Mirror/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2024-06-07 19:40:48 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix: pass prediction options when using the model

Browse Source
This commit is contained in:
mudler 2023-05-05 15:56:02 +02:00
parent e96eadab40
commit 64c0a7967f
1 changed files with 58 additions and 51 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

109
api/prediction.go
View File

@ -56,7 +56,8 @@ func ModelEmbedding(s string, loader *model.ModelLoader, c Config) (func() ([]fl
switch model := inferenceModel.(type) {
case *llama.LLama:
fn = func() ([]float32, error) {
return model.Embeddings(s)
predictOptions := buildLLamaPredictOptions(c)
return model.Embeddings(s, predictOptions...)
}
default:
fn = func() ([]float32, error) {
@ -81,6 +82,61 @@ func ModelEmbedding(s string, loader *model.ModelLoader, c Config) (func() ([]fl
}, nil
}
func buildLLamaPredictOptions(c Config) []llama.PredictOption {
// Generate the prediction using the language model
predictOptions := []llama.PredictOption{
llama.SetTemperature(c.Temperature),
llama.SetTopP(c.TopP),
llama.SetTopK(c.TopK),
llama.SetTokens(c.Maxtokens),
llama.SetThreads(c.Threads),
}
if c.Mirostat != 0 {
predictOptions = append(predictOptions, llama.SetMirostat(c.Mirostat))
}
if c.MirostatETA != 0 {
predictOptions = append(predictOptions, llama.SetMirostatETA(c.MirostatETA))
}
if c.MirostatTAU != 0 {
predictOptions = append(predictOptions, llama.SetMirostatTAU(c.MirostatTAU))
}
if c.Debug {
predictOptions = append(predictOptions, llama.Debug)
}
predictOptions = append(predictOptions, llama.SetStopWords(c.StopWords...))
if c.RepeatPenalty != 0 {
predictOptions = append(predictOptions, llama.SetPenalty(c.RepeatPenalty))
}
if c.Keep != 0 {
predictOptions = append(predictOptions, llama.SetNKeep(c.Keep))
}
if c.Batch != 0 {
predictOptions = append(predictOptions, llama.SetBatch(c.Batch))
}
if c.F16 {
predictOptions = append(predictOptions, llama.EnableF16KV)
}
if c.IgnoreEOS {
predictOptions = append(predictOptions, llama.IgnoreEOS)
}
if c.Seed != 0 {
predictOptions = append(predictOptions, llama.SetSeed(c.Seed))
}
return predictOptions
}
func ModelInference(s string, loader *model.ModelLoader, c Config, tokenCallback func(string) bool) (func() (string, error), error) {
supportStreams := false
modelFile := c.Model
@ -198,56 +254,7 @@ func ModelInference(s string, loader *model.ModelLoader, c Config, tokenCallback
model.SetTokenCallback(tokenCallback)
}
// Generate the prediction using the language model
predictOptions := []llama.PredictOption{
llama.SetTemperature(c.Temperature),
llama.SetTopP(c.TopP),
llama.SetTopK(c.TopK),
llama.SetTokens(c.Maxtokens),
llama.SetThreads(c.Threads),
}
if c.Mirostat != 0 {
predictOptions = append(predictOptions, llama.SetMirostat(c.Mirostat))
}
if c.MirostatETA != 0 {
predictOptions = append(predictOptions, llama.SetMirostatETA(c.MirostatETA))
}
if c.MirostatTAU != 0 {
predictOptions = append(predictOptions, llama.SetMirostatTAU(c.MirostatTAU))
}
if c.Debug {
predictOptions = append(predictOptions, llama.Debug)
}
predictOptions = append(predictOptions, llama.SetStopWords(c.StopWords...))
if c.RepeatPenalty != 0 {
predictOptions = append(predictOptions, llama.SetPenalty(c.RepeatPenalty))
}
if c.Keep != 0 {
predictOptions = append(predictOptions, llama.SetNKeep(c.Keep))
}
if c.Batch != 0 {
predictOptions = append(predictOptions, llama.SetBatch(c.Batch))
}
if c.F16 {
predictOptions = append(predictOptions, llama.EnableF16KV)
}
if c.IgnoreEOS {
predictOptions = append(predictOptions, llama.IgnoreEOS)
}
if c.Seed != 0 {
predictOptions = append(predictOptions, llama.SetSeed(c.Seed))
}
predictOptions := buildLLamaPredictOptions(c)
str, er := model.Predict(
s,