +3542,11 @@ "dev": true }, "node_modules/linkify-it": { - "version": "4.0.1", - "resolved": "https://registry.npmjs.org/linkify-it/-/linkify-it-4.0.1.tgz", - "integrity": "sha512-C7bfi1UZmoj8+PQx22XyeXCuBlokoyWQL5pWSP+EI6nzRylyThouddufc2c1NDIcP9k5agmN9fLpA7VNJfIiqw==", + "version": "5.0.0", + "resolved": "https://registry.npmjs.org/linkify-it/-/linkify-it-5.0.0.tgz", + "integrity": "sha512-5aHCbzQRADcdP+ATqnDuhhJ/MRIqDkZX5pyjFHRRysS8vZ5AbqGEoFIb6pYHPZ+L/OC2Lc+xT8uHVVR5CAK/wQ==", "dependencies": { - "uc.micro": "^1.0.1" + "uc.micro": "^2.0.0" } }, "node_modules/locate-character": { @@ -3606,18 +3606,19 @@ } }, "node_modules/markdown-it": { - "version": "13.0.2", - "resolved": "https://registry.npmjs.org/markdown-it/-/markdown-it-13.0.2.tgz", - "integrity": "sha512-FtwnEuuK+2yVU7goGn/MJ0WBZMM9ZPgU9spqlFs7/A/pDIUNSOQZhUgOqYCficIuR2QaFnrt8LHqBWsbTAoI5w==", + "version": "14.0.0", + "resolved": "https://registry.npmjs.org/markdown-it/-/markdown-it-14.0.0.tgz", + "integrity": "sha512-seFjF0FIcPt4P9U39Bq1JYblX0KZCjDLFFQPHpL5AzHpqPEKtosxmdq/LTVZnjfH7tjt9BxStm+wXcDBNuYmzw==", "dependencies": { "argparse": "^2.0.1", - "entities": "~3.0.1", - "linkify-it": "^4.0.1", - "mdurl": "^1.0.1", - "uc.micro": "^1.0.5" + "entities": "^4.4.0", + "linkify-it": "^5.0.0", + "mdurl": "^2.0.0", + "punycode.js": "^2.3.1", + "uc.micro": "^2.0.0" }, "bin": { - "markdown-it": "bin/markdown-it.js" + "markdown-it": "bin/markdown-it.mjs" } }, "node_modules/markdown-it-highlightjs": { @@ -3634,9 +3635,9 @@ "integrity": "sha512-GaqWWShW4kv/G9IEucWScBx9G1/vsFZZJUO+tD26M8J8z3Kw5RDQjaoZe03YAClgeS/SWPOcb4nkFBTEi5DUEA==" }, "node_modules/mdurl": { - "version": "1.0.1", - "resolved": "https://registry.npmjs.org/mdurl/-/mdurl-1.0.1.tgz", - "integrity": "sha512-/sKlQJCBYVY9Ers9hqzKou4H6V5UWc/M59TH2dvkt+84itfnq7uFOMLpOiOS4ujvHP4etln18fmIxA5R5fll0g==" + "version": "2.0.0", + "resolved": "https://registry.npmjs.org/mdurl/-/mdurl-2.0.0.tgz", + "integrity": "sha512-Lf+9+2r+Tdp5wXDXC4PcIBjTDtq4UKjCPMQhKIuzpJNW0b96kVqSwW0bT7FhRSfmAiFYgP+SCRvdrDozfh0U5w==" }, "node_modules/merge-stream": { "version": "2.0.0", @@ -4437,6 +4438,14 @@ "node": ">=6" } }, + "node_modules/punycode.js": { + "version": "2.3.1", + "resolved": "https://registry.npmjs.org/punycode.js/-/punycode.js-2.3.1.tgz", + "integrity": "sha512-uxFIHU0YlHYhDQtV4R9J6a52SLx28BCjT+4ieh7IGbgwVJWO+km431c4yRlREUAsAmt/uMjQUyQHNEPf0M39CA==", + "engines": { + "node": ">=6" + } + }, "node_modules/queue-microtask": { "version": "1.2.3", "resolved": "https://registry.npmjs.org/queue-microtask/-/queue-microtask-1.2.3.tgz", @@ -5572,9 +5581,9 @@ } }, "node_modules/typescript": { - "version": "5.3.2", - "resolved": "https://registry.npmjs.org/typescript/-/typescript-5.3.2.tgz", - "integrity": "sha512-6l+RyNy7oAHDfxC4FzSJcz9vnjTKxrLpDG5M2Vu4SHRVNg6xzqZp6LYSR9zjqQTu8DU/f5xwxUdADOkbrIX2gQ==", + "version": "5.3.3", + "resolved": "https://registry.npmjs.org/typescript/-/typescript-5.3.3.tgz", + "integrity": "sha512-pXWcraxM0uxAS+tN0AG/BF2TyqmHO014Z070UsJ+pFvYuRSq8KH8DmWpnbXe0pEPDHXZV3FcAbJkijJ5oNEnWw==", "dev": true, "bin": { "tsc": "bin/tsc", @@ -5585,9 +5594,9 @@ } }, "node_modules/uc.micro": { - "version": "1.0.6", - "resolved": "https://registry.npmjs.org/uc.micro/-/uc.micro-1.0.6.tgz", - "integrity": "sha512-8Y75pvTYkLJW2hWQHXxoqRgV7qb9B+9vFEtidML+7koHUFapnVJAZ6cKs+Qjz5Aw3aZWHMC6u0wJE3At+nSGwA==" + "version": "2.0.0", + "resolved": "https://registry.npmjs.org/uc.micro/-/uc.micro-2.0.0.tgz", + "integrity": "sha512-DffL94LsNOccVn4hyfRe5rdKa273swqeA5DJpMOeFmEn1wCDc7nAbbB0gXlgBCL7TNzeTv6G7XVWzan7iJtfig==" }, "node_modules/unbox-primitive": { "version": "1.0.2", diff --git a/web/package.json b/web/package.json index 513f6e4..6877b7d 100644 --- a/web/package.json +++ b/web/package.json @@ -32,7 +32,7 @@ "svelte-check": "^3.6.2", "tailwindcss": "^3.3.6", "tslib": "^2.6.2", - "typescript": "^5.3.2", + "typescript": "^5.3.3", "vite": "^4.5.1" }, "type": "module", @@ -42,7 +42,7 @@ "clipboard": "^2.0.11", "daisyui": "^4.4.19", "highlight.js": "^11.9.0", - "markdown-it": "^13.0.2", + "markdown-it": "^14.0.0", "markdown-it-highlightjs": "^4.0.1", "prettier-plugin-svelte": "^3.1.2", "prettier-plugin-tailwindcss": "^0.5.9"