
Hugging Face Blog
· 2 min read
Inference for PROs
Today, we're introducing Inference for PRO users - a community offering that gives you access to APIs of curated endpoints for some of the most exciting models available, as well as improved rate limits for the usage of free Inference API. Use the following page to subscribe to PRO.
Hugging Face PRO users now have access to exclusive API endpoints for a curated list of powerful models that benefit from ultra-fast inference powered by text-generation-inference. This is a benefit on top of the free inference API, which is available to all Hugging Face users to facilitate testing and prototyping on 200,000+ models. PRO users enjoy higher rate limits on these models, as well as exclusive access to some of the best models available today.
Contents
- Supported Models
- Getting started with Inference for PROs
- Applications
- Chat with Llama 2 and Code Llama 34B
- Chat with Code Llama 70B
- Code infilling with Code Llama
- Stable Diffusion XL
- Messages API
- Generation Parameters
- Controlling Text Generation
- Controlling Image Generation
- Caching
- Streaming
- Subscribe to PRO
- FAQ
Supported Models
In addition to thousands of public models available in the Hub, PRO users get free access and higher rate limits to the following state-of-the-art models:
| Model | Size | Context Length | Use |
|---|---|---|---|
| Meta Llama 3 Instruct | 8B, 70B | 8k tokens | One of the best chat models |
| Mixtral 8x7B Instruct | 45B MOE | 32k tokens | Performance comparable to top proprietary models |
| Nous Hermes 2 Mixtral 8x7B DPO | 45B MOE | 32k tokens | Further trained over Mixtral 8x7B MoE |
| Zephyr 7B β | 7B | 4k tokens | One of the best chat models at the 7B weight |
| Llama 2 Chat | 7B, 13B | 4k tokens | One of the best conversational models |
| Mistral 7B Instruct v0.2 | 7B | 4k tokens | One of the best chat models at the 7B weight |
| Code Llama Base | 7B and 13B | 4k tokens | Autocomplete and infill code |
| Code Llama Instruct | 34B | 16k tokens | Conversational code assistant |
| Stable Diffusion XL | 3B UNet | - | Generate images |
| Bark | 0.9B | - | Text to audio generation |
pip install huggingface_hub
Original source
This story was published by Hugging Face Blog. SyncAI.news shows a preview; the complete article is on the publisher's site.
Read the full story on huggingface.co


