Commit Graph

602 Commits (f2f1d7fe72c8205f3740c41de53b4b868f5d72cf)
 

Author SHA1 Message Date
mudler b710147b95 Add mutex on same models (parallel isn't supported yet) 2 years ago
mudler ba70363330 Use template input 2 years ago
mudler 9fb581739b Allow to template model prompts inputs 2 years ago
mudler 48aca246e3 Drop unused interactive mode 2 years ago
mudler 12eee097b7 Make it compatible with openAI api, support multiple models 2 years ago
mudler b33d015b8c Use go-llama.cpp 2 years ago
Ettore Di Giacinto b7c0a108f5
Update README.md 2 years ago
Ettore Di Giacinto f694a89c28
Update README.md 2 years ago
Ettore Di Giacinto be682e6c2f
Update README.md 2 years ago
mudler bf85a31f9e Don't set a default model path 2 years ago
Ettore Di Giacinto d69048e0b0
Update README.md 2 years ago
mudler 827f189163 Update README 2 years ago
mudler a23deb5ec7 Drop duplicate target 2 years ago
mudler 999676b106 Add gpt4all instructions 2 years ago
mudler c61b023bc8 Drop fat images, will document how to consume models 2 years ago
mudler 650a22aef1 Add compatibility to gpt4all models 2 years ago
mudler 17b1724f7c Update llama-go 2 years ago
mudler e860e62036 Add mutex, build only lite images 2 years ago
Ettore Di Giacinto 1f45ff8cd6
Update README.md 2 years ago
mudler abee34f60a Cleanup leftover 2 years ago
mudler dbc70dc13c Add a simple web-page as index of the API for helping with inference testing 2 years ago
mudler 55142065eb Update README with building instructions 2 years ago
mudler d83d2293b5 Update version in kubernetes deployment 2 years ago
mudler 467ce5a7aa Update models download instructions, update images 2 years ago
mudler 4c9c5ce4ce Update README on instruction on how to prompt with the API 2 years ago
mudler 6394d85ca2 Lower conversion parallelism 2 years ago
mudler 2b6a5aef5f Lower earthly parallelism 2 years ago
mudler d191ecb9fe Disable release pipeline 2 years ago
mudler e14e1b0a77 Update README 2 years ago
mudler bffaf2aa42 Build images without model 2 years ago
mudler d98d1fe55e Use models from model repository 2 years ago
mudler 0785cb6b0b Update README with 13B and 30B model instructions 2 years ago
mudler f88d5ad829 Update MODEL_URL 2 years ago
Ettore Di Giacinto c7119a2882
Use tagged image in kubernetes deployment 2 years ago
mudler 8324402b49 Add interactive.go 2 years ago
mudler 9ba30c9c44 Update llama-go, allow to set context-size and enable alpaca model by default 2 years ago
mudler 973042bb4c Update README to use tagged container images 2 years ago
mudler 3ed2888646 Update README 2 years ago
mudler 593ff6308c Add simple client 2 years ago
mudler 4275bfc8c0 Add README 2 years ago
mudler 065815f947 Add kubernetes deployment sample 2 years ago
mudler 0460be964f Fix entrypoint 2 years ago
mudler 6ca13f0227 Cleanup workers to have more free space 2 years ago
mudler e6156b59fc Cleanup 2 years ago
mudler 8da01d768c Update Earthly versions 2 years ago
mudler e764c3225c Workaround Earthly issue 2 years ago
mudler 2ce1d51ad5 No need to set 0 for default context anymore 2 years ago
mudler 37660eeb6d Update go-skynet/llama 2 years ago
mudler 291a8a6d2e Multi-platform Earthly build must be in a target 2 years ago
mudler 896da59b87 Add GitHub action workflows 2 years ago