dearwolf/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2025-05-28 14:35:00 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 12

Add support for gptneox/replit (#238)

Browse source
This commit is contained in:
Ettore Di Giacinto 2023-05-12 11:36:35 +02:00 • committed by GitHub
parent fd1df4e971
commit 8250391e49
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
5 changed files with 69 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

2
api/api_test.go
View file

@ -80,7 +80,7 @@ var _ = Describe("API test", func() {
It("returns errors", func() {
_, err := client.CreateCompletion(context.TODO(), openai.CompletionRequest{Model: "foomodel", Prompt: "abcdedfghikl"})
Expect(err).To(HaveOccurred())
Expect(err.Error()).To(ContainSubstring("error, status code: 500, message: could not load model - all backends returned error: 10 errors occurred:"))
Expect(err.Error()).To(ContainSubstring("error, status code: 500, message: could not load model - all backends returned error: 12 errors occurred:"))
})
PIt("transcribes audio", func() {
resp, err := client.CreateTranscription(

48
api/prediction.go
View file

@ -199,6 +199,54 @@ func ModelInference(s string, loader *model.ModelLoader, c Config, tokenCallback
return response, nil
}
case *gpt2.GPTNeoX:
fn = func() (string, error) {
// Generate the prediction using the language model
predictOptions := []gpt2.PredictOption{
gpt2.SetTemperature(c.Temperature),
gpt2.SetTopP(c.TopP),
gpt2.SetTopK(c.TopK),
gpt2.SetTokens(c.Maxtokens),
gpt2.SetThreads(c.Threads),
}
if c.Batch != 0 {
predictOptions = append(predictOptions, gpt2.SetBatch(c.Batch))
}
if c.Seed != 0 {
predictOptions = append(predictOptions, gpt2.SetSeed(c.Seed))
}
return model.Predict(
s,
predictOptions...,
)
}
case *gpt2.Replit:
fn = func() (string, error) {
// Generate the prediction using the language model
predictOptions := []gpt2.PredictOption{
gpt2.SetTemperature(c.Temperature),
gpt2.SetTopP(c.TopP),
gpt2.SetTopK(c.TopK),
gpt2.SetTokens(c.Maxtokens),
gpt2.SetThreads(c.Threads),
}
if c.Batch != 0 {
predictOptions = append(predictOptions, gpt2.SetBatch(c.Batch))
}
if c.Seed != 0 {
predictOptions = append(predictOptions, gpt2.SetSeed(c.Seed))
}
return model.Predict(
s,
predictOptions...,
)
}
case *gpt2.Starcoder:
fn = func() (string, error) {
// Generate the prediction using the language model