Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

[Models] Add Phi3-mini, StableLM 1.6B, Qwen 1.8B, update MLC runtime #433

Merged
merged 1 commit into from
May 29, 2024
Merged

[Models] Add Phi3-mini, StableLM 1.6B, Qwen 1.8B, update MLC runtime #433

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
55 changes: 29 additions & 26 deletions examples/json-mode/src/json_mode.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,37 +1,40 @@
import * as webllm from "@mlc-ai/web-llm";

function setLabel(id: string, text: string) {
const label = document.getElementById(id);
if (label == null) {
throw Error("Cannot find label " + id);
}
label.innerText = text;
const label = document.getElementById(id);
if (label == null) {
throw Error("Cannot find label " + id);
}
label.innerText = text;
}

async function main() {
const initProgressCallback = (report: webllm.InitProgressReport) => {
setLabel("init-label", report.text);
};
const selectedModel = "Llama-2-7b-chat-hf-q4f32_1";
const engine: webllm.MLCEngineInterface = await webllm.CreateMLCEngine(
selectedModel,
{ initProgressCallback: initProgressCallback }
);
const initProgressCallback = (report: webllm.InitProgressReport) => {
setLabel("init-label", report.text);
};
const selectedModel = "Llama-3-8B-Instruct-q4f32_1";
const engine: webllm.MLCEngineInterface = await webllm.CreateMLCEngine(
selectedModel,
{ initProgressCallback: initProgressCallback },
);

const request: webllm.ChatCompletionRequest = {
stream: false, // works with streaming, logprobs, top_logprobs as well
messages: [
{ "role": "user", "content": "Write a short JSON file introducing yourself." }
],
n: 2,
max_gen_len: 128,
response_format: { type: "json_object" } as webllm.ResponseFormat
};
const request: webllm.ChatCompletionRequest = {
stream: false, // works with streaming, logprobs, top_logprobs as well
messages: [
{
role: "user",
content: "Write a short JSON file introducing yourself.",
},
],
n: 2,
max_gen_len: 128,
response_format: { type: "json_object" } as webllm.ResponseFormat,
};

const reply0 = await engine.chatCompletion(request);
console.log(reply0);
console.log("First reply's last choice:\n" + await engine.getMessage());
console.log(await engine.runtimeStatsText());
const reply0 = await engine.chatCompletion(request);
console.log(reply0);
console.log("First reply's last choice:\n" + (await engine.getMessage()));
console.log(await engine.runtimeStatsText());
}

main();
18 changes: 9 additions & 9 deletions examples/json-schema/src/json_schema.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -38,8 +38,8 @@ async function simpleStructuredTextExample() {
setLabel("init-label", report.text);
};
const engine: webllm.MLCEngineInterface = await webllm.CreateMLCEngine(
"Llama-2-7b-chat-hf-q4f16_1",
{ initProgressCallback: initProgressCallback }
"Llama-3-8B-Instruct-q4f16_1",
{ initProgressCallback: initProgressCallback },
);

const request: webllm.ChatCompletionRequest = {
Expand Down Expand Up @@ -105,8 +105,8 @@ async function harryPotterExample() {
};

const engine: webllm.MLCEngineInterface = await webllm.CreateMLCEngine(
"Llama-2-7b-chat-hf-q4f16_1",
{ initProgressCallback: initProgressCallback }
"Llama-3-8B-Instruct-q4f16_1",
{ initProgressCallback: initProgressCallback },
);

const request: webllm.ChatCompletionRequest = {
Expand Down Expand Up @@ -138,7 +138,7 @@ async function functionCallingExample() {
Type.Object({
arguments: Type.Any(),
name: Type.String(),
})
}),
),
});
type T = Static<typeof T>;
Expand Down Expand Up @@ -170,12 +170,12 @@ async function functionCallingExample() {
setLabel("init-label", report.text);
};

const selectedModel = "Hermes-2-Pro-Mistral-7B-q4f16_1";
const selectedModel = "Hermes-2-Pro-Llama-3-8B-q4f16_1";
const engine: webllm.MLCEngineInterface = await webllm.CreateMLCEngine(
selectedModel,
{
initProgressCallback: initProgressCallback,
}
},
);

const request: webllm.ChatCompletionRequest = {
Expand All @@ -184,12 +184,12 @@ async function functionCallingExample() {
{
role: "system",
content: `You are a function calling AI model. You are provided with function signatures within <tools></tools> XML tags. You may call one or more functions to assist with the user query. Don't make assumptions about what values to plug into functions. Here are the available tools: <tools> ${JSON.stringify(
tools
tools,
)} </tools>. Do not stop calling functions until the task has been accomplished or you've reached max iteration of 10.
Calling multiple functions at once can overload the system and increase cost so call one function at a time please.
If you plan to continue with analysis, always call another function.
Return a valid json object (using double quotes) in the following schema: ${JSON.stringify(
schema
schema,
)}.`,
},
{
Expand Down
Loading
Loading