matt/ollama37
1
0
Fork 0
mirror of https://github.com/dogkeeper886/ollama37.git synced 2025-12-12 00:37:04 +00:00
Code Issues Packages Projects Releases Wiki Activity

remove tmp directories created by previous servers (#559)

Browse Source 
* remove tmp directories created by previous servers

* clean up on server stop

* Update routes.go

* Update server/routes.go

Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>

* create top-level temp ollama dir

* check file exists before creating

---------

Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>
Co-authored-by: Michael Yang <mxyng@pm.me>
This commit is contained in:
Bruce MacDonald
2023-09-21 20:38:49 +01:00
committed by GitHub
parent 8c83701e9f
commit 4cba75efc5
6 changed files with 56 additions and 60 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
llm/llm.go
View File

@@ -21,7 +21,7 @@ type LLM interface {
Ping(context.Context) error
}
func New(model string, adapters []string, opts api.Options) (LLM, error) {
func New(workDir, model string, adapters []string, opts api.Options) (LLM, error) {
if _, err := os.Stat(model); err != nil {
return nil, err
}
@@ -91,9 +91,9 @@ func New(model string, adapters []string, opts api.Options) (LLM, error) {
switch ggml.Name() {
case "gguf":
opts.NumGQA = 0 // TODO: remove this when llama.cpp runners differ enough to need separate newLlama functions
return newLlama(model, adapters, ggufRunner(), opts)
return newLlama(model, adapters, chooseRunners(workDir, "gguf"), opts)
case "ggml", "ggmf", "ggjt", "ggla":
return newLlama(model, adapters, ggmlRunner(), opts)
return newLlama(model, adapters, chooseRunners(workDir, "ggml"), opts)
default:
return nil, fmt.Errorf("unknown ggml type: %s", ggml.ModelFamily())
}