Fix CI bot (#1687)

Wauplin · HuggingFaceInfra · web-flow · commit 6caea2cb7e4b · 2025-04-15T17:07:34.000+02:00
* Fix CI bot * more logs * remove logs + auth if no auth * rename * add * Update Inference Providers documentation (automated) (#1688) Co-authored-by: Wauplin <11801849+Wauplin@users.noreply.github.com> --------- Co-authored-by: HuggingFaceInfra <148469759+HuggingFaceInfra@users.noreply.github.com> Co-authored-by: Wauplin <11801849+Wauplin@users.noreply.github.com>
diff --git a/.github/workflows/generate_inference_providers_documentation.yml b/.github/workflows/generate_inference_providers_documentation.yml
@@ -1,12 +1,12 @@
-name: Update Inference Providers Documentation
+name: Generate Inference Providers Documentation
 
 on:
   workflow_dispatch:
   schedule:
     - cron: "0 3 * * *" # Every day at 3am
 
 concurrency:
-  group: api_inference_generate_documentation
+  group: generate_inference_providers_documentation
   cancel-in-progress: true
 
 jobs:
@@ -29,7 +29,7 @@ jobs:
       - name: Update huggingface/tasks package
         working-directory: ./scripts/inference-providers
         run: |
-          pnpm update @huggingface/tasks@latest
+          pnpm update @huggingface/tasks@latest @huggingface/inference@latest
       # Generate
       - name: Generate Inference Providers documentation
         run: pnpm run generate
@@ -62,14 +62,14 @@ jobs:
           delete-branch: true
           title: "[Bot] Update Inference Providers documentation"
           body: |
-            This PR automatically upgrades the `@huggingface/tasks` package and regenerates the Inference Providers documentation by running:
+            This PR automatically upgrades the `@huggingface/tasks` and `@huggingface/inference` packages and regenerates the Inference Providers documentation by running:
             ```sh
             cd scripts/inference-providers
-            pnpm update @huggingface/tasks@latest
+            pnpm update @huggingface/tasks@latest @huggingface/inference@latest
             pnpm run generate
             ```
 
-            This PR was automatically created by the [Update Inference Providers Documentation workflow](https://github.com/huggingface/hub-docs/blob/main/.github/workflows/api_inference_generate_documentation.yml).
+            This PR was automatically created by the [Update Inference Providers Documentation workflow](https://github.com/huggingface/hub-docs/blob/main/.github/workflows/generate_inference_providers_documentation.yml).
 
             Please review the changes before merging.
           reviewers: |
diff --git a/docs/inference-providers/tasks/audio-classification.md b/docs/inference-providers/tasks/audio-classification.md
@@ -38,7 +38,10 @@ Explore all available models and find the one that suits you best [here](https:/
 ### Using the API
 
 
-No snippet available for this task.
+<InferenceSnippet
+    pipeline=audio-classification
+    providersMapping={ {"hf-inference":{"modelId":"ehcalabres/wav2vec2-lg-xlsr-en-speech-emotion-recognition","providerModelId":"ehcalabres/wav2vec2-lg-xlsr-en-speech-emotion-recognition"}} }
+/>
 
 
 
diff --git a/docs/inference-providers/tasks/chat-completion.md b/docs/inference-providers/tasks/chat-completion.md
@@ -60,7 +60,7 @@ The API supports:
 
 <InferenceSnippet
     pipeline=text-generation
-    providersMapping={ {"cerebras":{"modelId":"meta-llama/Llama-3.3-70B-Instruct","providerModelId":"llama-3.3-70b"},"fireworks-ai":{"modelId":"Qwen/QwQ-32B","providerModelId":"accounts/fireworks/models/qwq-32b"},"hf-inference":{"modelId":"Qwen/QwQ-32B","providerModelId":"Qwen/QwQ-32B"},"hyperbolic":{"modelId":"Qwen/QwQ-32B","providerModelId":"Qwen/QwQ-32B"},"nebius":{"modelId":"Qwen/QwQ-32B","providerModelId":"Qwen/QwQ-32B-fast"},"novita":{"modelId":"Qwen/QwQ-32B","providerModelId":"qwen/qwq-32b"},"sambanova":{"modelId":"Qwen/QwQ-32B","providerModelId":"QwQ-32B"},"together":{"modelId":"deepseek-ai/DeepSeek-R1","providerModelId":"deepseek-ai/DeepSeek-R1"}} }
+    providersMapping={ {"cerebras":{"modelId":"meta-llama/Llama-3.3-70B-Instruct","providerModelId":"llama-3.3-70b"},"fireworks-ai":{"modelId":"deepseek-ai/DeepSeek-V3-0324","providerModelId":"accounts/fireworks/models/deepseek-v3-0324"},"hf-inference":{"modelId":"Qwen/QwQ-32B","providerModelId":"Qwen/QwQ-32B"},"hyperbolic":{"modelId":"deepseek-ai/DeepSeek-V3-0324","providerModelId":"deepseek-ai/DeepSeek-V3-0324"},"nebius":{"modelId":"deepseek-ai/DeepSeek-V3-0324","providerModelId":"deepseek-ai/DeepSeek-V3-0324-fast"},"novita":{"modelId":"deepseek-ai/DeepSeek-V3-0324","providerModelId":"deepseek/deepseek-v3-0324"},"sambanova":{"modelId":"deepseek-ai/DeepSeek-V3-0324","providerModelId":"DeepSeek-V3-0324"},"together":{"modelId":"deepseek-ai/DeepSeek-R1","providerModelId":"deepseek-ai/DeepSeek-R1"}} }
 conversational />
 
 
@@ -70,7 +70,7 @@ conversational />
 
 <InferenceSnippet
     pipeline=image-text-to-text
-    providersMapping={ {"fireworks-ai":{"modelId":"meta-llama/Llama-3.2-11B-Vision-Instruct","providerModelId":"accounts/fireworks/models/llama-v3p2-11b-vision-instruct"},"hf-inference":{"modelId":"google/gemma-3-27b-it","providerModelId":"google/gemma-3-27b-it"},"hyperbolic":{"modelId":"Qwen/Qwen2.5-VL-7B-Instruct","providerModelId":"Qwen/Qwen2.5-VL-7B-Instruct"},"nebius":{"modelId":"google/gemma-3-27b-it","providerModelId":"google/gemma-3-27b-it-fast"},"novita":{"modelId":"meta-llama/Llama-3.2-11B-Vision-Instruct","providerModelId":"meta-llama/llama-3.2-11b-vision-instruct"},"sambanova":{"modelId":"meta-llama/Llama-3.2-11B-Vision-Instruct","providerModelId":"Llama-3.2-11B-Vision-Instruct"},"together":{"modelId":"meta-llama/Llama-3.2-11B-Vision-Instruct","providerModelId":"meta-llama/Llama-3.2-11B-Vision-Instruct"}} }
+    providersMapping={ {"fireworks-ai":{"modelId":"meta-llama/Llama-4-Scout-17B-16E-Instruct","providerModelId":"accounts/fireworks/models/llama4-scout-instruct-basic"},"hf-inference":{"modelId":"google/gemma-3-27b-it","providerModelId":"google/gemma-3-27b-it"},"hyperbolic":{"modelId":"Qwen/Qwen2.5-VL-7B-Instruct","providerModelId":"Qwen/Qwen2.5-VL-7B-Instruct"},"nebius":{"modelId":"google/gemma-3-27b-it","providerModelId":"google/gemma-3-27b-it-fast"},"novita":{"modelId":"meta-llama/Llama-4-Scout-17B-16E-Instruct","providerModelId":"meta-llama/llama-4-scout-17b-16e-instruct"},"sambanova":{"modelId":"meta-llama/Llama-4-Scout-17B-16E-Instruct","providerModelId":"Llama-4-Scout-17B-16E-Instruct"},"together":{"modelId":"meta-llama/Llama-4-Scout-17B-16E-Instruct","providerModelId":"meta-llama/Llama-4-Scout-17B-16E-Instruct"}} }
 conversational />
 
 
diff --git a/docs/inference-providers/tasks/fill-mask.md b/docs/inference-providers/tasks/fill-mask.md
@@ -33,7 +33,7 @@ Explore all available models and find the one that suits you best [here](https:/
 
 <InferenceSnippet
     pipeline=fill-mask
-    providersMapping={ {"hf-inference":{"modelId":"Rostlab/prot_bert","providerModelId":"Rostlab/prot_bert"}} }
+    providersMapping={ {"hf-inference":{"modelId":"google-bert/bert-base-uncased","providerModelId":"google-bert/bert-base-uncased"}} }
 />
 
 
diff --git a/docs/inference-providers/tasks/image-segmentation.md b/docs/inference-providers/tasks/image-segmentation.md
@@ -32,10 +32,7 @@ Explore all available models and find the one that suits you best [here](https:/
 ### Using the API
 
 
-<InferenceSnippet
-    pipeline=image-segmentation
-    providersMapping={ {"hf-inference":{"modelId":"jonathandinu/face-parsing","providerModelId":"jonathandinu/face-parsing"}} }
-/>
+No snippet available for this task.
 
 
 
diff --git a/docs/inference-providers/tasks/question-answering.md b/docs/inference-providers/tasks/question-answering.md
@@ -35,7 +35,7 @@ Explore all available models and find the one that suits you best [here](https:/
 
 <InferenceSnippet
     pipeline=question-answering
-    providersMapping={ {"hf-inference":{"modelId":"distilbert/distilbert-base-cased-distilled-squad","providerModelId":"distilbert/distilbert-base-cased-distilled-squad"}} }
+    providersMapping={ {"hf-inference":{"modelId":"deepset/gelectra-large-germanquad","providerModelId":"deepset/gelectra-large-germanquad"}} }
 />
 
 
diff --git a/docs/inference-providers/tasks/text-to-video.md b/docs/inference-providers/tasks/text-to-video.md
@@ -55,15 +55,10 @@ Explore all available models and find the one that suits you best [here](https:/
 | **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;seed** | _integer_ | Seed for the random number generator. |
 
 
-Some options can be configured by passing headers to the Inference API. Here are the available headers:
-
 | Headers |   |    |
 | :--- | :--- | :--- |
-| **authorization** | _string_ | Authentication header in the form `'Bearer: hf_****'` when `hf_****` is a personal user access token with Inference API permission. You can generate one from [your settings page](https://huggingface.co/settings/tokens). |
-| **x-use-cache** | _boolean, default to `true`_ | There is a cache layer on the inference API to speed up requests we have already seen. Most models can use those results as they are deterministic (meaning the outputs will be the same anyway). However, if you use a nondeterministic model, you can set this parameter to prevent the caching mechanism from being used, resulting in a real new query. Read more about caching [here](../parameters#caching]). |
-| **x-wait-for-model** | _boolean, default to `false`_ | If the model is not ready, wait for it instead of receiving 503. It limits the number of requests required to get your inference done. It is advised to only set this flag to true after receiving a 503 error, as it will limit hanging in your application to known places. Read more about model availability [here](../overview#eligibility]). |
+| **authorization** | _string_ | Authentication header in the form `'Bearer: hf_****'` when `hf_****` is a personal user access token with "Inference Providers" permission. You can generate one from [your settings page](https://huggingface.co/settings/tokens/new?ownUserPermissions=inference.serverless.write&tokenType=fineGrained). |
 
-For more information about Inference API headers, check out the parameters [guide](../parameters).
 
 #### Response
 
diff --git a/docs/inference-providers/tasks/token-classification.md b/docs/inference-providers/tasks/token-classification.md
@@ -36,7 +36,7 @@ Explore all available models and find the one that suits you best [here](https:/
 
 <InferenceSnippet
     pipeline=token-classification
-    providersMapping={ {"hf-inference":{"modelId":"dslim/bert-base-NER","providerModelId":"dslim/bert-base-NER"}} }
+    providersMapping={ {"hf-inference":{"modelId":"dbmdz/bert-large-cased-finetuned-conll03-english","providerModelId":"dbmdz/bert-large-cased-finetuned-conll03-english"}} }
 />
 
 
diff --git a/scripts/inference-providers/package.json b/scripts/inference-providers/package.json
@@ -14,8 +14,8 @@
   "author": "",
   "license": "ISC",
   "dependencies": {
-    "@huggingface/inference": "^3.6.1",
-    "@huggingface/tasks": "^0.18.4",
+    "@huggingface/inference": "^3.7.1",
+    "@huggingface/tasks": "^0.18.7",
     "@types/node": "^22.5.0",
     "handlebars": "^4.7.8",
     "node": "^20.17.0",
diff --git a/scripts/inference-providers/pnpm-lock.yaml b/scripts/inference-providers/pnpm-lock.yaml
diff --git a/scripts/inference-providers/scripts/generate.ts b/scripts/inference-providers/scripts/generate.ts
@@ -29,7 +29,9 @@ const TASKS: PipelineType[] = [
 const TASKS_EXTENDED = [...TASKS, "chat-completion"];
 const SPECS_REVISION = "main";
 
-const HEADERS = { Authorization: `Bearer ${process.env.HF_TOKEN}` };
+const HEADERS: Record<string, string> = process.env.HF_TOKEN
+  ? { Authorization: `Bearer ${process.env.HF_TOKEN}` }
+  : {};
 
 const PROVIDERS_HUB_ORGS: Record<string, string> = {
   cerebras: "cerebras",
@@ -511,6 +513,9 @@ async function fetchWarmModels(
           tags: string[];
         }[];
         if (modelsData.length === 0) {
+          console.warn(
+            `   ⚠️  No warm model found for ${task} from ${provider}`
+          );
           return;
         }
 
