Foundation Text-Generation Models Below 360M Parameters Collection Great candidates for fine-tuning targeting Wllama and Transformers.js for mobile devices, ordered by number of parameters. โข 34 items โข Updated 1 day ago โข 27
view post Post 2047 Squeezing out tensor bits, part IIAt post time, watt-ai/watt-tool-70B continues to top the Berkeley Function-Calling Leaderboard, with the 8B version occupying the 4th place. A remarkable achievement for a model of that size!The "squeezed" version is now available at eaddario/Watt-Tool-8B-GGUF(For context please see: https://huggingface.co./posts/eaddario/832567461491467) See translation 2 replies ยท ๐ 4 4 + Reply