dearwolf/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2025-06-27 13:15:00 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 22

chore(llama-ggml): drop deprecated backend

Browse source 
The GGML format is now dead, since in the next version of LocalAI we
already bring many breaking compatibility changes, taking the occasion
also to drop ggml support (pre-gguf).

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto 2025-02-06 16:44:31 +01:00
parent 8d45670e41
commit 695935c184
6 changed files with 7 additions and 348 deletions
Download patch file Download diff file Expand all files Collapse all files

71
core/http/app_test.go
View file

@ -526,77 +526,6 @@ var _ = Describe("API test", func() {
Expect(content["usage"]).To(ContainSubstring("You can test this model with curl like this"))
})
It("runs openllama(llama-ggml backend)", Label("llama"), func() {
if runtime.GOOS != "linux" {
Skip("test supported only on linux")
}
response := postModelApplyRequest("http://127.0.0.1:9090/models/apply", modelApplyRequest{
URL: "github:go-skynet/model-gallery/openllama_3b.yaml",
Name: "openllama_3b",
Overrides: map[string]interface{}{"backend": "llama-ggml", "mmap": true, "f16": true, "context_size": 128},
})
Expect(response["uuid"]).ToNot(BeEmpty(), fmt.Sprint(response))
uuid := response["uuid"].(string)
Eventually(func() bool {
response := getModelStatus("http://127.0.0.1:9090/models/jobs/" + uuid)
return response["processed"].(bool)
}, "360s", "10s").Should(Equal(true))
By("testing completion")
resp, err := client.CreateCompletion(context.TODO(), openai.CompletionRequest{Model: "openllama_3b", Prompt: "Count up to five: one, two, three, four, "})
Expect(err).ToNot(HaveOccurred())
Expect(len(resp.Choices)).To(Equal(1))
Expect(resp.Choices[0].Text).To(ContainSubstring("five"))
By("testing functions")
resp2, err := client.CreateChatCompletion(
context.TODO(),
openai.ChatCompletionRequest{
Model: "openllama_3b",
Messages: []openai.ChatCompletionMessage{
{
Role: "user",
Content: "What is the weather like in San Francisco (celsius)?",
},
},
Functions: []openai.FunctionDefinition{
openai.FunctionDefinition{
Name: "get_current_weather",
Description: "Get the current weather",
Parameters: jsonschema.Definition{
Type: jsonschema.Object,
Properties: map[string]jsonschema.Definition{
"location": {
Type: jsonschema.String,
Description: "The city and state, e.g. San Francisco, CA",
},
"unit": {
Type: jsonschema.String,
Enum: []string{"celcius", "fahrenheit"},
},
},
Required: []string{"location"},
},
},
},
})
Expect(err).ToNot(HaveOccurred())
Expect(len(resp2.Choices)).To(Equal(1))
Expect(resp2.Choices[0].Message.FunctionCall).ToNot(BeNil())
Expect(resp2.Choices[0].Message.FunctionCall.Name).To(Equal("get_current_weather"), resp2.Choices[0].Message.FunctionCall.Name)
var res map[string]string
err = json.Unmarshal([]byte(resp2.Choices[0].Message.FunctionCall.Arguments), &res)
Expect(err).ToNot(HaveOccurred())
Expect(res["location"]).To(ContainSubstring("San Francisco"), fmt.Sprint(res))
Expect(res["unit"]).To(Equal("celcius"), fmt.Sprint(res))
Expect(string(resp2.Choices[0].FinishReason)).To(Equal("function_call"), fmt.Sprint(resp2.Choices[0].FinishReason))
})
It("runs openllama gguf(llama-cpp)", Label("llama-gguf"), func() {
if runtime.GOOS != "linux" {
Skip("test supported only on linux")