image: repository: huggingface name: chat-ui nodeSelector: role-huggingchat: "true" tolerations: - key: "huggingface.co/huggingchat" operator: "Equal" value: "true" effect: "NoSchedule" serviceAccount: enabled: true create: true name: huggingchat-prod ingress: path: "/chat" annotations: alb.ingress.kubernetes.io/healthcheck-path: "/healthcheck" alb.ingress.kubernetes.io/listen-ports: "[{\"HTTP\": 80}, {\"HTTPS\": 443}]" alb.ingress.kubernetes.io/group.name: "hub-prod" alb.ingress.kubernetes.io/scheme: "internet-facing" alb.ingress.kubernetes.io/ssl-redirect: "443" alb.ingress.kubernetes.io/tags: "Env=prod,Project=hub,Terraform=true" alb.ingress.kubernetes.io/target-node-labels: "role-hub-utils=true" kubernetes.io/ingress.class: "alb" envVars: ADDRESS_HEADER: 'X-Forwarded-For' ALTERNATIVE_REDIRECT_URLS: '["huggingchat://login/callback"]' APP_BASE: "/chat" ALLOW_IFRAME: "false" COMMUNITY_TOOLS: "true" COOKIE_SAMESITE: "lax" COOKIE_SECURE: "true" ENABLE_ASSISTANTS: "true" ENABLE_ASSISTANTS_RAG: "true" METRICS_PORT: 5565 LOG_LEVEL: "debug" METRICS_ENABLED: "true" MODELS: > [ { "name": "meta-llama/Llama-3.3-70B-Instruct", "id": "meta-llama/Llama-3.3-70B-Instruct", "description": "Ideal for everyday use. A fast and extremely capable model matching closed source models' capabilities. Now with the latest Llama 3.3 weights!", "modelUrl": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "websiteUrl": "https://llama.meta.com/", "logoUrl": "https://huggingface.co/datasets/huggingchat/models-logo/resolve/main/meta-logo.png", "tools": true, "preprompt": "", "parameters": { "stop": ["<|endoftext|>", "<|eot_id|>"], "temperature": 0.6, "max_new_tokens": 1024, "truncate": 7167 }, "promptExamples": [ { "title": "Write an email from bullet list", "prompt": "As a restaurant owner, write a professional email to the supplier to get these products every week: \n\n- Wine (x10)\n- Eggs (x24)\n- Bread (x12)" }, { "title": "Code a snake game", "prompt": "Code a basic snake game in python, give explanations for each step." }, { "title": "Assist in a task", "prompt": "How do I make a delicious lemon cheesecake?" } ] }, { "name": "Qwen/Qwen2.5-72B-Instruct", "description": "The latest Qwen open model with improved role-playing, long text generation and structured data understanding.", "modelUrl": "https://huggingface.co/Qwen/Qwen2.5-72B-Instruct", "websiteUrl": "https://qwenlm.github.io/blog/qwen2.5/", "logoUrl": "https://huggingface.co/datasets/huggingchat/models-logo/resolve/main/qwen-logo.png", "preprompt": "You are Qwen, created by Alibaba Cloud. You are a helpful assistant.", "parameters": { "stop": ["<|endoftext|>", "<|im_end|>"], "temperature": 0.6, "truncate": 28672, "max_new_tokens": 3072 }, "tools": true, "promptExamples": [ { "title": "Write an email from bullet list", "prompt": "As a restaurant owner, write a professional email to the supplier to get these products every week: \n\n- Wine (x10)\n- Eggs (x24)\n- Bread (x12)" }, { "title": "Code a snake game", "prompt": "Code a basic snake game in python, give explanations for each step." }, { "title": "Assist in a task", "prompt": "How do I make a delicious lemon cheesecake?" } ] }, { "name": "CohereForAI/c4ai-command-r-plus-08-2024", "description": "Cohere's largest language model, optimized for conversational interaction and tool use. Now with the 2024 update!", "modelUrl": "https://huggingface.co/CohereForAI/c4ai-command-r-plus-08-2024", "websiteUrl": "https://docs.cohere.com/docs/command-r-plus", "logoUrl": "https://huggingface.co/datasets/huggingchat/models-logo/resolve/main/cohere-logo.png", "tools": true, "parameters": { "stop": ["<|END_OF_TURN_TOKEN|>", "<|im_end|>"], "truncate": 28672, "max_new_tokens": 2048, "temperature": 0.3 }, "promptExamples": [ { "title": "Generate a mouse portrait", "prompt": "Generate the portrait of a scientific mouse in its laboratory." }, { "title": "Review a pull request", "prompt": "Review this pull request: https://github.com/huggingface/chat-ui/pull/1131/files" }, { "title": "Code a snake game", "prompt": "Code a basic snake game in python, give explanations for each step." } ] }, { "name": "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B", "modelUrl": "https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B", "websiteUrl": "https://deepseek.com/", "logoUrl": "https://huggingface.co/datasets/huggingchat/models-logo/resolve/main/deepseek-logo.png", "description": "The first reasoning model from DeepSeek, distilled into a 32B dense model. Outperforms o1-mini on multiple benchmarks.", "reasoning": { "type": "tokens", "beginToken": "", "endToken": "" }, "promptExamples": [ { "title": "Rs in strawberry", "prompt": "how many R in strawberry?" }, { "title": "Larger number", "prompt": "9.11 or 9.9 which number is larger?" }, { "title": "Measuring 6 liters", "prompt": "I have a 6- and a 12-liter jug. I want to measure exactly 6 liters." } ], "endpoints": [ { "type": "openai", "baseURL": "https://internal.api-inference.huggingface.co/models/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B/v1" } ] }, { "name": "nvidia/Llama-3.1-Nemotron-70B-Instruct-HF", "modelUrl": "https://huggingface.co/nvidia/Llama-3.1-Nemotron-70B-Instruct-HF", "websiteUrl": "https://www.nvidia.com/", "logoUrl": "https://huggingface.co/datasets/huggingchat/models-logo/resolve/main/nvidia-logo.png", "description": "Nvidia's latest Llama fine-tune, topping alignment benchmarks and optimized for instruction following.", "parameters": { "stop": ["<|eot_id|>", "<|im_end|>"], "temperature": 0.5, "truncate": 28672, "max_new_tokens": 2048 }, "promptExamples": [ { "title": "Rs in strawberry", "prompt": "how many R in strawberry?" }, { "title": "Larger number", "prompt": "9.11 or 9.9 which number is larger?" }, { "title": "Measuring 6 liters", "prompt": "I have a 6- and a 12-liter jug. I want to measure exactly 6 liters." } ], "endpoints": [ { "type": "openai", "baseURL": "https://internal.api-inference.huggingface.co/models/nvidia/Llama-3.1-Nemotron-70B-Instruct-HF/v1" } ] }, { "name": "Qwen/QwQ-32B", "preprompt": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step.", "modelUrl": "https://huggingface.co/Qwen/QwQ-32B", "websiteUrl": "https://qwenlm.github.io/blog/qwq-32b/", "logoUrl": "https://huggingface.co/datasets/huggingchat/models-logo/resolve/main/qwen-logo.png", "description": "QwQ is the latest reasoning model released by the Qwen team, approaching the capabilities of R1 in benchmarks.", "reasoning": { "type": "tokens", "beginToken": "", "endToken": "" }, "promptExamples": [ { "title": "Rs in strawberry", "prompt": "how many R in strawberry?" }, { "title": "Larger number", "prompt": "9.11 or 9.9 which number is larger?" }, { "title": "Measuring 6 liters", "prompt": "I have a 6- and a 12-liter jug. I want to measure exactly 6 liters." } ], "endpoints": [ { "type": "openai", "baseURL": "https://atv7xs1nxxtx2wl0.us-east-1.aws.endpoints.huggingface.cloud/v1" } ] }, { "name": "Qwen/Qwen2.5-Coder-32B-Instruct", "description": "Qwen's latest coding model, in its biggest size yet. SOTA on many coding benchmarks.", "modelUrl": "https://huggingface.co/Qwen/Qwen2.5-Coder-32B-Instruct", "websiteUrl": "https://qwenlm.github.io/blog/qwen2.5-coder-family/", "logoUrl": "https://huggingface.co/datasets/huggingchat/models-logo/resolve/main/qwen-logo.png", "preprompt": "You are Qwen, created by Alibaba Cloud. You are a helpful assistant.", "parameters": { "stop": ["<|im_end|>", "<|endoftext|>"], "temperature": 0.6, "truncate": 28672, "max_new_tokens": 3072 }, "promptExamples": [ { "title": "To-do list web app", "prompt": "Create a simple to-do list application where users can:\n- Add new tasks.\n- Mark tasks as complete.\n- Delete completed tasks.\nThe tasks should persist in the browser's local storage so that they remain available even after a page reload.\n" }, { "title": "Create a REST API", "prompt": "Build a simple REST API using Node.js, TypeScript and Express:\n- POST /items: Accepts a JSON body with name and quantity and adds a new item.\n- GET /items: Returns a list of all items.\n- PUT /items/:id: Updates the name or quantity of an item by its id.\n- DELETE /items/:id: Removes an item by its id.\nUse an in-memory array as the data store (no need for a database). Include basic error handling (e.g., item not found)." }, { "title": "Simple website", "prompt": "Generate a snazzy static landing page for a local coffee shop using HTML and CSS. You can use tailwind using ." } ], "endpoints": [ { "type": "openai", "baseURL": "https://internal.api-inference.huggingface.co/models/Qwen/Qwen2.5-Coder-32B-Instruct/v1" } ] }, { "name": "google/gemma-3-27b-it", "logoUrl": "https://huggingface.co/datasets/huggingchat/models-logo/resolve/main/google-logo.png", "multimodal": true, "description": "Google's latest open model with great multilingual performance, supports image inputs natively.", "websiteUrl": "https://blog.google/technology/developers/gemma-3/", "promptExamples": [ { "title": "Write an email from bullet list", "prompt": "As a restaurant owner, write a professional email to the supplier to get these products every week: \n\n- Wine (x10)\n- Eggs (x24)\n- Bread (x12)" }, { "title": "Code a snake game", "prompt": "Code a basic snake game in python, give explanations for each step." }, { "title": "Assist in a task", "prompt": "How do I make a delicious lemon cheesecake?" } ], "endpoints": [ { "type": "openai", "baseURL": "https://wp0d3hn6s3k8jk22.us-east-1.aws.endpoints.huggingface.cloud/v1", "multimodal": { "image": { "maxSizeInMB": 10, "maxWidth": 560, "maxHeight": 560, "supportedMimeTypes": ["image/jpeg"], "preferredMimeType": "image/jpeg" } } } ] }, { "name": "meta-llama/Llama-3.2-11B-Vision-Instruct", "logoUrl": "https://huggingface.co/datasets/huggingchat/models-logo/resolve/main/meta-logo.png", "description": "The latest multimodal model from Meta! Supports image inputs natively.", "websiteUrl": "https://llama.com/", "multimodal": true, "parameters": { "stop": ["<|eot_id|>", "<|im_end|>"], "temperature": 0.6, "truncate": 14336, "max_new_tokens": 1536 }, "promptExamples": [ { "title": "Write an email from bullet list", "prompt": "As a restaurant owner, write a professional email to the supplier to get these products every week: \n\n- Wine (x10)\n- Eggs (x24)\n- Bread (x12)" }, { "title": "Code a snake game", "prompt": "Code a basic snake game in python, give explanations for each step." }, { "title": "Assist in a task", "prompt": "How do I make a delicious lemon cheesecake?" } ], "endpoints": [ { "type": "openai", "baseURL": "https://internal.api-inference.huggingface.co/models/meta-llama/Llama-3.2-11B-Vision-Instruct/v1", "multimodal": { "image": { "maxSizeInMB": 10, "maxWidth": 560, "maxHeight": 560, "supportedMimeTypes": ["image/png", "image/jpeg", "image/webp"], "preferredMimeType": "image/webp" } } } ] }, { "name": "NousResearch/Hermes-3-Llama-3.1-8B", "description": "Nous Research's latest Hermes 3 release in 8B size. Follows instruction closely.", "logoUrl": "https://huggingface.co/datasets/huggingchat/models-logo/resolve/main/nous-logo.png", "websiteUrl": "https://nousresearch.com/", "modelUrl": "https://huggingface.co/NousResearch/Hermes-3-Llama-3.1-8B", "promptExamples": [ { "title": "Write an email from bullet list", "prompt": "As a restaurant owner, write a professional email to the supplier to get these products every week: \n\n- Wine (x10)\n- Eggs (x24)\n- Bread (x12)" }, { "title": "Code a snake game", "prompt": "Code a basic snake game in python, give explanations for each step." }, { "title": "Assist in a task", "prompt": "How do I make a delicious lemon cheesecake?" } ], "parameters": { "stop": ["<|im_end|>"], "temperature": 0.6, "truncate": 14336, "max_new_tokens": 1536 } }, { "name": "mistralai/Mistral-Nemo-Instruct-2407", "displayName": "mistralai/Mistral-Nemo-Instruct-2407", "description": "A small model with good capabilities in language understanding and commonsense reasoning.", "logoUrl": "https://huggingface.co/datasets/huggingchat/models-logo/resolve/main/mistral-logo.png", "websiteUrl": "https://mistral.ai/news/mistral-nemo/", "modelUrl": "https://huggingface.co/mistralai/Mistral-Nemo-Instruct-2407", "preprompt": "", "parameters": { "stop": [""], "temperature": 0.6, "truncate": 14336, "max_new_tokens": 1536 }, "promptExamples": [ { "title": "Write an email from bullet list", "prompt": "As a restaurant owner, write a professional email to the supplier to get these products every week: \n\n- Wine (x10)\n- Eggs (x24)\n- Bread (x12)" }, { "title": "Code a snake game", "prompt": "Code a basic snake game in python, give explanations for each step." }, { "title": "Assist in a task", "prompt": "How do I make a delicious lemon cheesecake?" } ] }, { "name": "microsoft/Phi-3.5-mini-instruct", "description": "One of the best small models (3.8B parameters), super fast for simple tasks.", "logoUrl": "https://huggingface.co/datasets/huggingchat/models-logo/resolve/main/microsoft-logo.png", "modelUrl": "https://huggingface.co/microsoft/Phi-3.5-mini-instruct", "websiteUrl": "https://techcommunity.microsoft.com/t5/ai-azure-ai-services-blog/discover-the-new-multi-lingual-high-quality-phi-3-5-slms/ba-p/4225280/", "preprompt": "", "parameters": { "stop": ["<|end|>", "<|endoftext|>", "<|assistant|>"], "temperature": 0.6, "truncate": 28672, "max_new_tokens": 3072 }, "promptExamples": [ { "title": "Write an email from bullet list", "prompt": "As a restaurant owner, write a professional email to the supplier to get these products every week: \n\n- Wine (x10)\n- Eggs (x24)\n- Bread (x12)" }, { "title": "Code a snake game", "prompt": "Code a basic snake game in python, give explanations for each step." }, { "title": "Assist in a task", "prompt": "How do I make a delicious lemon cheesecake?" } ] }, { "name": "internal/task", "tokenizer" : "NousResearch/Hermes-3-Llama-3.1-8B", "unlisted": true, "tools" : true, "endpoints": [ { "type": "openai", "baseURL": "https://internal.api-inference.huggingface.co/models/NousResearch/Hermes-3-Llama-3.1-8B/v1" } ], "parameters": { "temperature": 0.1, "max_new_tokens": 256 }, } ] NODE_ENV: "prod" NODE_LOG_STRUCTURED_DATA: true OLD_MODELS: > [ { "name": "bigcode/starcoder" }, { "name": "OpenAssistant/oasst-sft-6-llama-30b-xor" }, { "name": "HuggingFaceH4/zephyr-7b-alpha" }, { "name": "openchat/openchat_3.5" }, { "name": "openchat/openchat-3.5-1210" }, { "name": "tiiuae/falcon-180B-chat" }, { "name": "codellama/CodeLlama-34b-Instruct-hf" }, { "name": "google/gemma-7b-it" }, { "name": "meta-llama/Llama-2-70b-chat-hf" }, { "name": "codellama/CodeLlama-70b-Instruct-hf" }, { "name": "openchat/openchat-3.5-0106" }, { "name": "meta-llama/Meta-Llama-3-70B-Instruct" }, { "name": "meta-llama/Meta-Llama-3.1-405B-Instruct-FP8" }, { "name": "CohereForAI/c4ai-command-r-plus", "transferTo": "CohereForAI/c4ai-command-r-plus-08-2024" }, { "name": "01-ai/Yi-1.5-34B-Chat", "transferTo": "CohereForAI/c4ai-command-r-plus-08-2024" }, { "name": "mistralai/Mixtral-8x7B-Instruct-v0.1", "transferTo": "mistralai/Mistral-Nemo-Instruct-2407" }, { "name": "NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO", "transferTo": "NousResearch/Hermes-3-Llama-3.1-8B" }, { "name": "mistralai/Mistral-7B-Instruct-v0.3", "transferTo": "mistralai/Mistral-Nemo-Instruct-2407" }, { "name": "microsoft/Phi-3-mini-4k-instruct", "transferTo": "microsoft/Phi-3.5-mini-instruct" }, { "name": "meta-llama/Meta-Llama-3.1-70B-Instruct", "transferTo": "meta-llama/Llama-3.3-70B-Instruct" }, { "name": "Qwen/QwQ-32B-Preview", "transferTo": "Qwen/QwQ-32B" } ] PUBLIC_ORIGIN: "https://huggingface.co" PUBLIC_SHARE_PREFIX: "https://hf.co/chat" PUBLIC_ANNOUNCEMENT_BANNERS: > [ { "title": "DeepSeek R1 is now available!", "linkTitle": "Try it out!", "linkHref": "https://huggingface.co/chat/models/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B" } ] PUBLIC_APP_NAME: "HuggingChat" PUBLIC_APP_ASSETS: "huggingchat" PUBLIC_APP_COLOR: "yellow" PUBLIC_APP_DESCRIPTION: "Making the community's best AI chat models available to everyone." PUBLIC_APP_DISCLAIMER_MESSAGE: "Disclaimer: AI is an area of active research with known problems such as biased generation and misinformation. Do not use this application for high-stakes decisions or advice." PUBLIC_APP_GUEST_MESSAGE: "Sign in with a free Hugging Face account to continue using HuggingChat." PUBLIC_APP_DATA_SHARING: 0 PUBLIC_APP_DISCLAIMER: 1 PUBLIC_PLAUSIBLE_SCRIPT_URL: "/js/script.js" REQUIRE_FEATURED_ASSISTANTS: "true" TASK_MODEL: "internal/task" TEXT_EMBEDDING_MODELS: > [{ "name": "bge-base-en-v1-5-sxa", "displayName": "bge-base-en-v1-5-sxa", "chunkCharLength": 512, "endpoints": [{ "type": "tei", "url": "https://huggingchat-tei.hf.space/" }] }] WEBSEARCH_BLOCKLIST: '["youtube.com", "twitter.com"]' XFF_DEPTH: '2' TOOLS: > [ { "_id": "000000000000000000000001", "displayName": "Image Generation", "description": "Use this tool to generate images based on a prompt.", "color": "yellow", "icon": "camera", "baseUrl": "black-forest-labs/FLUX.1-schnell", "name": "image_generation", "endpoint": "/infer", "inputs": [ { "name": "prompt", "description": "A prompt to generate an image from", "paramType": "required", "type": "str" }, { "name": "seed", "paramType": "fixed", "value": "0", "type": "float" }, { "name": "randomize_seed", "paramType": "fixed", "value": "true", "type": "bool" }, { "name": "width", "description": "numeric value between 256 and 2048", "paramType": "optional", "default": 1024, "type": "float" }, { "name": "height", "description": "numeric value between 256 and 2048", "paramType": "optional", "default": 1024, "type": "float" }, { "name": "num_inference_steps", "paramType": "fixed", "value": "4", "type": "float" } ], "outputComponent": "image", "outputComponentIdx": 0, "showOutput": true }, { "_id": "000000000000000000000002", "displayName": "Document Parser", "description": "Use this tool to parse any document and get its content in markdown format.", "color": "yellow", "icon": "cloud", "baseUrl": "huggingchat/document-parser", "name": "document_parser", "endpoint": "/predict", "inputs": [ { "name": "document", "description": "Filename of the document to parse", "paramType": "required", "type": "file", "mimeTypes": 'application/*' }, { "name": "filename", "paramType": "fixed", "value": "document.pdf", "type": "str" } ], "outputComponent": "textbox", "outputComponentIdx": 0, "showOutput": false, "isHidden": true }, { "_id": "000000000000000000000003", "name": "edit_image", "baseUrl": "multimodalart/cosxl", "endpoint": "/run_edit", "inputs": [ { "name": "image", "description": "The image path to be edited", "paramType": "required", "type": "file", "mimeTypes": 'image/*' }, { "name": "prompt", "description": "The prompt with which to edit the image", "paramType": "required", "type": "str" }, { "name": "negative_prompt", "paramType": "fixed", "value": "", "type": "str" }, { "name": "guidance_scale", "paramType": "fixed", "value": 6.5, "type": "float" }, { "name": "steps", "paramType": "fixed", "value": 30, "type": "float" } ], "outputComponent": "image", "showOutput": true, "displayName": "Image Editor", "color": "green", "icon": "camera", "description": "This tool lets you edit images", "outputComponentIdx": 0 } ] HF_ORG_ADMIN: '644171cfbd0c97265298aa99' HF_ORG_EARLY_ACCESS: '5e67bd5b1009063689407478' HF_API_ROOT: 'https://internal.api-inference.huggingface.co/models' infisical: enabled: true env: "prod-us-east-1" autoscaling: enabled: true minReplicas: 12 maxReplicas: 30 targetMemoryUtilizationPercentage: "50" targetCPUUtilizationPercentage: "50" resources: requests: cpu: 2 memory: 4Gi limits: cpu: 4 memory: 8Gi monitoring: enabled: true