Skip to content

local-apps: update llama.cpp snippet #1103

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

Merged
merged 2 commits into from
Jan 17, 2025
Merged

local-apps: update llama.cpp snippet #1103

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
e0a8f36
local-apps: update llama.cpp snippet
ngxson Jan 14, 2025
8a69d7d
fix test case
ngxson Jan 14, 2025
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
10 changes: 2 additions & 8 deletions packages/tasks/src/local-apps.spec.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,11 +13,7 @@ describe("local-apps", () => {
const snippet = snippetFunc(model);

expect(snippet[0].content).toEqual(`# Load and run the model:
llama-cli \\
--hf-repo "bartowski/Llama-3.2-3B-Instruct-GGUF" \\
--hf-file {{GGUF_FILE}} \\
-p "You are a helpful assistant" \\
--conversation`);
llama-cli -hf bartowski/Llama-3.2-3B-Instruct-GGUF`);
});

it("llama.cpp non-conversational", async () => {
Expand All @@ -30,9 +26,7 @@ llama-cli \\
const snippet = snippetFunc(model);

expect(snippet[0].content).toEqual(`# Load and run the model:
llama-cli \\
--hf-repo "mlabonne/gemma-2b-GGUF" \\
--hf-file {{GGUF_FILE}} \\
llama-cli -hf mlabonne/gemma-2b-GGUF \\
-p "Once upon a time,"`);
});

Expand Down
15 changes: 9 additions & 6 deletions packages/tasks/src/local-apps.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -95,17 +95,20 @@ function isMlxModel(model: ModelData) {
}

const snippetLlamacpp = (model: ModelData, filepath?: string): LocalAppSnippet[] => {
let tagName = "";
if (filepath) {
const quantLabel = parseGGUFQuantLabel(filepath);
tagName = quantLabel ? `:${quantLabel}` : "";
}
const command = (binary: string) => {
const snippet = [
"# Load and run the model:",
`${binary} \\`,
` --hf-repo "${model.id}" \\`,
` --hf-file ${filepath ?? "{{GGUF_FILE}}"} \\`,
` -p "${model.tags.includes("conversational") ? "You are a helpful assistant" : "Once upon a time,"}"`,
`${binary} -hf ${model.id}${tagName}`,
];
if (model.tags.includes("conversational")) {
if (!model.tags.includes("conversational")) {
// for non-conversational models, add a prompt
snippet[snippet.length - 1] += " \\";
snippet.push(" --conversation");
snippet.push(" -p \"Once upon a time,\"");
}
return snippet.join("\n");
};
Expand Down
Loading