Skip to content

Commit 1dd31ab

Browse files
SBrandeisSBrandeis
authored
[Inference Providers] add Public AI (#1918)
* Add Public AI to the docs * re-generate docs
1 parent 0a72ff1 commit 1dd31ab

File tree

11 files changed

+86
-4
lines changed

11 files changed

+86
-4
lines changed

‎docs/inference-providers/_toctree.yml‎

Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -97,6 +97,8 @@
9797
title: Novita
9898
- local: providers/nscale
9999
title: Nscale
100+
- local: providers/publicai
101+
title: Public AI
100102
- local: providers/replicate
101103
title: Replicate
102104
- local: providers/sambanova

‎docs/inference-providers/index.md‎

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -24,6 +24,7 @@ Our platform integrates with leading AI infrastructure providers, giving you acc
2424
| [Nebius](./providers/nebius) | ✅ | ✅ | ✅ | ✅ | | |
2525
| [Novita](./providers/novita) | ✅ | ✅ | | | ✅ | |
2626
| [Nscale](./providers/nscale) | ✅ | ✅ | | ✅ | | |
27+
| [Public AI](./providers/publicai) | ✅ | | | | | |
2728
| [Replicate](./providers/replicate) | | | | ✅ | ✅ | ✅ |
2829
| [SambaNova](./providers/sambanova) | ✅ | | ✅ | | | |
2930
| [Scaleway](./providers/scaleway) | ✅ | | ✅ | | | |

‎docs/inference-providers/providers/hf-inference.md‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -193,7 +193,7 @@ Find out more about Translation [here](../tasks/translation).
193193

194194
<InferenceSnippet
195195
pipeline=translation
196-
providersMapping={ {"hf-inference":{"modelId":"google-t5/t5-base","providerModelId":"google-t5/t5-base"} } }
196+
providersMapping={ {"hf-inference":{"modelId":"google-t5/t5-small","providerModelId":"google-t5/t5-small"} } }
197197
/>
198198

199199

‎docs/inference-providers/providers/publicai.md‎

Lines changed: 57 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,57 @@
1+
<!---
2+
WARNING
3+
4+
This markdown file has been generated from a script. Please do not edit it directly.
5+
6+
### Template
7+
8+
If you want to update the content related to publicai's description, please edit the template file under `https://github.com/huggingface/hub-docs/tree/main/scripts/inference-providers/templates/providers/publicai.handlebars`.
9+
10+
### Logos
11+
12+
If you want to update publicai's logo, upload a file by opening a PR on https://huggingface.co/datasets/huggingface/documentation-images/tree/main/inference-providers/logos. Ping @wauplin and @celinah on the PR to let them know you uploaded a new logo.
13+
Logos must be in .png format and be named `publicai-light.png` and `publicai-dark.png`. Visit https://huggingface.co/settings/theme to switch between light and dark mode and check that the logos are displayed correctly.
14+
15+
### Generation script
16+
17+
For more details, check out the `generate.ts` script: https://github.com/huggingface/hub-docs/blob/main/scripts/inference-providers/scripts/generate.ts.
18+
--->
19+
20+
# PublicAI
21+
22+
<Tip>
23+
24+
All models supported by the PublicAI Inference Utility can be found [here](https://huggingface.co/models?inference_provider=publicai&sort=trending)
25+
26+
</Tip>
27+
28+
<div class="flex justify-center">
29+
<a href="https://publicai.co/" target="_blank">
30+
<img class="block dark:hidden" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/inference-providers/logos/publicai-light.png"/>
31+
<img class="hidden dark:block" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/inference-providers/logos/publicai-dark.png"/>
32+
</a>
33+
</div>
34+
35+
<div class="flex">
36+
<a href="https://huggingface.co/publicai" target="_blank">
37+
<img class="block dark:hidden" src="https://huggingface.co/datasets/huggingface/badges/resolve/main/follow-us-on-hf-lg.svg"/>
38+
<img class="hidden dark:block" src="https://huggingface.co/datasets/huggingface/badges/resolve/main/follow-us-on-hf-lg-dark.svg"/>
39+
</a>
40+
</div>
41+
42+
The Public AI Inference Utility is a nonprofit, open-source project. Their team builds products and organizes advocacy to support the work of public AI model builders like the Swiss AI Initiative, AI Singapore, AI Sweden, and the Barcelona Supercomputing Center.
43+
44+
They believe in public AI — AI as public infrastructure like highways, water, or electricity. Think of a BBC for AI, a public utility for AI, or public libraries for AI.
45+
46+
## Supported tasks
47+
48+
49+
### Chat Completion (LLM)
50+
51+
Find out more about Chat Completion (LLM) [here](../tasks/chat-completion).
52+
53+
<InferenceSnippet
54+
pipeline=text-generation
55+
providersMapping={ {"publicai":{"modelId":"swiss-ai/Apertus-8B-Instruct-2509","providerModelId":"swiss-ai/apertus-8b-instruct"} } }
56+
conversational />
57+

‎docs/inference-providers/tasks/chat-completion.md‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -64,7 +64,7 @@ The API supports:
6464

6565
<InferenceSnippet
6666
pipeline=text-generation
67-
providersMapping={ {"cerebras":{"modelId":"openai/gpt-oss-120b","providerModelId":"gpt-oss-120b"},"cohere":{"modelId":"CohereLabs/command-a-reasoning-08-2025","providerModelId":"command-a-reasoning-08-2025"},"featherless-ai":{"modelId":"meta-llama/Llama-3.1-8B-Instruct","providerModelId":"meta-llama/Meta-Llama-3.1-8B-Instruct"},"fireworks-ai":{"modelId":"deepseek-ai/DeepSeek-V3.1","providerModelId":"accounts/fireworks/models/deepseek-v3p1"},"groq":{"modelId":"openai/gpt-oss-20b","providerModelId":"openai/gpt-oss-20b"},"hf-inference":{"modelId":"HuggingFaceTB/SmolLM3-3B","providerModelId":"HuggingFaceTB/SmolLM3-3B"},"hyperbolic":{"modelId":"Qwen/Qwen3-Next-80B-A3B-Instruct","providerModelId":"Qwen/Qwen3-Next-80B-A3B-Instruct"},"nebius":{"modelId":"openai/gpt-oss-20b","providerModelId":"openai/gpt-oss-20b"},"novita":{"modelId":"deepseek-ai/DeepSeek-V3.1","providerModelId":"deepseek/deepseek-v3.1"},"nscale":{"modelId":"openai/gpt-oss-20b","providerModelId":"openai/gpt-oss-20b"},"sambanova":{"modelId":"meta-llama/Llama-3.1-8B-Instruct","providerModelId":"Meta-Llama-3.1-8B-Instruct"},"scaleway":{"modelId":"openai/gpt-oss-120b","providerModelId":"gpt-oss-120b"},"together":{"modelId":"deepseek-ai/DeepSeek-V3.1","providerModelId":"deepseek-ai/DeepSeek-V3.1"}} }
67+
providersMapping={ {"cerebras":{"modelId":"openai/gpt-oss-120b","providerModelId":"gpt-oss-120b"},"cohere":{"modelId":"CohereLabs/command-a-reasoning-08-2025","providerModelId":"command-a-reasoning-08-2025"},"featherless-ai":{"modelId":"meta-llama/Llama-3.1-8B-Instruct","providerModelId":"meta-llama/Meta-Llama-3.1-8B-Instruct"},"fireworks-ai":{"modelId":"deepseek-ai/DeepSeek-V3.1","providerModelId":"accounts/fireworks/models/deepseek-v3p1"},"groq":{"modelId":"openai/gpt-oss-20b","providerModelId":"openai/gpt-oss-20b"},"hf-inference":{"modelId":"HuggingFaceTB/SmolLM3-3B","providerModelId":"HuggingFaceTB/SmolLM3-3B"},"hyperbolic":{"modelId":"Qwen/Qwen3-Next-80B-A3B-Instruct","providerModelId":"Qwen/Qwen3-Next-80B-A3B-Instruct"},"nebius":{"modelId":"openai/gpt-oss-20b","providerModelId":"openai/gpt-oss-20b"},"novita":{"modelId":"deepseek-ai/DeepSeek-V3.1","providerModelId":"deepseek/deepseek-v3.1"},"nscale":{"modelId":"openai/gpt-oss-20b","providerModelId":"openai/gpt-oss-20b"},"publicai":{"modelId":"swiss-ai/Apertus-8B-Instruct-2509","providerModelId":"swiss-ai/apertus-8b-instruct"},"sambanova":{"modelId":"meta-llama/Llama-3.1-8B-Instruct","providerModelId":"Meta-Llama-3.1-8B-Instruct"},"scaleway":{"modelId":"openai/gpt-oss-120b","providerModelId":"gpt-oss-120b"},"together":{"modelId":"deepseek-ai/DeepSeek-V3.1","providerModelId":"deepseek-ai/DeepSeek-V3.1"}} }
6868
conversational />
6969

7070

‎docs/inference-providers/tasks/image-segmentation.md‎

Lines changed: 0 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -24,7 +24,6 @@ For more details about the `image-segmentation` task, check out its [dedicated p
2424

2525
### Recommended models
2626

27-
- [facebook/mask2former-swin-large-coco-panoptic](https://huggingface.co/facebook/mask2former-swin-large-coco-panoptic): Panoptic segmentation model trained on the COCO (common objects) dataset.
2827

2928
Explore all available models and find the one that suits you best [here](https://huggingface.co/models?inference=warm&pipeline_tag=image-segmentation&sort=trending).
3029

‎docs/inference-providers/tasks/text-classification.md‎

Lines changed: 3 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -26,6 +26,9 @@ For more details about the `text-classification` task, check out its [dedicated
2626

2727
- [distilbert/distilbert-base-uncased-finetuned-sst-2-english](https://huggingface.co/distilbert/distilbert-base-uncased-finetuned-sst-2-english): A robust model trained for sentiment analysis.
2828
- [ProsusAI/finbert](https://huggingface.co/ProsusAI/finbert): A sentiment analysis model specialized in financial sentiment.
29+
- [cardiffnlp/twitter-roberta-base-sentiment-latest](https://huggingface.co/cardiffnlp/twitter-roberta-base-sentiment-latest): A sentiment analysis model specialized in analyzing tweets.
30+
- [papluca/xlm-roberta-base-language-detection](https://huggingface.co/papluca/xlm-roberta-base-language-detection): A model that can classify languages.
31+
- [meta-llama/Prompt-Guard-86M](https://huggingface.co/meta-llama/Prompt-Guard-86M): A model that can classify text generation attacks.
2932

3033
Explore all available models and find the one that suits you best [here](https://huggingface.co/models?inference=warm&pipeline_tag=text-classification&sort=trending).
3134

‎docs/inference-providers/tasks/translation.md‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -33,7 +33,7 @@ Explore all available models and find the one that suits you best [here](https:/
3333

3434
<InferenceSnippet
3535
pipeline=translation
36-
providersMapping={ {"hf-inference":{"modelId":"google-t5/t5-base","providerModelId":"google-t5/t5-base"}} }
36+
providersMapping={ {"hf-inference":{"modelId":"google-t5/t5-small","providerModelId":"google-t5/t5-small"}} }
3737
/>
3838

3939

‎docs/inference-providers/tasks/zero-shot-classification.md‎

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -25,6 +25,7 @@ For more details about the `zero-shot-classification` task, check out its [dedic
2525
### Recommended models
2626

2727
- [facebook/bart-large-mnli](https://huggingface.co/facebook/bart-large-mnli): Powerful zero-shot text classification model.
28+
- [MoritzLaurer/ModernBERT-large-zeroshot-v2.0](https://huggingface.co/MoritzLaurer/ModernBERT-large-zeroshot-v2.0): Cutting-edge zero-shot multilingual text classification model.
2829

2930
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).
3031

‎scripts/inference-providers/scripts/generate.ts‎

Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -44,6 +44,7 @@ const PROVIDERS_HUB_ORGS: Record<string, string> = {
4444
nebius: "nebius",
4545
novita: "novita",
4646
nscale: "nscale",
47+
publicai: "publicai",
4748
replicate: "replicate",
4849
sambanova: "sambanovasystems",
4950
scaleway: "scaleway",
@@ -62,6 +63,7 @@ const PROVIDERS_URLS: Record<string, string> = {
6263
nebius: "https://nebius.com/",
6364
novita: "https://novita.ai/",
6465
nscale: "https://www.nscale.com/",
66+
publicai: "https://publicai.co/",
6567
replicate: "https://replicate.com/",
6668
sambanova: "https://sambanova.ai/",
6769
scaleway: "https://www.scaleway.com",

0 commit comments

Comments
 (0)