LukeParke/LocalAI
1
0
Fork 0
mirror of https://github.com/LukeHagar/LocalAI.git synced 2025-12-09 20:47:46 +00:00
Code Issues Packages Projects Releases Wiki Activity

Bump llama.cpp, downgrade gpt4all-j (#149)

Browse Source
This commit is contained in:
Ettore Di Giacinto
2023-05-02 16:07:18 +02:00
committed by GitHub
parent 271d3f6673
commit 156e15a4fa
5 changed files with 14 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
api/prediction.go
View File

@@ -37,7 +37,7 @@ func ModelInference(s string, loader *model.ModelLoader, c Config) (func() (stri
// TODO: this is ugly, better identifying the model somehow! however, it is a good stab for a first implementation..
model, llamaerr = loader.LoadLLaMAModel(modelFile, llamaOpts...)
if llamaerr != nil {
gptModel, gptjerr = loader.LoadGPTJModel(modelFile, gptj.SetThreads(c.Threads))
gptModel, gptjerr = loader.LoadGPTJModel(modelFile)
if gptjerr != nil {
gpt2Model, gpt2err = loader.LoadGPT2Model(modelFile)
if gpt2err != nil {
@@ -108,12 +108,17 @@ func ModelInference(s string, loader *model.ModelLoader, c Config) (func() (stri
gptj.SetTopP(c.TopP),
gptj.SetTopK(c.TopK),
gptj.SetTokens(c.Maxtokens),
gptj.SetThreads(c.Threads),
}
if c.Batch != 0 {
predictOptions = append(predictOptions, gptj.SetBatch(c.Batch))
}
if c.Seed != 0 {
predictOptions = append(predictOptions, gptj.SetSeed(c.Seed))
}
return gptModel.Predict(
s,
predictOptions...,