diff --git a/docs/inference-providers/providers/featherless-ai.md b/docs/inference-providers/providers/featherless-ai.md
index 5eb562045..1353a0cc1 100644
--- a/docs/inference-providers/providers/featherless-ai.md
+++ b/docs/inference-providers/providers/featherless-ai.md
@@ -52,7 +52,7 @@ Find out more about Chat Completion (LLM) [here](../tasks/chat-completion).
@@ -62,7 +62,7 @@ Find out more about Chat Completion (VLM) [here](../tasks/chat-completion).
@@ -72,6 +72,6 @@ Find out more about Text Generation [here](../tasks/text_generation).
diff --git a/docs/inference-providers/providers/groq.md b/docs/inference-providers/providers/groq.md
index 2d77a0c61..9eb478646 100644
--- a/docs/inference-providers/providers/groq.md
+++ b/docs/inference-providers/providers/groq.md
@@ -60,7 +60,7 @@ Find out more about Chat Completion (LLM) [here](../tasks/chat-completion).
diff --git a/docs/inference-providers/providers/hf-inference.md b/docs/inference-providers/providers/hf-inference.md
index 355909840..d1d6c87fe 100644
--- a/docs/inference-providers/providers/hf-inference.md
+++ b/docs/inference-providers/providers/hf-inference.md
@@ -42,6 +42,8 @@ All supported HF Inference models can be found [here](https://huggingface.co/mod
HF Inference is the serverless Inference API powered by Hugging Face. This service used to be called "Inference API (serverless)" prior to Inference Providers.
If you are interested in deploying models to a dedicated and autoscaling infrastructure managed by Hugging Face, check out [Inference Endpoints](https://huggingface.co/docs/inference-endpoints/index) instead.
+As of July 2025, hf-inference focuses mostly on CPU inference (e.g. embedding, text-ranking, text-classification, or smaller LLMs that have historical importance like BERT or GPT-2).
+
## Supported tasks
@@ -55,6 +57,16 @@ Find out more about Automatic Speech Recognition [here](../tasks/automatic_speec
/>
+### Chat Completion (LLM)
+
+Find out more about Chat Completion (LLM) [here](../tasks/chat-completion).
+
+
+
+
### Chat Completion (VLM)
Find out more about Chat Completion (VLM) [here](../tasks/chat-completion).
@@ -101,7 +113,7 @@ Find out more about Image Segmentation [here](../tasks/image_segmentation).
@@ -155,6 +167,16 @@ Find out more about Text Classification [here](../tasks/text_classification).
/>
+### Text Generation
+
+Find out more about Text Generation [here](../tasks/text_generation).
+
+
+
+
### Text To Image
Find out more about Text To Image [here](../tasks/text_to_image).
@@ -184,3 +206,13 @@ Find out more about Translation [here](../tasks/translation).
providersMapping={ {"hf-inference":{"modelId":"google-t5/t5-base","providerModelId":"google-t5/t5-base"} } }
/>
+
+### Zero Shot Classification
+
+Find out more about Zero Shot Classification [here](../tasks/zero_shot_classification).
+
+
+
diff --git a/docs/inference-providers/providers/nebius.md b/docs/inference-providers/providers/nebius.md
index ddc50921c..a23441bef 100644
--- a/docs/inference-providers/providers/nebius.md
+++ b/docs/inference-providers/providers/nebius.md
@@ -74,6 +74,16 @@ Find out more about Feature Extraction [here](../tasks/feature_extraction).
/>
+### Text Generation
+
+Find out more about Text Generation [here](../tasks/text_generation).
+
+
+
+
### Text To Image
Find out more about Text To Image [here](../tasks/text_to_image).
diff --git a/docs/inference-providers/providers/novita.md b/docs/inference-providers/providers/novita.md
index 82a826c09..8ebb67a1f 100644
--- a/docs/inference-providers/providers/novita.md
+++ b/docs/inference-providers/providers/novita.md
@@ -52,7 +52,7 @@ Find out more about Chat Completion (LLM) [here](../tasks/chat-completion).
@@ -62,7 +62,7 @@ Find out more about Chat Completion (VLM) [here](../tasks/chat-completion).
diff --git a/docs/inference-providers/providers/together.md b/docs/inference-providers/providers/together.md
index 07a9c9574..13dac88cb 100644
--- a/docs/inference-providers/providers/together.md
+++ b/docs/inference-providers/providers/together.md
@@ -50,7 +50,7 @@ Find out more about Chat Completion (LLM) [here](../tasks/chat-completion).
@@ -70,7 +70,7 @@ Find out more about Text Generation [here](../tasks/text_generation).
diff --git a/docs/inference-providers/tasks/chat-completion.md b/docs/inference-providers/tasks/chat-completion.md
index 13bd80bd5..aeecd1f30 100644
--- a/docs/inference-providers/tasks/chat-completion.md
+++ b/docs/inference-providers/tasks/chat-completion.md
@@ -63,7 +63,7 @@ The API supports:
@@ -73,7 +73,7 @@ conversational />
@@ -108,7 +108,7 @@ conversational />
| ** (#2)** | _object_ | |
| ** tool_calls*** | _object[]_ | |
| ** function*** | _object_ | |
-| ** parameters*** | _unknown_ | |
+| ** parameters** | _unknown_ | |
| ** description** | _string_ | |
| ** name*** | _string_ | |
| ** id*** | _string_ | |
@@ -145,7 +145,7 @@ conversational />
| **tool_prompt** | _string_ | A prompt to be appended before the tools |
| **tools** | _object[]_ | A list of tools the model may call. Currently, only functions are supported as a tool. Use this to provide a list of functions the model may generate JSON inputs for. |
| ** function*** | _object_ | |
-| ** parameters*** | _unknown_ | |
+| ** parameters** | _unknown_ | |
| ** description** | _string_ | |
| ** name*** | _string_ | |
| ** type*** | _string_ | |
diff --git a/docs/inference-providers/tasks/image-segmentation.md b/docs/inference-providers/tasks/image-segmentation.md
index 197800740..24f69d233 100644
--- a/docs/inference-providers/tasks/image-segmentation.md
+++ b/docs/inference-providers/tasks/image-segmentation.md
@@ -34,7 +34,7 @@ Explore all available models and find the one that suits you best [here](https:/
diff --git a/docs/inference-providers/tasks/image-text-to-text.md b/docs/inference-providers/tasks/image-text-to-text.md
index 1af52a723..e10b4ae73 100644
--- a/docs/inference-providers/tasks/image-text-to-text.md
+++ b/docs/inference-providers/tasks/image-text-to-text.md
@@ -33,7 +33,7 @@ Explore all available models and find the one that suits you best [here](https:/
diff --git a/docs/inference-providers/tasks/text-generation.md b/docs/inference-providers/tasks/text-generation.md
index 51ecfbcbb..f7f06373f 100644
--- a/docs/inference-providers/tasks/text-generation.md
+++ b/docs/inference-providers/tasks/text-generation.md
@@ -41,7 +41,7 @@ Explore all available models and find the one that suits you best [here](https:/
diff --git a/docs/inference-providers/tasks/zero-shot-classification.md b/docs/inference-providers/tasks/zero-shot-classification.md
index d046ba432..1c57edfb9 100644
--- a/docs/inference-providers/tasks/zero-shot-classification.md
+++ b/docs/inference-providers/tasks/zero-shot-classification.md
@@ -24,13 +24,17 @@ For more details about the `zero-shot-classification` task, check out its [dedic
### Recommended models
+- [facebook/bart-large-mnli](https://huggingface.co/facebook/bart-large-mnli): Powerful zero-shot text classification model.
Explore all available models and find the one that suits you best [here](https://huggingface.co/models?inference=warm&pipeline_tag=zero-shot-classification&sort=trending).
### Using the API
-There are currently no snippet examples for the **zero-shot-classification** task, as no providers support it yet.
+
diff --git a/scripts/inference-providers/package.json b/scripts/inference-providers/package.json
index 0298ebcef..293a272ae 100644
--- a/scripts/inference-providers/package.json
+++ b/scripts/inference-providers/package.json
@@ -14,8 +14,8 @@
"author": "",
"license": "ISC",
"dependencies": {
- "@huggingface/inference": "^4.3.2",
- "@huggingface/tasks": "^0.19.22",
+ "@huggingface/inference": "^4.5.3",
+ "@huggingface/tasks": "^0.19.27",
"@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
index 36efe78c1..89e8a0096 100644
--- a/scripts/inference-providers/pnpm-lock.yaml
+++ b/scripts/inference-providers/pnpm-lock.yaml
@@ -9,11 +9,11 @@ importers:
.:
dependencies:
'@huggingface/inference':
- specifier: ^4.3.2
- version: 4.3.2
+ specifier: ^4.5.3
+ version: 4.5.3
'@huggingface/tasks':
- specifier: ^0.19.22
- version: 0.19.22
+ specifier: ^0.19.27
+ version: 0.19.27
'@types/node':
specifier: ^22.5.0
version: 22.5.0
@@ -189,16 +189,16 @@ packages:
cpu: [x64]
os: [win32]
- '@huggingface/inference@4.3.2':
- resolution: {integrity: sha512-c7MJJPDbhb0Xy3JHvO3LaRhCDnfAthdmV3UiLCYH440UkIkECGwaLHAsWg9G2gdUrmcfzybZvZ0lAQhwsiTKnA==}
+ '@huggingface/inference@4.5.3':
+ resolution: {integrity: sha512-SAWKT+e32jSfxwYkRaBQx1rlfgzkHCu0PXbCbOpY0Pvx6Si5wHia2BzZZdwgrpldaRbmFClxmNJy6lfCzQYfOw==}
engines: {node: '>=18'}
- '@huggingface/jinja@0.5.0':
- resolution: {integrity: sha512-Ptc03/jGRiYRoi0bUYKZ14MkDslsBRT24oxmsvUlfYrvQMldrxCevhPnT+hfX8awKTT8/f/0ZBBWldoeAcMHdQ==}
+ '@huggingface/jinja@0.5.1':
+ resolution: {integrity: sha512-yUZLld4lrM9iFxHCwFQ7D1HW2MWMwSbeB7WzWqFYDWK+rEb+WldkLdAJxUPOmgICMHZLzZGVcVjFh3w/YGubng==}
engines: {node: '>=18'}
- '@huggingface/tasks@0.19.22':
- resolution: {integrity: sha512-jtRXsJZTES01X4gJ5VOUnEm3ONyyfXUcWKObbWkr/SQmjaH/kxtWqc2zVWKaxL4QLoXqXJ+T+Pi5xupMStSudQ==}
+ '@huggingface/tasks@0.19.27':
+ resolution: {integrity: sha512-0UT2+SU5zWDrvlEcdVDrvUe2idNeblgBuS9AqDaDsaDV2KphmT5rvvYji6fDJCIUXFnoqg/TB4cn5b8yGXSr8w==}
'@jridgewell/resolve-uri@3.1.2':
resolution: {integrity: sha512-bRISgCIjP20/tbWSPWMEi54QVPRZExkuD9lJL+UIxUKtwVJA8wW1Trb1jMs1RFXo1CBTNZ/5hpC9QvmKWdopKw==}
@@ -415,14 +415,14 @@ snapshots:
'@esbuild/win32-x64@0.23.1':
optional: true
- '@huggingface/inference@4.3.2':
+ '@huggingface/inference@4.5.3':
dependencies:
- '@huggingface/jinja': 0.5.0
- '@huggingface/tasks': 0.19.22
+ '@huggingface/jinja': 0.5.1
+ '@huggingface/tasks': 0.19.27
- '@huggingface/jinja@0.5.0': {}
+ '@huggingface/jinja@0.5.1': {}
- '@huggingface/tasks@0.19.22': {}
+ '@huggingface/tasks@0.19.27': {}
'@jridgewell/resolve-uri@3.1.2': {}