Skip to content

Featherless provider: max_tokens #1474

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
SBrandeis merged 7 commits into from
May 23, 2025
Merged

Featherless provider: max_tokens #1474

Changes from 1 commit
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
beef3d1
featherless max_tokens
pohnean May 21, 2025
6ec9766
Update packages/inference/src/providers/featherless-ai.ts
pohnean May 22, 2025
f9d0213
reformatting
pohnean May 22, 2025
c3b56b5
Merge branch 'huggingface:main' into main
pohnean May 22, 2025
6533eea
Merge remote-tracking branch 'origin/main' into pohnean/main
SBrandeis May 23, 2025
ee6dde7
lint
SBrandeis May 23, 2025
bc1b8ec
Merge branch 'main' into main
SBrandeis May 23, 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: 8 additions & 2 deletions packages/inference/src/providers/featherless-ai.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,6 +7,7 @@ import type {
import { InferenceOutputError } from "../lib/InferenceOutputError";
import type { BodyParams } from "../types";
import { BaseConversationalTask, BaseTextGenerationTask } from "./providerHelper";
import { omit } from "../utils/omit";

interface FeatherlessAITextCompletionOutput extends Omit<ChatCompletionOutput, "choices"> {
choices: Array<{
Expand All @@ -33,9 +34,14 @@ export class FeatherlessAITextGenerationTask extends BaseTextGenerationTask {

override preparePayload(params: BodyParams<TextGenerationInput>): Record<string, unknown> {
return {
...params.args,
...params.args.parameters,
model: params.model,
...omit(params.args, ["inputs", "parameters"]),
...(params.args.parameters
? {
max_tokens: (params.args.parameters as Record<string, unknown>).max_new_tokens,
...omit(params.args.parameters as Record<string, unknown>, "max_new_tokens"),
}
: undefined),
prompt: params.args.inputs,
};
}
Expand Down
Loading