Commit History

Author SHA1 Message Date
  Michael Yang fb6cbc02fb update named templates 10 months ago
  Michael Yang 9b6c2e6eb6 detect chat template from KV 11 months ago
  Michael Yang 171eb040fc simplify safetensors reading 11 months ago
  Michael Yang 34d5ef29b3 fix conversion for f16 or f32 inputs 1 year ago
  jmorganca 63a453554d `go mod tidy` 11 months ago
  Patrick Devine 1e1634daca update go deps (#4324) 1 year ago
  Patrick Devine 9f8691c6c8 Add llama2 / torch models for `ollama create` (#3607) 1 year ago
  Patrick Devine 5a5efee46b Add gemma safetensors conversion (#3250) 1 year ago
  Patrick Devine 1b272d5bcd change `github.com/jmorganca/ollama` to `github.com/ollama/ollama` (#3347) 1 year ago
  Patrick Devine 2c017ca441 Convert Safetensors to an Ollama model (#2824) 1 year ago
  Michael Yang fc483274ad clean up go.mod 1 year ago
  vinjn 66ef308abd Import "containerd/console" lib to support colorful output in Windows terminal 1 year ago
  Daniel Hiltgen 29e90cc13b Implement new Go based Desktop app 1 year ago
  Daniel Hiltgen ecbfc0182f Go bump to v1.21 to pick up slog 1 year ago
  Daniel Hiltgen 39928a42e8 Always dynamically load the llm server library 1 year ago
  Daniel Hiltgen d4cd695759 Add cgo implementation for llama.cpp 1 year ago
  Patrick Devine 630518f0d9 Add unit test of API routes (#1528) 1 year ago
  Michael Yang 7232f1fa41 go mod tidy 1 year ago
  Michael Yang 01ea6002c4 replace go-humanize with format.HumanBytes 1 year ago
  Michael Yang 341fb7e35f go mod tidy 1 year ago
  Patrick Devine deeac961bb new readline library (#847) 1 year ago
  Ajay Kemparaj bb8464c0d2 update golang.org/x/net fixes CVE-2023-3978,CVE-2023-39325,CVE-2023-44487 (#855) 1 year ago
  Bruce MacDonald a0c3e989de deprecate modelfile embed command (#759) 1 year ago
  Michael Yang 8544edca21 parallel chunked downloads 1 year ago
  Patrick Devine 87d9efb364 switch to forked readline lib which doesn't wreck the repl prompt (#578) 1 year ago
  Michael Yang e9f6df7dca use slices.DeleteFunc 1 year ago
  Bruce MacDonald 42998d797d subprocess llama.cpp server (#401) 1 year ago
  Michael Yang d791df75dd check memory requirements before loading 1 year ago
  Bruce MacDonald a6f6d18f83 embed text document in modelfile 1 year ago
  Bruce MacDonald 1c5a8770ee read runner parameter options from map 1 year ago