Skip to content

Commit a86a44a

Browse files
committed
Add HF-Inference page
1 parent bf087a8 commit a86a44a

File tree

5 files changed

+221
-14
lines changed

5 files changed

+221
-14
lines changed

docs/inference-providers/_toctree.yml

Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -21,6 +21,8 @@
2121
title: Fireworks
2222
- local: providers/hyperbolic
2323
title: Hyperbolic
24+
- local: providers/hf-inference
25+
title: HF Inference
2426
- local: providers/nebius
2527
title: Nebius
2628
- local: providers/novita

docs/inference-providers/index.md

Lines changed: 12 additions & 11 deletions
Original file line numberDiff line numberDiff line change
@@ -13,17 +13,18 @@ To learn more about the launch of Inference Providers, check out our [announceme
1313

1414
Here is the complete list of partners integrated with Inference Providers, and the supported tasks for each of them:
1515

16-
| Provider | Chat completion (LLM) | Chat completion (VLM) | Feature Extraction | Text to Image | Text to video |
17-
| ------------------------------------- | :-------------------: | :-------------------: | :----------------: | :-----------: | :-----------: |
18-
| [Cerebras](./providers/cerebras) || | | | |
19-
| [Fal AI](./providers/fal-ai) | | | |||
20-
| [Fireworks](./providers/fireworks-ai) ||| | | |
21-
| [Hyperbolic](./providers/hyperbolic) ||| | | |
22-
| [Nebius](./providers/nebius) ||| || |
23-
| [Novita](./providers/novita) ||| | ||
24-
| [Replicate](./providers/replicate) | | | |||
25-
| [SambaNova](./providers/sambanova) || || | |
26-
| [Together](./providers/together) ||| || |
16+
| Provider | Chat completion (LLM) | Chat completion (VLM) | Feature Extraction | Text to Image | Text to video |
17+
| ---------------------------------------- | :-------------------: | :-------------------: | :----------------: | :-----------: | :-----------: |
18+
| [Cerebras](./providers/cerebras) || | | | |
19+
| [Fal AI](./providers/fal-ai) | | | |||
20+
| [Fireworks](./providers/fireworks-ai) ||| | | |
21+
| [HF Inference](./providers/hf-inference) ||||| |
22+
| [Hyperbolic](./providers/hyperbolic) ||| | | |
23+
| [Nebius](./providers/nebius) ||| || |
24+
| [Novita](./providers/novita) ||| | ||
25+
| [Replicate](./providers/replicate) | | | |||
26+
| [SambaNova](./providers/sambanova) || || | |
27+
| [Together](./providers/together) ||| || |
2728

2829
## Why use Inference Providers?
2930

Lines changed: 199 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,199 @@
1+
<!---
2+
WARNING
3+
4+
This markdown file has been generated from a script. Please do not edit it directly.
5+
6+
If you want to update the content related to hf-inference's description, please edit the template file under `https://github.com/huggingface/hub-docs/tree/main/scripts/inference-providers/templates/providers/hf-inference.handlebars`.
7+
8+
For more details, check out the `generate.ts` script: https://github.com/huggingface/hub-docs/blob/main/scripts/inference-providers/scripts/generate.ts.
9+
--->
10+
11+
# HF Inference
12+
13+
![https://huggingface.co/](https://huggingface.co/datasets/huggingface/brand-assets/resolve/main/hf-logo-with-title.png)
14+
15+
HF Inference is the serverless Inference API powered by Hugging Face. This service used to be called "Inference API (serverless)" prior to Inference Providers.
16+
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.
17+
18+
## Supported tasks
19+
20+
21+
### Audio Classification
22+
23+
Find out more about Audio Classification [here](../tasks/audio_classification).
24+
25+
<InferenceSnippet
26+
pipeline=audio-classification
27+
providersMapping={ {"hf-inference":{"modelId":"ehcalabres/wav2vec2-lg-xlsr-en-speech-emotion-recognition","providerModelId":"ehcalabres/wav2vec2-lg-xlsr-en-speech-emotion-recognition"} } }
28+
/>
29+
30+
31+
### Automatic Speech Recognition
32+
33+
Find out more about Automatic Speech Recognition [here](../tasks/automatic_speech_recognition).
34+
35+
<InferenceSnippet
36+
pipeline=automatic-speech-recognition
37+
providersMapping={ {"hf-inference":{"modelId":"openai/whisper-large-v3-turbo","providerModelId":"openai/whisper-large-v3-turbo"} } }
38+
/>
39+
40+
41+
### Chat Completion (LLM)
42+
43+
Find out more about Chat Completion (LLM) [here](../tasks/chat-completion).
44+
45+
<InferenceSnippet
46+
pipeline=text-generation
47+
providersMapping={ {"hf-inference":{"modelId":"Qwen/QwQ-32B","providerModelId":"Qwen/QwQ-32B"} } }
48+
conversational />
49+
50+
51+
### Chat Completion (VLM)
52+
53+
Find out more about Chat Completion (VLM) [here](../tasks/chat-completion).
54+
55+
<InferenceSnippet
56+
pipeline=image-text-to-text
57+
providersMapping={ {"hf-inference":{"modelId":"google/gemma-3-27b-it","providerModelId":"google/gemma-3-27b-it"} } }
58+
conversational />
59+
60+
61+
### Feature Extraction
62+
63+
Find out more about Feature Extraction [here](../tasks/feature_extraction).
64+
65+
<InferenceSnippet
66+
pipeline=feature-extraction
67+
providersMapping={ {"hf-inference":{"modelId":"intfloat/multilingual-e5-large-instruct","providerModelId":"intfloat/multilingual-e5-large-instruct"} } }
68+
/>
69+
70+
71+
### Fill Mask
72+
73+
Find out more about Fill Mask [here](../tasks/fill_mask).
74+
75+
<InferenceSnippet
76+
pipeline=fill-mask
77+
providersMapping={ {"hf-inference":{"modelId":"google-bert/bert-base-uncased","providerModelId":"google-bert/bert-base-uncased"} } }
78+
/>
79+
80+
81+
### Image Classification
82+
83+
Find out more about Image Classification [here](../tasks/image_classification).
84+
85+
<InferenceSnippet
86+
pipeline=image-classification
87+
providersMapping={ {"hf-inference":{"modelId":"Falconsai/nsfw_image_detection","providerModelId":"Falconsai/nsfw_image_detection"} } }
88+
/>
89+
90+
91+
### Image To Image
92+
93+
Find out more about Image To Image [here](../tasks/image_to_image).
94+
95+
<InferenceSnippet
96+
pipeline=image-to-image
97+
providersMapping={ {"hf-inference":{"modelId":"enhanceaiteam/Flux-Uncensored-V2","providerModelId":"black-forest-labs/FLUX.1-dev"} } }
98+
/>
99+
100+
101+
### Object Detection
102+
103+
Find out more about Object Detection [here](../tasks/object_detection).
104+
105+
<InferenceSnippet
106+
pipeline=object-detection
107+
providersMapping={ {"hf-inference":{"modelId":"facebook/detr-resnet-50","providerModelId":"facebook/detr-resnet-50"} } }
108+
/>
109+
110+
111+
### Question Answering
112+
113+
Find out more about Question Answering [here](../tasks/question_answering).
114+
115+
<InferenceSnippet
116+
pipeline=question-answering
117+
providersMapping={ {"hf-inference":{"modelId":"deepset/gelectra-large-germanquad","providerModelId":"deepset/gelectra-large-germanquad"} } }
118+
/>
119+
120+
121+
### Summarization
122+
123+
Find out more about Summarization [here](../tasks/summarization).
124+
125+
<InferenceSnippet
126+
pipeline=summarization
127+
providersMapping={ {"hf-inference":{"modelId":"facebook/bart-large-cnn","providerModelId":"facebook/bart-large-cnn"} } }
128+
/>
129+
130+
131+
### Text Classification
132+
133+
Find out more about Text Classification [here](../tasks/text_classification).
134+
135+
<InferenceSnippet
136+
pipeline=text-classification
137+
providersMapping={ {"hf-inference":{"modelId":"ProsusAI/finbert","providerModelId":"ProsusAI/finbert"} } }
138+
/>
139+
140+
141+
### Text Generation
142+
143+
Find out more about Text Generation [here](../tasks/text_generation).
144+
145+
<InferenceSnippet
146+
pipeline=text-generation
147+
providersMapping={ {"hf-inference":{"modelId":"Qwen/QwQ-32B","providerModelId":"Qwen/QwQ-32B"} } }
148+
/>
149+
150+
151+
### Text To Image
152+
153+
Find out more about Text To Image [here](../tasks/text_to_image).
154+
155+
<InferenceSnippet
156+
pipeline=text-to-image
157+
providersMapping={ {"hf-inference":{"modelId":"black-forest-labs/FLUX.1-dev","providerModelId":"black-forest-labs/FLUX.1-dev"} } }
158+
/>
159+
160+
161+
### Text To Video
162+
163+
Find out more about Text To Video [here](../tasks/text_to_video).
164+
165+
<InferenceSnippet
166+
pipeline=text-to-video
167+
providersMapping={ {"hf-inference":{"modelId":"AdamLucek/Wan2.1-T2V-14B-OldBookIllustrations","providerModelId":"black-forest-labs/FLUX.1-dev"} } }
168+
/>
169+
170+
171+
### Token Classification
172+
173+
Find out more about Token Classification [here](../tasks/token_classification).
174+
175+
<InferenceSnippet
176+
pipeline=token-classification
177+
providersMapping={ {"hf-inference":{"modelId":"dbmdz/bert-large-cased-finetuned-conll03-english","providerModelId":"dbmdz/bert-large-cased-finetuned-conll03-english"} } }
178+
/>
179+
180+
181+
### Translation
182+
183+
Find out more about Translation [here](../tasks/translation).
184+
185+
<InferenceSnippet
186+
pipeline=translation
187+
providersMapping={ {"hf-inference":{"modelId":"facebook/nllb-200-distilled-600M","providerModelId":"facebook/nllb-200-distilled-600M"} } }
188+
/>
189+
190+
191+
### Zero Shot Classification
192+
193+
Find out more about Zero Shot Classification [here](../tasks/zero_shot_classification).
194+
195+
<InferenceSnippet
196+
pipeline=zero-shot-classification
197+
providersMapping={ {"hf-inference":{"modelId":"facebook/bart-large-mnli","providerModelId":"facebook/bart-large-mnli"} } }
198+
/>
199+

scripts/inference-providers/scripts/generate.ts

Lines changed: 0 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -736,9 +736,6 @@ await Promise.all(
736736

737737
await Promise.all(
738738
Object.entries(PER_PROVIDER_TASKS).map(async ([provider, tasks]) => {
739-
if (provider === "hf-inference") {
740-
return;
741-
}
742739
const rendered = await renderTemplate(provider, "providers", {
743740
tasksSection: PROVIDER_TASKS_TEMPLATE({ tasks }),
744741
});
Lines changed: 8 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,8 @@
1+
# HF Inference
2+
3+
![https://huggingface.co/](https://huggingface.co/datasets/huggingface/brand-assets/resolve/main/hf-logo-with-title.png)
4+
5+
HF Inference is the serverless Inference API powered by Hugging Face. This service used to be called "Inference API (serverless)" prior to Inference Providers.
6+
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.
7+
8+
{{{tasksSection}}}

0 commit comments

Comments
 (0)