← Latest products

Like grep but for natural questions. Mixtral 8x7B

28 tok/s on 8GB GPU. Like grep but for natural language questions. Based on Mistral 7B or Mixtral 8x7B. Like grep but for natural language questions.

CLIOpen source

387 stars · GitHubexternal site

Visit github.comexternal site

Reactions (1)

Similar products

by description similarity

  1. OSS implementation of Test Time Diffusion that runs on a 24gb GPU

    github.com

    The implementation of Test Time Diffusion paper by Google with some tweaks to run on 24gb gpu

    Hacker News21 pts

  2. Minimal LLM Post-Training Experiments on an 8GB GPU (SFT

    github.com

    DPO, GRPO)

    Hacker News21 pts

  3. Free Tools for Tabs

    lamucal.com

    Chords, Lyrics Use 8 A100 GPUs

    Hacker News30 pts

  4. Fine-tune an 8B model on a 4 GB laptop GPU

    github.com

    Fine-tune LLMs from one YAML. Layer streaming trains an 8B model on a 4 GB laptop GPU.

    Hacker News139 pts

  5. wc-GPU

    github.com

    The Unix util `wc` running on a GPU

    Hacker News15 pts