feat: bump llama.cpp, add gguf support (#943)

**Description**

This PR syncs up the `llama` backend to use `gguf`
(https://github.com/go-skynet/go-llama.cpp/pull/180). It also adds
`llama-stable` to the targets so we can still load ggml. It adapts the
current tests to use the `llama-backend` for ggml and uses a `gguf`
model to run tests on the new backend.

In order to consume the new version of go-llama.cpp, it also bump go to
1.21 (images, pipelines, etc)

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto 2023-08-24 01:18:58 +02:00 committed by GitHub
parent 704323b805
commit 1120847f72
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
7 changed files with 89 additions and 16 deletions

View file

@ -296,7 +296,7 @@ var _ = Describe("API test", func() {
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", "mmap": true, "f16": true, "context_size": 128},
Overrides: map[string]interface{}{"backend": "llama-stable", "mmap": true, "f16": true, "context_size": 128},
})
Expect(response["uuid"]).ToNot(BeEmpty(), fmt.Sprint(response))
@ -359,6 +359,76 @@ var _ = Describe("API test", func() {
Expect(string(resp2.Choices[0].FinishReason)).To(Equal("function_call"), fmt.Sprint(resp2.Choices[0].FinishReason))
})
It("runs openllama gguf", Label("llama-gguf"), 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-gguf.yaml",
Name: "openllama_3b_gguf",
Overrides: map[string]interface{}{"backend": "llama", "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_gguf", 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_gguf",
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(Equal("San Francisco, California"), 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 gpt4all", Label("gpt4all"), func() {
if runtime.GOOS != "linux" {
Skip("test supported only on linux")