Skip to content
@inferless

Inferless

Building World's most reliable Serverless GPU Inference Offering. In Private Beta

Popular repositories Loading

  1. rmbg-1.4 rmbg-1.4 Public template

    State-of-the-art background removal model, designed to effectively separate foreground from background. <metadata> gpu: T4 | collections: ["HF Transformers"] </metadata>

    Python 20 11

  2. triton-co-pilot triton-co-pilot Public

    Generate Glue Code in seconds to simplify your Nvidia Triton Inference Server Deployments

    Python 19 3

  3. Smaug-72B Smaug-72B Public

    Smaug-72B - which topped the Hugging Face LLM leaderboard and it’s the first model with an average score of 80, making it the world’s best open-source foundation model.

    Python 17 5

  4. qwq-32b-preview qwq-32b-preview Public template

    A 32B experimental reasoning model for advanced text generation and robust instruction following. <metadata> gpu: A100 | collections: ["vLLM"] </metadata>

    Python 17 6

  5. whisper-large-v3 whisper-large-v3 Public

    State‑of‑the‑art speech recognition model for English, delivering transcription accuracy across diverse audio scenarios. <metadata> gpu: T4 | collections: ["CTranslate2"] </metadata>

    Python 16 13

  6. deepseek-r1-distill-qwen-32b deepseek-r1-distill-qwen-32b Public template

    A distilled DeepSeek-R1 variant built on Qwen2.5-32B, fine-tuned with curated data for enhanced performance and efficiency. <metadata> gpu: A100 | collections: ["vLLM"] </metadata>

    Python 16 23

Repositories

Showing 10 of 160 repositories
  • DINet Public

    A deformation inpainting network that enables realistic facial dubbing on high-resolution video by seamlessly modifying expressions with advanced inpainting techniques. <metadata> gpu: A100 | collections: ["Using Complex Outputs"] </metadata>

    Python 0 1 0 0 Updated Apr 14, 2025
  • Phi-3.5-MoE-instruct-8bit Public

    Phi-3.5-MoE a compact yet powerful model designed for instruction-following tasks. This model is part of the Phi-3 family, known for its efficiency and high performance. The Phi-3 Mini-128K-Instruct exhibited robust, state-of-the-art performance among models with fewer than 13B parameters.

    Python 0 0 0 0 Updated Apr 13, 2025
  • idefics-9b-instruct-8bit Public

    IDEFICS (Image-aware Decoder Enhanced à la Flamingo with Interleaved Cross-attentionS) is an open-access reproduction of Flamingo, a closed-source visual language model developed by Deepmind. Like GPT-4, the multimodal model accepts arbitrary sequences of image and text inputs and produces text outputs.

    Python 0 3 0 0 Updated Apr 13, 2025
  • Book-Audio-Summary-Generator Public
    Python 0 0 0 0 Updated Apr 12, 2025
  • TenyxChat-8x7B-v1 Public
    Python 0 0 0 0 Updated Apr 12, 2025
  • Command-r-v01 Public

    35B model delivering high performance in reasoning, summarization, and question answering. <metadata> gpu: A100 | collections: ["HF Transformers"] </metadata>

    Python 2 4 0 0 Updated Apr 11, 2025
  • InternVL2-Llama3-76B-AWQ Public
    Python 0 1 0 0 Updated Apr 10, 2025
  • Stable-Diffusion-3.5-large Public
    Python 0 0 0 0 Updated Apr 10, 2025
  • realvis-xl_v4.0_lightning Public

    A lightweight, accelerated variant of RealVisXL V4.0, engineered for real‑time, high‑quality image generation with enhanced efficiency. <metadata> gpu: T4 | collections: ["Diffusers"] </metadata>

    Python 0 6 0 0 Updated Apr 10, 2025
  • tinyllama-1.1b-chat-vllm-gguf Public

    Deploy GGUF quantized version of Tinyllama-1.1B GGUF vLLM for efficient inference. <metadata> gpu: A100 | collections: ["Using NFS Volumes", "vLLM"] </metadata>

    Python 1 7 0 0 Updated Apr 10, 2025
View all repositories

Most used topics

Loading…